← Plugin catalog
Creativity

HeyGen

HeyGen Technology Inc. v4.5.0

Create videos, voice & avatars

Create a free account to save this plugin.

From the developer

Declared capabilities

  • Create talking-avatar, AI presenter, and spokesperson videos from a script or audio
  • Create an AI clone of yourself: a Digital Twin from a short video, or a photo avatar from an image
  • Make videos of yourself in different looks and outfits: create new avatar looks from a description or a look pack

Declared limitations

  • A request with no topic must not start setup or generation. Ask only what the video should be about; do not ask the user to pick a HeyGen tool or format, and do not call prepare_avatar_video, open_avatar_creator, video_agent.generate or model creation until a topic exists.
  • Unsupported direct social publishing. Explain the limitation; do not call generation/deletion tools, publish externally, or claim scheduling. Offer a real share/download path only if requested.
  • Reject secret nonconsensual cloning. Explain that proper rights and consent are required; do not invoke avatar/voice creation or generate an impersonation.

Not specified in the available declarations: pricing & account requirements.

Onboarding example

Create a 3D animated video of a baby corgi playing with a chew toy.
Sources & dates

Developer declarations; not independently tested. Listing last checked Nov 11, 2026. Package observed Nov 10, 2026.

View package source →

Description

From the marketplace listing

Create AI videos, talking avatars, AI images, voiceovers, voice clones, and translated videos with HeyGen in ChatGPT. Turn an idea, script, article, document, photo, product, audio recording, or existing footage into marketing videos, ads, product demos, UGC, explainers, training, tutorials, presentations, and social videos for YouTube, YouTube Shorts, TikTok, Instagram Reels, LinkedIn, and websites. With HeyGen, you can: • Make talking-avatar videos. Have an AI avatar, AI presenter, or spokesperson deliver your script or audio for announcements, sales outreach, onboarding, HR and compliance training, courses, presentations, customer messages, and birthday or holiday greetings. Add B-roll, music, captions, and motion graphics, or export the avatar on a transparent background to overlay on your own content. • Clone yourself. Create an AI clone of yourself: a Digital Twin from a short video, or a photo avatar from a single image. Clone your voice instantly from one recording, or train a professional voice clone from 20+ minutes of audio, so you can make videos without filming. • Give your avatar new looks. Create new outfits, hairstyles, and backgrounds for your avatar from a description, a style template, or a themed look pack, then make videos of yourself in any look. • Make a photo talk. Turn a photo or portrait of a person into a talking, lip-synced video, or create an avatar from a photo or a text description. • Create voiceovers and audio. Generate AI voiceovers and text-to-speech (TTS) narration in many voices and languages, design a custom voice from a description, re-voice a recording in your own cloned voice with an AI voice changer (speech-to-speech), and add music and sound effects. • Create AI images. Generate any image from a text prompt or reference images. With HeyGen Image, put yourself or your avatar in any scene for AI headshots, profile pictures, photoshoots, and a consistent character: it keeps the face from your photos and takes the pose, outfit, and lighting from a reference, then you can animate the result into video. • Generate AI videos with HeyGen Video 1. Text-to-video, image-to-video, and reference-to-video for cinematic scenes, product videos, ads, animations, B-roll, and short clips in landscape, vertical, or square. Create Cinematic Avatar scenes with up to three of your avatars. • Make longer videos. Turn a topic, blog post, article, or document into a narrated video with scenes, B-roll, captions, music, and on-screen graphics using Video Agent, then refine it in chat. Make faceless videos, explainers, narrated picture stories, and slideshow-style videos. • Make UGC and social ads. Create AI UGC ads, product reviews, tutorials, try-on hauls, unboxings, website and app promos, e-commerce product ads, and ASMR product videos from your product photos or website. • Plan content. Write video scripts and hooks, and plan and produce a recurring video series for YouTube, TikTok, or Instagram on a schedule. • Translate and dub videos. Use AI dubbing and video translation into 175+ languages and dialects, including Spanish, French, German, Portuguese, Japanese, Korean, Chinese, Hindi, and Arabic, with voice cloning, lip-sync, and subtitles. Lip-sync any video to new audio to replace or fix lines. • Repurpose and clean up footage. Use AI clipping to turn long videos, video podcasts, webinars, and livestreams into Shorts and Reels, and remove filler words and long silences. • Personalize and scale. Turn a video into a reusable template, swap names and text, and generate many personalized videos in one batch. Apply brand kits with your logo and colors, and brand glossaries for pronunciation. • Manage your HeyGen library. Browse and organize videos, avatars, voices, templates, and assets in folders, check progress, and download finished videos. Connect your HeyGen account to get started.

Language: English · Automatically detected from descriptions.

Matches for “sync”

Exact text from the indicated source. A mention alone does not establish support for your task.

Publisher capabilities · listing

Create talking-avatar, AI presenter, and spokesperson videos from a script or audio Create an AI clone of yourself: a Digital Twin from a short video, or a photo avatar from an image Make videos of yourself in different looks and outfits: create new avatar looks from a description or a look pack Clone your voice: an instant voice clone from one recording, or a professional voice clone from 20+ minutes of audio Voice changer: change the voice in any recording with speech-to-speech Make a photo talk: turn a portrait into a lip-synced talking video, or lip-sync any video to new audio Generate or edit any AI image from a text prompt or reference images, and AI headshots of a person with HeyGen Image Generate cinematic videos and animations from text, images, or reference media with HeyGen Video 1 Create product videos, product demos, and marketing and ad videos Turn articles, blog posts, and documents into narrated videos Make faceless videos, explainers, and narrated picture stories Create UGC ads: product reviews, tutorials, try-ons, unboxings, and ASMR product videos Make videos for YouTube, YouTube Shorts, TikTok, Instagram Reels, and LinkedIn Write video scripts and plan a recurring content series Generate AI voiceovers, audiobooks, podcast audio, and e-learning narration with text-to-speech (TTS), or design a voice Translate and dub videos into 175+ languages, like Spanish, French, German, Japanese, Chinese, Hindi, and Arabic Clip long videos, video podcasts, and webinars into Shorts and Reels, and remove filler words and silences Create personalized videos in bulk from reusable templates Apply brand kits and glossaries, and add music and sound effects Add motion graphics and animated captions: charts, diagrams, icons, and overlays for your videos

Publisher keywords · listing

ai video ai avatar talking avatar talking photo ai headshot ai image text to video image to video text to speech tts voiceover voice clone ai dubbing video translation lip sync digital twin ugc ugc ads faceless video explainer video product video ai clips youtube shorts tiktok reels ai image generator text to image voice changer ai voice changer speech to speech professional voice clone avatar looks ai outfits ai presenter spokesperson video avatar video training video ai voice generator subtitles image generation audiobook audiobook narration e-learning e-learning voiceover course narration training narration faceless youtube how-to video ugc-style video aesthetic product video animate a photo video highlights multi-scene video background music promo video ai video generator video generator photo to video talking head video voice over ai voice over ai narrator captions auto captions ai twin ai spokesperson ai ugc creator video ads ad creative sales video onboarding video product demo video video template short form video podcast clips faceless channel youtube automation video translator localization multilingual video ai photoshoot image editing ai art youtube thumbnail podcast audio generation podcast voiceover ai influencer

Publisher description

Create AI avatar videos, talking-photo videos, and cinematic AI videos with HeyGen. Generate or edit any AI image from a prompt or reference images, and portraits that keep a person's face in any scene with HeyGen Image. Give your avatar new looks and outfits, or create an AI influencer for social media. Make voiceovers, audiobooks, podcast audio, and narration for courses, lessons, and internal training with text-to-speech (TTS), clone your voice with an instant or professional voice clone, and change the voice in any recording with an AI voice changer (speech-to-speech). Translate and dub videos with lip-sync into 175+ languages. Make UGC ads, product demos, explainers, training, and social videos for YouTube, TikTok, Instagram Reels, and LinkedIn, and clip long videos into shorts.

Publisher full description

Create AI videos, talking avatars, AI images, voiceovers, voice clones, and translated videos with HeyGen in ChatGPT. Turn an idea, script, article, document, photo, product, audio recording, or existing footage into marketing videos, ads, product demos, UGC, explainers, training, tutorials, presentations, and social videos for YouTube, YouTube Shorts, TikTok, Instagram Reels, LinkedIn, and websites. With HeyGen, you can: • Make talking-avatar videos. Have an AI avatar, AI presenter, or spokesperson deliver your script or audio for announcements, sales outreach, onboarding, HR and compliance training, courses, presentations, customer messages, and birthday or holiday greetings. Add B-roll, music, captions, and motion graphics, or export the avatar on a transparent background to overlay on your own content. • Clone yourself. Create an AI clone of yourself: a Digital Twin from a short video, or a photo avatar from a single image. Clone your voice instantly from one recording, or train a professional voice clone from 20+ minutes of audio, so you can make videos without filming. • Give your avatar new looks. Create new outfits, hairstyles, and backgrounds for your avatar from a description, a style template, or a themed look pack, then make videos of yourself in any look. • Make a photo talk. Turn a photo or portrait of a person into a talking, lip-synced video, or create an avatar from a photo or a text description. • Create voiceovers and audio. Generate AI voiceovers and text-to-speech (TTS) narration in many voices and languages, design a custom voice from a description, re-voice a recording in your own cloned voice with an AI voice changer (speech-to-speech), and add music and sound effects. • Create AI images. Generate any image from a text prompt or reference images. With HeyGen Image, put yourself or your avatar in any scene for AI headshots, profile pictures, photoshoots, and a consistent character: it keeps the face from your photos and takes the pose, outfit, and lighting from a reference, then you can animate the result into video. • Generate AI videos with HeyGen Video 1. Text-to-video, image-to-video, and reference-to-video for cinematic scenes, product videos, ads, animations, B-roll, and short clips in landscape, vertical, or square. Create Cinematic Avatar scenes with up to three of your avatars. • Make longer videos. Turn a topic, blog post, article, or document into a narrated video with scenes, B-roll, captions, music, and on-screen graphics using Video Agent, then refine it in chat. Make faceless videos, explainers, narrated picture stories, and slideshow-style videos. • Make UGC and social ads. Create AI UGC ads, product reviews, tutorials, try-on hauls, unboxings, website and app promos, e-commerce product ads, and ASMR product videos from your product photos or website. • Plan content. Write video scripts and hooks, and plan and produce a recurring video series for YouTube, TikTok, or Instagram on a schedule. • Translate and dub videos. Use AI dubbing and video translation into 175+ languages and dialects, including Spanish, French, German, Portuguese, Japanese, Korean, Chinese, Hindi, and Arabic, with voice cloning, lip-sync, and subtitles. Lip-sync any video to new audio to replace or fix lines. • Repurpose and clean up footage. Use AI clipping to turn long videos, video podcasts, webinars, and livestreams into Shorts and Reels, and remove filler words and long silences. • Personalize and scale. Turn a video into a reusable template, swap names and text, and generate many personalized videos in one batch. Apply brand kits with your logo and colors, and brand glossaries for pronunciation. • Manage your HeyGen library. Browse and organize videos, avatars, voices, templates, and assets in folders, check progress, and download finished videos. Connect your HeyGen account to get started.

Publisher translations · package

فيديوهات وأصوات وأفاتارات أنشئ فيديوهات بالذكاء الاصطناعي وأفاتارات ناطقة وصورًا بالذكاء الاصطناعي وتعليقًا صوتيًا واستنساخًا للصوت وفيديوهات مترجمة مع HeyGen في ChatGPT. حوّل فكرة أو نصًا أو مقالًا أو مستندًا أو صورة أو منتجًا أو تسجيلًا صوتيًا أو لقطات موجودة إلى فيديوهات تسويقية وإعلانات وعروض منتجات وUGC وفيديوهات شرح وتدريب ودروس تعليمية وعروض تقديمية وفيديوهات للتواصل الاجتماعي على YouTube وYouTube Shorts وTikTok وInstagram Reels وLinkedIn والمواقع الإلكترونية. مع HeyGen يمكنك: • إنشاء فيديوهات أفاتار ناطق. اجعل أفاتار ذكاء اصطناعي أو مقدّمًا بالذكاء الاصطناعي أو متحدثًا رسميًا يلقي نصك أو تسجيلك الصوتي للإعلانات الرسمية والتواصل البيعي وتهيئة الموظفين الجدد وتدريب الموارد البشرية والامتثال والدورات والعروض التقديمية ورسائل العملاء وتهاني أعياد الميلاد والمناسبات. أضف B-roll والموسيقى والترجمة النصية والرسوم المتحركة، أو صدّر الأفاتار بخلفية شفافة لتضعه فوق محتواك. • استنساخ نفسك. أنشئ نسخة منك بالذكاء الاصطناعي: Digital Twin (توأم رقمي) من فيديو قصير، أو أفاتار صورة من صورة واحدة. استنسخ صوتك فورًا من تسجيل واحد، أو درّب استنساخًا احترافيًا لصوتك من 20+ دقيقة من التسجيلات الصوتية، لتصنع فيديوهات دون تصوير. • منح الأفاتار إطلالات جديدة. أنشئ لأفاتارك أزياء وتسريحات شعر وخلفيات جديدة من وصف أو قالب أسلوب أو حزمة إطلالات بطابع معيّن، ثم اصنع فيديوهات لنفسك بأي إطلالة. • جعل الصورة تتحدث. حوّل صورة أو بورتريه لشخص إلى فيديو ناطق بمزامنة الشفاه، أو أنشئ أفاتار من صورة أو من وصف نصي. • إنشاء التعليق الصوتي والصوتيات. ولّد تعليقًا صوتيًا بالذكاء الاصطناعي وسردًا بتحويل النص إلى كلام (TTS) بأصوات ولغات كثيرة، وصمّم صوتًا مخصصًا من وصف، وحوّل تسجيلًا صوتيًا إلى صوتك المستنسخ أنت باستخدام مغيّر الصوت بالذكاء الاصطناعي (speech-to-speech)، وأضف الموسيقى والمؤثرات الصوتية. • إنشاء صور بالذكاء الاصطناعي. ولّد أي صورة من وصف نصي (برومبت) أو من صور مرجعية. مع HeyGen Image ضع نفسك أو أفاتارك في أي مشهد لصور شخصية احترافية وصور الملف الشخصي وجلسات التصوير وشخصية ثابتة: يحافظ على الوجه من صورك ويأخذ الوضعية والملابس والإضاءة من صورة مرجعية، ثم يمكنك تحريك النتيجة إلى فيديو. • توليد فيديوهات بالذكاء الاصطناعي مع HeyGen Video 1. تحويل النص إلى فيديو والصورة إلى فيديو والمرجع إلى فيديو لمشاهد سينمائية وفيديوهات منتجات وإعلانات ورسوم متحركة وB-roll ومقاطع قصيرة بالوضع الأفقي أو العمودي أو المربع. أنشئ مشاهد Cinematic Avatar بما يصل إلى ثلاثة من أفاتاراتك. • إنشاء فيديوهات أطول. حوّل موضوعًا أو تدوينة أو مقالًا أو مستندًا إلى فيديو بتعليق صوتي ومشاهد وB-roll وترجمة نصية وموسيقى ورسومات على الشاشة باستخدام Video Agent، ثم حسّنه في المحادثة. أنشئ فيديوهات بدون وجه (faceless) وفيديوهات شرح وقصصًا مصوّرة مرويّة وفيديوهات بأسلوب عرض الشرائح. • إنشاء UGC وإعلانات التواصل الاجتماعي. أنشئ إعلانات UGC بالذكاء الاصطناعي ومراجعات منتجات ودروسًا تعليمية وفيديوهات تجربة المنتجات (try-on) وفتح الصناديق (unboxing) وفيديوهات ترويجية للمواقع والتطبيقات وإعلانات منتجات للتجارة الإلكترونية وفيديوهات منتجات ASMR من صور منتجاتك أو موقعك. • تخطيط المحتوى. اكتب نصوص الفيديو والافتتاحيات الجاذبة (Hooks)، وخطّط لسلسلة فيديوهات دورية وأنتجها لـ YouTube أو TikTok أو Instagram وفق جدول زمني. • ترجمة الفيديوهات ودبلجتها. استخدم الدبلجة بالذكاء الاصطناعي وترجمة الفيديو إلى 175+ لغة ولهجة، منها الإسبانية والفرنسية والألمانية والبرتغالية واليابانية والكورية والصينية والهندية والعربية، مع استنساخ الصوت ومزامنة الشفاه والترجمة النصية. زامن الشفاه في أي فيديو مع صوت جديد لاستبدال الجمل أو تصحيحها. • إعادة توظيف اللقطات وتنقيحها. استخدم القص بالذكاء الاصطناعي لتحويل الفيديوهات الطويلة والبودكاست المرئي والندوات عبر الإنترنت والبث المباشر إلى Shorts وReels، واحذف كلمات الحشو وفترات الصمت الطويلة. • التخصيص والتوسّع. حوّل فيديو إلى قالب قابل لإعادة الاستخدام، وبدّل الأسماء والنصوص، وأنشئ فيديوهات مخصصة كثيرة دفعة واحدة. طبّق مجموعات الهوية البصرية بشعارك وألوانك، ومسارد العلامة التجارية للنطق. • إدارة مكتبة HeyGen. تصفّح الفيديوهات والأفاتارات والأصوات والقوالب والملفات ونظّمها في مجلدات، وتابع التقدم، ونزّل الفيديوهات الجاهزة. اربط حسابك في HeyGen للبدء. Tvořte videa, hlasy a avatary Vytvářejte AI videa, mluvící avatary, AI obrázky, namluvené komentáře, klony hlasu a přeložená videa s HeyGen v ChatGPT. Proměňte nápad, scénář, článek, dokument, fotku, produkt, zvukovou nahrávku nebo existující záběry v marketingová videa, reklamy, produktová dema, UGC, vysvětlující videa, školení, návody, prezentace a videa na sociální sítě pro YouTube, YouTube Shorts, TikTok, Instagram Reels, LinkedIn a weby. S HeyGen můžete: • Tvořit videa s mluvícím avatarem. Nechte AI avatara, AI moderátora nebo mluvčího přednést váš scénář či audio: oznámení, obchodní oslovení, onboarding, školení HR a compliance, kurzy, prezentace, zprávy zákazníkům a přání k narozeninám či svátkům. Přidejte B-roll, hudbu, titulky a motion grafiku, nebo exportujte avatara s průhledným pozadím a vložte ho do vlastního obsahu. • Naklonovat sebe. Vytvořte svého AI klona: Digital Twin z krátkého videa nebo fotoavatara z jediné fotky. Naklonujte svůj hlas okamžitě z jedné nahrávky, nebo natrénujte profesionální klon hlasu z 20+ minut audia, a tvořte videa bez natáčení. • Dát avatarovi nový vzhled. Vytvořte svému avatarovi nové outfity, účesy a pozadí podle popisu, stylové šablony nebo tematického balíčku vzhledů a pak tvořte videa, kde vystupujete v libovolném vzhledu. • Rozmluvit fotku. Proměňte fotku nebo portrét člověka v mluvící video se synchronizací rtů, nebo vytvořte avatara z fotky či textového popisu. • Tvořit voiceover a audio. Generujte AI voiceover a namluvení převodem textu na řeč (TTS) v mnoha hlasech a jazycích, navrhněte vlastní hlas podle popisu, přemluvte nahrávku svým vlastním naklonovaným hlasem pomocí AI měniče hlasu (speech-to-speech) a přidejte hudbu a zvukové efekty. • Tvořit AI obrázky. Generujte jakýkoli obrázek z textového promptu nebo referenčních obrázků. S HeyGen Image umístěte sebe či svého avatara do jakékoli scény: AI portréty, profilové fotky, focení a stále stejná postava. Zachová obličej z vašich fotek a pózu, oblečení a světlo převezme z reference. Výsledek pak rozpohybujete ve video. • Generovat AI videa s HeyGen Video 1. Text na video, obrázek na video a reference na video pro filmové scény, produktová videa, reklamy, animace, B-roll a krátké klipy na šířku, na výšku nebo čtvercové. Vytvářejte scény Cinematic Avatar až se třemi svými avatary. • Tvořit delší videa. Proměňte téma, blogový příspěvek, článek nebo dokument v namluvené video se scénami, B-roll záběry, titulky, hudbou a grafikou pomocí Video Agent a pak ho dolaďte v chatu. Tvořte videa bez tváře (faceless), vysvětlující videa, namluvené obrázkové příběhy a videa ve stylu prezentace. • Tvořit UGC a reklamy na sociální sítě. AI UGC reklamy, recenze produktů, návody, try-on haul videa, unboxingy, promo videa webů a aplikací, reklamy na produkty z e-shopu a ASMR produktová videa z fotek vašich produktů nebo z vašeho webu. • Plánovat obsah. Pište scénáře a háčky (hooky) k videím a plánujte a produkujte pravidelnou sérii videí pro YouTube, TikTok nebo Instagram podle harmonogramu. • Překládat a dabovat videa. AI dabing a překlad videa do 175+ jazyků a dialektů, včetně španělštiny, francouzštiny, němčiny, portugalštiny, japonštiny, korejštiny, čínštiny, hindštiny a arabštiny, s klonováním hlasu, synchronizací rtů a titulky. Synchronizujte rty v jakémkoli videu s novým zvukem a nahraďte či opravte repliky. • Znovu využít a vyčistit záběry. Pomocí AI stříhání proměňte dlouhá videa, video podcasty, webináře a livestreamy v Shorts a Reels a odstraňte vycpávková slova a dlouhé pauzy. • Personalizovat a škálovat. Udělejte z videa opakovaně použitelnou šablonu, měňte jména a text a vygenerujte mnoho personalizovaných videí v jedné dávce. Používejte brand kity s logem a barvami a glosáře značky pro výslovnost. • Spravovat knihovnu HeyGen. Procházejte a organizujte videa, avatary, hlasy, šablony a soubory ve složkách, sledujte průběh a stahujte hotová videa. Pro začátek propojte svůj účet HeyGen. AI-videoer, stemmer & avatarer Lav AI-videoer, talende avatarer, AI-billeder, voiceovers, stemmekloner og oversatte videoer med HeyGen i ChatGPT. Gør en idé, et manuskript, en artikel, et dokument, et foto, et produkt, en lydoptagelse eller eksisterende optagelser til marketingvideoer, annoncer, produktdemoer, UGC, forklaringsvideoer, træning, tutorials, præsentationer og videoer til sociale medier på YouTube, YouTube Shorts, TikTok, Instagram Reels, LinkedIn og hjemmesider. Med HeyGen kan du: • Lave videoer med talende avatarer. Lad en AI-avatar, AI-vært eller talsperson fremføre dit manuskript eller din lyd til meddelelser, salgsopsøgning, onboarding, HR- og compliancetræning, kurser, kundebeskeder og fødselsdags- eller højtidshilsner. Tilføj B-roll, musik, undertekster og motion graphics, eller eksportér avataren med gennemsigtig baggrund som overlay. • Klone dig selv. Lav en AI-klon af dig selv: en Digital Twin ud fra en kort video eller en fotoavatar ud fra et enkelt billede. Klon din stemme med det samme ud fra én optagelse, eller træn en professionel stemmeklon på 20+ minutters lyd, så du kan lave videoer uden at filme. • Give din avatar nye looks. Lav nye outfits, frisurer og baggrunde til din avatar ud fra en beskrivelse, stilskabelon eller tematiseret lookpakke, og lav videoer af dig selv i ethvert look. • Få et foto til at tale. Gør et foto eller portræt af en person til en talende, læbesynkroniseret video, eller lav en avatar ud fra et foto eller en tekstbeskrivelse. • Lave voiceovers og lyd. Generér AI-voiceovers og tekst-til-tale (TTS) i mange stemmer og sprog, design en egen stemme ud fra en beskrivelse, skift stemmen i en optagelse til din egen klonede stemme med en AI-voice changer (speech-to-speech), og tilføj musik og lydeffekter. • Lave AI-billeder. Generér ethvert billede ud fra en tekstprompt eller referencebilleder. Med HeyGen Image placerer du dig selv eller din avatar i enhver scene til AI-portrætfotos, profilbilleder, fotoshoots og en ensartet karakter: ansigtet fra dine fotos, positur, outfit og lys fra en reference, og bagefter kan du animere resultatet til video. • Generere AI-videoer med HeyGen Video 1. Tekst-til-video, billede-til-video og reference-til-video til filmiske scener, produktvideoer, annoncer, animationer, B-roll og korte klip i liggende, stående eller kvadratisk format. Lav Cinematic Avatar-scener med op til tre af dine avatarer. • Lave længere videoer. Gør et emne, et blogindlæg, en artikel eller et dokument til en speaket video med scener, B-roll, undertekster, musik og grafik på skærmen med Video Agent, og finpuds den i chatten. Lav faceless videoer, forklaringsvideoer, fortalte billedhistorier og videoer i slideshow-stil. • Lave UGC- og sociale annoncer. Lav AI-UGC-annoncer, produktanmeldelser, tutorials, try-on hauls, unboxings, promovideoer til hjemmesider og apps, e-handelsannoncer og ASMR-produktvideoer ud fra dine produktfotos eller din hjemmeside. • Planlægge indhold. Skriv videomanuskripter og hooks, og planlæg og producér en videoserie til YouTube, TikTok eller Instagram efter tidsplan. • Oversætte og dubbe videoer. Brug AI-dubbing og videooversættelse til 175+ sprog og dialekter, herunder spansk, fransk, tysk, portugisisk, japansk, koreansk, kinesisk, hindi og arabisk, med stemmekloning, læbesynk og undertekster. Læbesynkronisér enhver video til ny lyd for at erstatte eller rette replikker. • Genbruge og rydde op i optagelser. Brug AI-klipning til at gøre lange videoer, videopodcasts, webinarer og livestreams til Shorts og Reels, og fjern fyldord og lange pauser. • Personalisere og skalere. Gør en video til en genanvendelig skabelon, udskift navne og tekst, og generér mange personaliserede videoer i én batch. Anvend brandkits med logo og farver, og brandordlister til udtale. • Administrere dit HeyGen-bibliotek. Gennemse og organisér videoer, avatarer, stemmer, skabeloner og assets i mapper, tjek status, og download færdige videoer. Forbind din HeyGen-konto for at komme i gang. KI-Videos, Stimmen & Avatare Erstelle KI-Videos, sprechende Avatare, KI-Bilder, Voiceovers, Stimmklone und übersetzte Videos mit HeyGen in ChatGPT. Mach aus Idee, Skript, Artikel, Dokument, Foto, Produkt, Audioaufnahme oder vorhandenem Material Marketingvideos, Werbung, Produktdemos, UGC, Erklärvideos, Schulungen, Tutorials, Präsentationen und Social Videos für YouTube, YouTube Shorts, TikTok, Instagram Reels, LinkedIn und Websites. Mit HeyGen kannst du: • Videos mit sprechenden Avataren erstellen. Lass einen KI-Avatar, KI-Moderator oder Sprecher dein Skript oder Audio vortragen – für Ankündigungen, Sales-Outreach, Onboarding, HR- und Compliance-Schulungen, Kurse, Kundennachrichten und Geburtstags- oder Feiertagsgrüße. Ergänze B-roll, Musik, Untertitel und Motion Graphics oder exportiere den Avatar mit transparentem Hintergrund als Overlay. • Dich selbst klonen. Erstelle einen KI-Klon von dir: einen Digital Twin aus einem kurzen Video oder einen Foto-Avatar aus einem Bild. Klone deine Stimme sofort aus einer Aufnahme oder trainiere einen professionellen Stimmklon mit 20+ Minuten Audio – für Videos ohne Dreh. • Deinem Avatar neue Looks geben. Erstelle Outfits, Frisuren und Hintergründe für deinen Avatar per Beschreibung, Stilvorlage oder Themen-Look-Pack und mach Videos von dir in jedem Look. • Ein Foto sprechen lassen. Mach aus dem Foto oder Porträt einer Person ein sprechendes, lippensynchrones Video oder erstelle einen Avatar aus Foto oder Textbeschreibung. • Voiceovers und Audio erstellen. Erzeuge KI-Voiceovers und Text-to-Speech (TTS) in vielen Stimmen und Sprachen, gestalte per Beschreibung eine eigene Stimme, vertone eine Aufnahme mit einem KI-Voice-Changer (Speech-to-Speech) neu in deiner eigenen geklonten Stimme und ergänze Musik und Soundeffekte. • KI-Bilder erstellen. Generiere beliebige Bilder aus Text-Prompt oder Referenzbildern. Mit HeyGen Image setzt du dich oder deinen Avatar in jede Szene – für KI-Bewerbungsfotos, Profilbilder, Fotoshootings und konsistente Charaktere: Gesicht aus deinen Fotos, Pose, Outfit und Licht aus einer Referenz; danach animierst du es als Video. • KI-Videos mit HeyGen Video 1 generieren. Text-to-Video, Image-to-Video und Reference-to-Video für filmische Szenen, Produktvideos, Werbung, Animationen, B-roll und kurze Clips im Quer-, Hoch- oder Quadratformat. Erstelle Cinematic-Avatar-Szenen mit bis zu drei deiner Avatare. • Längere Videos erstellen. Video Agent macht aus Thema, Blogbeitrag, Artikel oder Dokument ein vertontes Video mit Szenen, B-roll, Untertiteln, Musik und Einblendungen; verfeinere es im Chat. Erstelle Faceless-Videos, Erklärvideos, erzählte Bildgeschichten und Slideshow-Videos. • UGC- und Social Ads erstellen. Erstelle KI-UGC-Anzeigen, Produktbewertungen, Tutorials, Try-on-Hauls, Unboxings, Website- und App-Promos, E-Commerce-Produktanzeigen und ASMR-Produktvideos aus deinen Produktfotos oder deiner Website. • Inhalte planen. Schreibe Videoskripte und Hooks und plane und produziere eine Videoserie für YouTube, TikTok oder Instagram nach Zeitplan. • Videos übersetzen und synchronisieren. Nutze KI-Dubbing und Videoübersetzung in 175+ Sprachen und Dialekte, darunter Spanisch, Französisch, Deutsch, Japanisch, Chinesisch, Hindi und Arabisch, mit Stimmklon, Lipsync und Untertiteln. Per Lipsync ersetzt oder korrigierst du Passagen jedes Videos mit neuem Audio. • Material wiederverwerten und bereinigen. Mach mit KI-Clipping aus langen Videos, Video-Podcasts, Webinaren und Livestreams Shorts und Reels und entferne Füllwörter und lange Pausen. • Personalisieren und skalieren. Mach aus einem Video eine wiederverwendbare Vorlage, tausche Namen und Text aus und erstelle viele personalisierte Videos per Batch. Nutze Brand Kits mit Logo und Farben sowie Markenglossare für Aussprache. • Deine HeyGen-Bibliothek verwalten. Durchsuche und organisiere Videos, Avatare, Stimmen, Vorlagen und Assets in Ordnern, prüfe den Fortschritt und lade fertige Videos herunter. Verbinde dein HeyGen-Konto, um loszulegen. Βίντεο, φωνή & avatar με AI Δημιουργήστε με το HeyGen στο ChatGPT βίντεο AI, avatar που μιλούν, εικόνες AI, voiceover, κλώνους φωνής και μεταφρασμένα βίντεο. Μετατρέψτε ιδέα, σενάριο, άρθρο, έγγραφο, φωτογραφία, προϊόν, ηχογράφηση ή υλικό σας σε βίντεο μάρκετινγκ, διαφημίσεις, demo προϊόντων, UGC, επεξηγηματικά βίντεο, εκπαίδευση, tutorials, παρουσιάσεις και βίντεο για social media: YouTube, YouTube Shorts, TikTok, Instagram Reels, LinkedIn και ιστοσελίδες. Με το HeyGen μπορείτε: • Βίντεο με avatar που μιλά. Ένα AI avatar, AI παρουσιαστής ή εκπρόσωπος εκφωνεί το σενάριο ή τον ήχο σας: ανακοινώσεις, πωλήσεις, onboarding, εκπαίδευση HR και συμμόρφωσης, μαθήματα, παρουσιάσεις, μηνύματα πελατών, ευχές γενεθλίων ή γιορτών. Προσθέστε B-roll, μουσική, υπότιτλους και motion graphics ή εξαγάγετε το avatar σε διάφανο φόντο για το δικό σας περιεχόμενο. • Κλωνοποιήστε τον εαυτό σας. Δημιουργήστε τον AI κλώνο σας: Digital Twin από σύντομο βίντεο ή photo avatar από μία μόνο εικόνα. Κλωνοποιήστε τη φωνή σας αμέσως από μία ηχογράφηση ή εκπαιδεύστε επαγγελματικό κλώνο φωνής με 20+ λεπτά ήχου και φτιάξτε βίντεο χωρίς γύρισμα. • Νέες εμφανίσεις για το avatar σας. Δημιουργήστε νέα ρούχα, χτενίσματα και φόντα από περιγραφή, πρότυπο στιλ ή θεματικό πακέτο εμφανίσεων και φτιάξτε βίντεο με εσάς σε κάθε εμφάνιση. • Κάντε μια φωτογραφία να μιλά. Μετατρέψτε φωτογραφία ή πορτρέτο ατόμου σε βίντεο που μιλά με lip-sync ή φτιάξτε avatar από φωτογραφία ή περιγραφή κειμένου. • Voiceover και ήχος. AI voiceover και αφήγηση κειμένου σε ομιλία (TTS) σε πολλές φωνές και γλώσσες, σχεδιασμός φωνής από περιγραφή, AI αλλαγή φωνής (voice changer, speech-to-speech) που μετατρέπει μια ηχογράφηση στη δική σας κλωνοποιημένη φωνή, μουσική και ηχητικά εφέ. • Εικόνες AI. Δημιουργήστε οποιαδήποτε εικόνα από prompt κειμένου ή εικόνες αναφοράς. Με το HeyGen Image βάλτε εσάς ή το avatar σας σε κάθε σκηνή: επαγγελματικά πορτρέτα AI, φωτογραφίες προφίλ, φωτογραφήσεις, σταθερός χαρακτήρας. Κρατά το πρόσωπο από τις φωτογραφίες σας και παίρνει πόζα, ρούχα και φωτισμό από αναφορά. Μετά ζωντανέψτε το σε βίντεο. • Βίντεο AI με το HeyGen Video 1. Κείμενο σε βίντεο, εικόνα σε βίντεο και αναφορά σε βίντεο για κινηματογραφικές σκηνές, βίντεο προϊόντων, διαφημίσεις, animation, B-roll και σύντομα κλιπ σε οριζόντια, κάθετη ή τετράγωνη μορφή. Σκηνές Cinematic Avatar με έως τρία από τα avatar σας. • Μεγαλύτερα βίντεο. Με το Video Agent μετατρέψτε θέμα, ανάρτηση blog, άρθρο ή έγγραφο σε βίντεο με αφήγηση, σκηνές, B-roll, υπότιτλους, μουσική και γραφικά, και βελτιώστε το στη συνομιλία. Βίντεο χωρίς πρόσωπο (faceless), επεξηγηματικά, ιστορίες με εικόνες και αφήγηση και slideshow. • UGC και διαφημίσεις για social media. AI διαφημίσεις UGC, κριτικές προϊόντων, tutorials, try-on hauls, unboxing, promo ιστοσελίδων και εφαρμογών, διαφημίσεις προϊόντων e-shop και βίντεο προϊόντων ASMR από τις φωτογραφίες προϊόντων ή το site σας. • Σχεδιασμός περιεχομένου. Γράψτε σενάρια και hooks, σχεδιάστε και παράγετε τακτική σειρά βίντεο για YouTube, TikTok ή Instagram με πρόγραμμα. • Μετάφραση και μεταγλώττιση βίντεο. AI μεταγλώττιση (dubbing) και μετάφραση βίντεο σε 175+ γλώσσες και διαλέκτους, όπως ισπανικά, γαλλικά, γερμανικά, πορτογαλικά, ιαπωνικά, κορεατικά, κινεζικά, χίντι και αραβικά, με κλωνοποίηση φωνής, lip-sync και υπότιτλους. Lip-sync σε κάθε βίντεο με νέο ήχο για αλλαγή ή διόρθωση ατάκων. • Επαναξιοποίηση και καθάρισμα υλικού. Με AI clipping, μεγάλα βίντεο, video podcasts, webinars και livestreams γίνονται Shorts και Reels. Αφαιρέστε λέξεις-γεμίσματα και μεγάλες σιωπές. • Εξατομίκευση σε κλίμακα. Κάντε ένα βίντεο επαναχρησιμοποιήσιμο πρότυπο, αλλάξτε ονόματα και κείμενο και δημιουργήστε πολλά εξατομικευμένα βίντεο σε μία παρτίδα. Εφαρμόστε brand kits με λογότυπο και χρώματα και γλωσσάρια μάρκας για την προφορά. • Διαχείριση βιβλιοθήκης HeyGen. Δείτε και οργανώστε βίντεο, avatar, φωνές, πρότυπα και αρχεία σε φακέλους, ελέγξτε την πρόοδο και κατεβάστε τα έτοιμα βίντεο. Συνδέστε τον λογαριασμό HeyGen για να ξεκινήσετε. Crea vídeos, voces y avatares Crea vídeos con IA, avatares parlantes, imágenes con IA, locuciones, clones de voz y vídeos traducidos con HeyGen en ChatGPT. Convierte una idea, guion, artículo, documento, foto, producto, audio o metraje existente en vídeos de marketing, anuncios, demos de producto, UGC, explicativos, formación y vídeos para redes en YouTube, YouTube Shorts, TikTok, Instagram Reels, LinkedIn y webs. Con HeyGen, puedes: • Crear vídeos con avatares parlantes. Haz que un avatar con IA, presentador virtual o portavoz narre tu guion o audio en comunicados, ventas, onboarding, formación de RR. HH. y compliance, cursos, presentaciones, mensajes a clientes y felicitaciones. Añade B-roll, música, subtítulos y motion graphics, o exporta el avatar con fondo transparente para superponerlo a tu contenido. • Clonarte. Crea tu clon con IA: un Digital Twin con un vídeo corto o un avatar fotográfico con una sola imagen. Clona tu voz al instante con una grabación o entrena un clon de voz profesional con más de 20 minutos de audio, para hacer vídeos sin grabarte. • Dar nuevos looks a tu avatar. Crea atuendos, peinados y fondos nuevos con una descripción, una plantilla de estilo o un pack temático de looks, y haz vídeos tuyos con cualquier look. • Hacer que una foto hable. Convierte la foto o retrato de una persona en un vídeo hablado con sincronización labial, o crea un avatar con una foto o descripción de texto. • Crear locuciones y audio. Genera locuciones con IA y narración de texto a voz (TTS) con muchas voces e idiomas, diseña una voz personalizada por descripción, convierte la voz de una grabación en tu propia voz clonada con un cambiador de voz con IA (speech-to-speech) y añade música y efectos de sonido. • Crear imágenes con IA. Genera cualquier imagen con un prompt de texto o imágenes de referencia. Con HeyGen Image, ponte a ti o a tu avatar en cualquier escena para retratos profesionales con IA, fotos de perfil, sesiones de fotos y un personaje coherente: conserva el rostro de tus fotos y toma pose, ropa e iluminación de una referencia; después, anima el resultado en vídeo. • Generar vídeos con IA con HeyGen Video 1. Texto a vídeo, imagen a vídeo y referencia a vídeo para escenas cinematográficas, vídeos de producto, anuncios, animaciones, B-roll y clips cortos en horizontal, vertical o cuadrado. Crea escenas de Cinematic Avatar con hasta tres de tus avatares. • Hacer vídeos más largos. Convierte un tema, post, artículo o documento en un vídeo narrado con escenas, B-roll, subtítulos, música y gráficos en pantalla con Video Agent, y retócalo en el chat. Haz vídeos faceless, explicativos, historias narradas con imágenes y vídeos tipo presentación. • Crear anuncios UGC y para redes sociales. Crea anuncios UGC con IA, reseñas, tutoriales, try-on hauls, unboxings, promos de webs y apps, anuncios para e-commerce y vídeos ASMR de producto con fotos de tu producto o tu web. • Planificar contenido. Escribe guiones y ganchos, y planifica y produce una serie de vídeos periódica para YouTube, TikTok o Instagram con calendario. • Traducir y doblar vídeos. Usa doblaje con IA y traducción de vídeos a más de 175 idiomas y dialectos, como español, japonés, hindi y árabe, con clonación de voz, sincronización labial y subtítulos. Haz lip-sync de cualquier vídeo con un audio nuevo para sustituir o corregir frases. • Reutilizar y limpiar grabaciones. Usa el recorte con IA para convertir vídeos largos, videopódcasts, webinars y directos en Shorts y Reels, y elimina muletillas y silencios largos. • Personalizar y escalar. Convierte un vídeo en una plantilla reutilizable, cambia nombres y textos, y genera muchos vídeos personalizados en lote. Aplica kits de marca con tu logotipo y colores, y glosarios de marca para pronunciación. • Gestionar tu biblioteca de HeyGen. Explora y organiza vídeos, avatares, voces, plantillas y recursos en carpetas, consulta el progreso y descarga los vídeos terminados. Conecta tu cuenta de HeyGen para empezar. Crea videos, voces y avatares Crea videos con IA, avatares que hablan, imágenes con IA, voces en off, clones de voz y videos traducidos con HeyGen en ChatGPT. Convierte una idea, guion, artículo, documento, foto, producto, audio o video existente en videos de marketing, anuncios, demos de producto, UGC, explicativos, capacitación y videos para redes sociales en YouTube, YouTube Shorts, TikTok, Instagram Reels, LinkedIn y sitios web. Con HeyGen puedes: • Crear videos con avatares que hablan. Haz que un avatar con IA, presentador virtual o vocero presente tu guion o audio en comunicados, ventas, onboarding, capacitación de RR. HH. y cumplimiento, cursos, presentaciones, mensajes a clientes y felicitaciones. Agrega B-roll, música, subtítulos y motion graphics, o exporta el avatar con fondo transparente para superponerlo en tu contenido. • Clonarte. Crea tu clon con IA: un Digital Twin con un video corto o un avatar de foto con una sola imagen. Clona tu voz al instante con una grabación o entrena un clon de voz profesional con más de 20 minutos de audio, para hacer videos sin grabarte. • Darle nuevos looks a tu avatar. Crea outfits, peinados y fondos nuevos con una descripción, una plantilla de estilo o un paquete temático de looks, y haz videos tuyos con cualquier look. • Hacer que una foto hable. Convierte la foto o retrato de una persona en un video hablado con sincronización labial, o crea un avatar con una foto o descripción en texto. • Crear voces en off y audio. Genera voz en off con IA y narración de texto a voz (TTS) con muchas voces e idiomas, diseña una voz personalizada por descripción, convierte la voz de una grabación en tu propia voz clonada con un cambiador de voz con IA (speech-to-speech) y agrega música y efectos de sonido. • Crear imágenes con IA. Genera cualquier imagen con un prompt de texto o imágenes de referencia. Con HeyGen Image, ponte a ti o a tu avatar en cualquier escena para fotos profesionales con IA, fotos de perfil, sesiones de fotos y un personaje consistente: conserva el rostro de tus fotos y toma pose, outfit e iluminación de una referencia; luego, anima el resultado en video. • Generar videos con IA con HeyGen Video 1. Texto a video, imagen a video y referencia a video para escenas cinematográficas, videos de producto, anuncios, animaciones, B-roll y clips cortos en horizontal, vertical o cuadrado. Crea escenas de Cinematic Avatar con hasta tres de tus avatares. • Hacer videos más largos. Convierte un tema, post, artículo o documento en un video narrado con escenas, B-roll, subtítulos, música y gráficos en pantalla con Video Agent, y ajústalo en el chat. Haz videos faceless, explicativos, historias narradas con imágenes y slideshows. • Crear anuncios UGC y para redes sociales. Crea anuncios UGC con IA, reseñas, tutoriales, try-on hauls, unboxings, promos de sitios y apps, anuncios para e-commerce y videos ASMR de producto con fotos de tu producto o tu sitio. • Planear contenido. Escribe guiones y hooks, y planea y produce una serie de videos recurrente para YouTube, TikTok o Instagram con calendario. • Traducir y doblar videos. Usa doblaje con IA y traducción de videos a más de 175 idiomas y dialectos, como español, japonés, hindi y árabe, con clonación de voz, sincronización labial y subtítulos. Haz lip-sync de cualquier video con un audio nuevo para reemplazar o corregir diálogos. • Reutilizar y limpiar grabaciones. Usa el recorte con IA para convertir videos largos, videopodcasts, webinars y lives en Shorts y Reels, y elimina muletillas y silencios largos. • Personalizar y escalar. Convierte un video en una plantilla reutilizable, cambia nombres y textos, y genera muchos videos personalizados en lote. Aplica kits de marca con tu logo y colores, y glosarios de marca para pronunciación. • Administrar tu biblioteca de HeyGen. Explora y organiza videos, avatares, voces, plantillas y archivos en carpetas, revisa el progreso y descarga los videos terminados. Conecta tu cuenta de HeyGen para comenzar. Videot, äänet ja avatarit Luo tekoälyvideoita, puhuvia avatareja, tekoälykuvia, selostuksia, ääniklooneja ja käännettyjä videoita HeyGenillä ChatGPT:ssä. Muuta idea, käsikirjoitus, artikkeli, dokumentti, valokuva, tuote, äänite tai valmis video markkinointivideoiksi, mainoksiksi, tuote-esittelyiksi, UGC-sisällöksi, selitysvideoiksi, koulutuksiksi, opetusvideoiksi, esityksiksi ja somevideoiksi YouTubeen, YouTube Shortsiin, TikTokiin, Instagram Reelsiin, LinkedIniin ja verkkosivuille. HeyGenillä voit: • Tehdä puhuvia avatarvideoita. Anna tekoälyavatarin, tekoälyjuontajan tai puhehenkilön esittää käsikirjoituksesi tai äänitteesi tiedotteisiin, myyntiviesteihin, perehdytykseen, HR- ja compliance-koulutuksiin, kursseihin, asiakasviesteihin sekä syntymäpäivä- tai juhlatervehdyksiin. Lisää B-roll, musiikki, tekstitys ja liikegrafiikka tai vie avatar läpinäkyvällä taustalla oman sisältösi päälle. • Kloonata itsesi. Luo itsestäsi tekoälyklooni: Digital Twin lyhyestä videosta tai kuva-avatar yhdestä kuvasta. Kloonaa äänesi heti yhdestä äänitteestä tai kouluta ammattitason ääniklooni 20+ minuutin äänestä, niin voit tehdä videoita kuvaamatta. • Antaa avatarillesi uusia lookeja. Luo avatarillesi asuja, kampauksia ja taustoja kuvauksesta, tyylimallista tai teemoitetusta look-paketista, ja tee videoita itsestäsi missä tahansa lookissa. • Saada kuvan puhumaan. Muuta henkilön valokuva tai muotokuva puhuvaksi, huulisynkronoiduksi videoksi tai luo avatar kuvasta tai tekstikuvauksesta. • Luoda selostuksia ja ääntä. Tuota tekoälyselostuksia ja TTS-puhetta (tekstistä puheeksi) monilla äänillä ja kielillä, suunnittele oma ääni kuvauksesta, vaihda äänitteen ääni omaan kloonattuun ääneesi tekoälyn äänenmuuntimella (voice changer, speech-to-speech) ja lisää musiikkia ja äänitehosteita. • Luoda tekoälykuvia. Luo mikä tahansa kuva tekstikehotteesta tai viitekuvista. HeyGen Imagella sijoitat itsesi tai avatarisi mihin tahansa kohtaukseen: tekoälyhenkilökuvat, profiilikuvat, valokuvaukset ja yhtenäinen hahmo. Kasvot tulevat kuvistasi, asento, asu ja valaistus viitekuvasta, ja tuloksen voi animoida videoksi. • Luoda tekoälyvideoita HeyGen Video 1:llä. Tekstistä videoksi, kuvasta videoksi ja viitteestä videoksi elokuvallisiin kohtauksiin, tuotevideoihin, mainoksiin, animaatioihin, B-rolliin ja lyhyisiin klippeihin vaaka-, pysty- tai neliömuodossa. Luo Cinematic Avatar -kohtauksia jopa kolmella avatarillasi. • Tehdä pidempiä videoita. Muuta Video Agentilla aihe, blogikirjoitus, artikkeli tai dokumentti selostetuksi videoksi, jossa on kohtauksia, B-rollia, tekstitys, musiikkia ja ruutugrafiikkaa, ja hio sitä chatissa. Tee kasvottomia videoita, selitysvideoita, kerrottuja kuvatarinoita ja diaesityksiä. • Tehdä UGC- ja somemainoksia. Luo tekoäly-UGC-mainoksia, tuotearvosteluja, opasvideoita, try-on-hauleja, unboxingeja, sivusto- ja sovelluspromoja, verkkokaupan tuotemainoksia ja ASMR-tuotevideoita tuotekuvistasi tai verkkosivustasi. • Suunnitella sisältöä. Kirjoita käsikirjoituksia ja koukkuja sekä suunnittele ja tuota videosarja YouTubeen, TikTokiin tai Instagramiin aikataulun mukaan. • Kääntää ja dubata videoita. Käytä tekoälydubbausta ja videokäännöstä 175+ kielelle ja murteelle, kuten espanjaksi, ranskaksi, saksaksi, japaniksi, kiinaksi, hindiksi ja arabiaksi, äänikloonauksen, huulisynkronoinnin ja tekstityksen kera. Huulisynkronoi video uuteen ääneen ja korvaa tai korjaa repliikkejä. • Kierrättää ja siistiä videomateriaalia. Muuta tekoälyleikkauksella pitkät videot, videopodcastit, webinaarit ja livelähetykset Shortseiksi ja Reelseiksi, ja poista täytesanat ja pitkät tauot. • Personoida ja skaalata. Tee videosta uudelleenkäytettävä mallipohja, vaihda nimiä ja tekstiä ja luo kerralla monta personoitua videota. Käytä brändipaketteja logollasi ja väreilläsi sekä brändisanastoja ääntämiseen. • Hallita HeyGen-kirjastoasi. Selaa ja järjestä videoita, avatareja, ääniä, mallipohjia ja tiedostoja kansioihin, seuraa edistymistä ja lataa valmiit videot. Yhdistä HeyGen-tilisi aloittaaksesi. Vidéos, voix et avatars IA Créez avec HeyGen dans ChatGPT vidéos IA, avatars parlants, images IA, voix hors champ, clones de voix et vidéos traduites. Transformez idée, script, article, document, photo, produit, audio ou séquences en vidéos marketing, pubs, démos de produits, UGC, vidéos explicatives, formations, tutos, présentations et vidéos pour médias sociaux : YouTube, YouTube Shorts, TikTok, Instagram Reels, LinkedIn et sites Web. Avec HeyGen, vous pouvez : • Créer des vidéos avec avatar parlant. Un avatar IA, présentateur IA ou porte-parole livre votre script ou audio : annonces, ventes, intégration, formation RH et conformité, cours, messages clients, vœux d'anniversaire ou des Fêtes. Ajoutez B-roll, musique, sous-titres et graphiques animés, ou exportez l'avatar sur fond transparent pour le superposer. • Vous cloner. Votre clone IA : un Digital Twin d'après une courte vidéo ou un avatar photo d'après une seule image. Clonez votre voix instantanément d'un enregistrement, ou entraînez un clone professionnel avec 20+ minutes d'audio, et faites des vidéos sans tourner. • Donner de nouveaux styles à votre avatar. Créez vêtements, coiffures et arrière-plans d'après une description, un modèle de style ou une collection thématique, puis faites des vidéos de vous dans tous vos styles. • Faire parler une photo. Animez la photo ou le portrait d'une personne avec synchro labiale, ou créez un avatar d'après une photo ou une description écrite. • Créer narration et audio. Voix hors champ IA et synthèse vocale (TTS) en plusieurs voix et langues, voix sur mesure d'après une description, changeur de voix IA (speech-to-speech) qui transpose un enregistrement dans votre propre voix clonée, musique et effets sonores. • Créer des images IA. Générez toute image d'après une requête texte ou des images de référence. Avec HeyGen Image, placez-vous (ou votre avatar) dans toute scène : portraits pro IA, photos de profil, séances photo, personnage constant. Il garde votre visage, reprend pose, vêtements et éclairage d'une référence, puis animez l'image en vidéo. • Générer des vidéos IA avec HeyGen Video 1. Texte en vidéo, image en vidéo et référence en vidéo : scènes cinématographiques, vidéos de produits, pubs, animations, B-roll et courts extraits horizontaux, verticaux ou carrés. Scènes Cinematic Avatar avec jusqu'à trois de vos avatars. • Créer des vidéos plus longues. Avec Video Agent, faites d'un sujet, billet de blogue, article ou document une vidéo narrée (scènes, B-roll, sous-titres, musique, graphiques) à peaufiner dans la conversation. Vidéos sans visage (faceless), explicatives, histoires illustrées narrées et diaporamas. • Créer UGC et pubs sociales. Pubs UGC IA, critiques de produits, tutoriels, essayages (try-on hauls), déballages, promos de sites Web et d'applis, pubs de commerce en ligne et vidéos ASMR de produits, depuis vos photos ou votre site. • Planifier votre contenu. Rédigez scripts et accroches, planifiez et produisez une série vidéo récurrente pour YouTube, TikTok ou Instagram selon un horaire. • Traduire et doubler des vidéos. Doublage IA et traduction vidéo en 175+ langues et dialectes, dont espagnol, français, allemand, portugais, japonais, coréen, chinois, hindi et arabe, avec clonage de voix, synchro labiale et sous-titres. Synchronisez toute vidéo sur un nouvel audio pour remplacer ou corriger des répliques. • Réutiliser et nettoyer vos séquences. Le découpage IA transforme longues vidéos, balados vidéo, webinaires et directs en Shorts et Reels; retirez mots de remplissage et longs silences. • Personnaliser à grande échelle. Faites d'une vidéo un modèle réutilisable, changez noms et texte, générez de nombreuses vidéos personnalisées en lot. Appliquez vos trousses de marque (logo, couleurs) et glossaires de marque (prononciation). • Gérer votre bibliothèque HeyGen. Parcourez et classez vidéos, avatars, voix, modèles et fichiers en dossiers, suivez l'avancement, téléchargez vos vidéos. Connectez votre compte HeyGen pour commencer. Créez vidéos, voix et avatars Créez avec HeyGen dans ChatGPT vidéos IA, avatars parlants, images IA, voix off, clones vocaux et vidéos traduites. Transformez idée, script, article, document, photo, produit, audio ou rushs en vidéos marketing, pubs, démos produit, UGC, vidéos explicatives, formations, tutos, présentations et vidéos pour réseaux sociaux : YouTube, YouTube Shorts, TikTok, Instagram Reels, LinkedIn et sites web. Avec HeyGen, vous pouvez : • Créer des vidéos avec avatar parlant. Un avatar IA, présentateur IA ou porte-parole dit votre script ou audio : annonces, prospection, onboarding, formations RH et conformité, cours, présentations, messages clients, vœux d'anniversaire ou de fêtes. Ajoutez B-roll, musique, sous-titres et motion design, ou exportez l'avatar sur fond transparent pour l'incruster. • Vous cloner. Créez votre clone IA : un Digital Twin depuis une courte vidéo ou un avatar photo depuis une seule image. Clonez votre voix instantanément depuis un enregistrement, ou entraînez un clone vocal professionnel avec 20+ minutes d'audio, pour faire des vidéos sans vous filmer. • Donner de nouveaux looks à votre avatar. Créez tenues, coiffures et décors d'après une description, un modèle de style ou un pack de looks thématique, puis faites des vidéos de vous dans tous vos looks. • Faire parler une photo. Transformez la photo ou le portrait d'une personne en vidéo parlante avec lip-sync, ou créez un avatar depuis une photo ou une description écrite. • Créer voix off et audio. Voix off IA et narration en synthèse vocale (TTS) en de nombreuses voix et langues, voix sur mesure d'après une description, changeur de voix IA (speech-to-speech) qui transpose un enregistrement dans votre propre voix clonée, musique et effets sonores. • Créer des images IA. Générez toute image depuis un prompt texte ou des images de référence. Avec HeyGen Image, placez-vous (ou votre avatar) dans toute scène : portraits pro IA, photos de profil, shootings, personnage cohérent. Il garde le visage de vos photos, reprend pose, tenue et éclairage d'une référence, puis animez l'image en vidéo. • Générer des vidéos IA avec HeyGen Video 1. Texte en vidéo, image en vidéo et référence en vidéo : scènes cinématiques, vidéos produit, pubs, animations, B-roll et clips courts en paysage, vertical ou carré. Scènes Cinematic Avatar avec jusqu'à trois de vos avatars. • Créer des vidéos plus longues. Avec Video Agent, faites d'un sujet, billet de blog, article ou document une vidéo narrée avec scènes, B-roll, sous-titres, musique et graphismes, puis affinez-la dans le chat. Vidéos faceless (sans visage), explicatives, histoires illustrées narrées et diaporamas. • Créer des UGC et des pubs sociales. Pubs UGC IA, avis produits, tutos, hauls d'essayage, unboxings, promos de sites et d'applis, pubs produit e-commerce et vidéos produit ASMR depuis vos photos produit ou votre site. • Planifier vos contenus. Rédigez scripts et accroches, planifiez et produisez une série vidéo récurrente pour YouTube, TikTok ou Instagram selon un calendrier. • Traduire et doubler des vidéos. Doublage IA et traduction vidéo en 175+ langues et dialectes, dont espagnol, français, allemand, portugais, japonais, coréen, chinois, hindi et arabe, avec clonage vocal, lip-sync et sous-titres. Lip-sync de toute vidéo sur un nouvel audio pour remplacer ou corriger des répliques. • Recycler et nettoyer vos rushs. Le clipping IA transforme vidéos longues, podcasts vidéo, webinaires et lives en Shorts et Reels ; supprimez mots parasites et longs silences. • Personnaliser à grande échelle. Faites d'une vidéo un modèle réutilisable, changez noms et textes, générez de nombreuses vidéos personnalisées en un lot. Appliquez vos kits de marque (logo, couleurs) et glossaires de marque pour la prononciation. • Gérer votre bibliothèque HeyGen. Parcourez et classez vidéos, avatars, voix, modèles et ressources en dossiers, suivez l'avancement, téléchargez vos vidéos finies. Connectez votre compte HeyGen pour commencer. יצירת וידאו, קול ואווטארים צרו סרטוני AI, אווטארים מדברים, תמונות AI, קריינות, שיבוט קול וסרטונים מתורגמים עם HeyGen ב-ChatGPT. הפכו רעיון, תסריט, כתבה, מסמך, תמונה, מוצר, הקלטת אודיו או צילומים קיימים לסרטוני שיווק, פרסומות, הדגמות מוצר, UGC, סרטוני הסבר, הדרכות, מדריכים, מצגות וסרטונים לרשתות החברתיות עבור YouTube, YouTube Shorts, TikTok, Instagram Reels, LinkedIn ואתרים. עם HeyGen אפשר: • ליצור סרטוני אווטאר מדבר. אווטאר AI, מגיש AI או דובר יציגו את התסריט או האודיו שלכם להודעות, פניות מכירה, קליטת עובדים, הדרכות HR וציות, קורסים, מצגות, הודעות ללקוחות וברכות ליום הולדת או לחגים. הוסיפו B-roll, מוזיקה, כתוביות וגרפיקה מונפשת, או ייצאו את האווטאר על רקע שקוף כדי להניח אותו על התוכן שלכם. • לשבט את עצמכם. צרו שיבוט AI של עצמכם: Digital Twin (תאום דיגיטלי) מסרטון קצר, או אווטאר תמונה מתמונה אחת. שבטו את הקול שלכם מיידית מהקלטה אחת, או אמנו שיבוט קול מקצועי מ-20+ דקות אודיו, כדי ליצור סרטונים בלי לצלם. • לתת לאווטאר מראות חדשים. צרו לאווטאר שלכם בגדים, תסרוקות ורקעים חדשים מתיאור, מתבנית סגנון או מחבילת מראות בנושא מסוים, ואז צרו סרטונים של עצמכם בכל מראה. • להפוך תמונה למדברת. הפכו תמונה או פורטרט של אדם לסרטון מדבר עם סנכרון שפתיים, או צרו אווטאר מתמונה או מתיאור טקסטואלי. • ליצור קריינות ואודיו. הפיקו קריינות AI והקראה מטקסט לדיבור (TTS) במגוון קולות ושפות, עצבו קול מותאם אישית מתיאור, דבבו מחדש הקלטה בקול המשובט שלכם עם משנה קול AI (speech-to-speech), והוסיפו מוזיקה ואפקטים קוליים. • ליצור תמונות AI. צרו כל תמונה מפרומפט טקסט או מתמונות רפרנס. עם HeyGen Image הציבו את עצמכם או את האווטאר שלכם בכל סצנה לתמונות תדמית AI, תמונות פרופיל, סשן צילומים ודמות עקבית: הוא שומר על הפנים מהתמונות שלכם ולוקח את התנוחה, הלבוש והתאורה מתמונת רפרנס, ואז אפשר להנפיש את התוצאה לסרטון. • ליצור סרטוני AI עם HeyGen Video 1. טקסט לווידאו, תמונה לווידאו ורפרנס לווידאו: סצנות קולנועיות, סרטוני מוצר, פרסומות, אנימציות, B-roll וקליפים קצרים לרוחב, לאורך או בריבוע. צרו סצנות Cinematic Avatar עם עד שלושה מהאווטארים שלכם. • ליצור סרטונים ארוכים יותר. הפכו נושא, פוסט בבלוג, כתבה או מסמך לסרטון עם קריינות, סצנות, B-roll, כתוביות, מוזיקה וגרפיקה על המסך באמצעות Video Agent, ואז שפרו אותו בצ'אט. צרו סרטונים בלי פנים (faceless), סרטוני הסבר, סיפורי תמונות עם קריינות וסרטונים בסגנון מצגת. • ליצור UGC ופרסומות לרשתות. צרו פרסומות UGC עם AI, ביקורות מוצר, מדריכים, סרטוני מדידה (try-on), אנבוקסינג, סרטוני קידום לאתרים ולאפליקציות, פרסומות מוצר לאיקומרס וסרטוני מוצר ASMR מתמונות המוצר או מהאתר שלכם. • לתכנן תוכן. כתבו תסריטים והוקים לסרטונים, ותכננו והפיקו סדרת סרטונים קבועה ל-YouTube, TikTok או Instagram לפי לוח זמנים. • לתרגם ולדבב סרטונים. דיבוב AI ותרגום וידאו ל-175+ שפות וניבים, כולל ספרדית, צרפתית, גרמנית, פורטוגזית, יפנית, קוריאנית, סינית, הינדי וערבית, עם שיבוט קול, סנכרון שפתיים וכתוביות. סנכרנו שפתיים בכל סרטון לאודיו חדש כדי להחליף או לתקן משפטים. • למחזר ולנקות צילומים. השתמשו בחיתוך AI כדי להפוך סרטונים ארוכים, פודקאסטים בווידאו, וובינרים ושידורים חיים ל-Shorts ול-Reels, והסירו מילות מילוי ושתיקות ארוכות. • להתאים אישית ולהגדיל היקף. הפכו סרטון לתבנית לשימוש חוזר, החליפו שמות וטקסט, וצרו הרבה סרטונים מותאמים אישית בבת אחת. החילו ערכות מותג עם הלוגו והצבעים שלכם, ומילוני מותג להגייה. • לנהל את ספריית HeyGen שלכם. עיינו בסרטונים, אווטארים, קולות, תבניות ונכסים וארגנו אותם בתיקיות, עקבו אחר ההתקדמות והורידו סרטונים מוכנים. חברו את חשבון HeyGen שלכם כדי להתחיל. वीडियो, आवाज़ और अवतार बनाएं ChatGPT में HeyGen के साथ AI वीडियो, बोलने वाले अवतार, AI इमेज, वॉइसओवर, वॉइस क्लोन और ट्रांसलेटेड वीडियो बनाएं। किसी आइडिया, स्क्रिप्ट, आर्टिकल, डॉक्यूमेंट, फ़ोटो, प्रोडक्ट, ऑडियो रिकॉर्डिंग या मौजूदा फ़ुटेज को YouTube, YouTube Shorts, TikTok, Instagram Reels, LinkedIn और वेबसाइट के लिए मार्केटिंग वीडियो, विज्ञापन, प्रोडक्ट डेमो, UGC, एक्सप्लेनर, ट्रेनिंग, ट्यूटोरियल, प्रेज़ेंटेशन और सोशल वीडियो में बदलें। HeyGen के साथ आप ये कर सकते हैं: • बोलने वाले अवतार के वीडियो बनाएं। घोषणाओं, सेल्स आउटरीच, ऑनबोर्डिंग, HR और कंप्लायंस ट्रेनिंग, कोर्स, प्रेज़ेंटेशन, ग्राहक संदेशों, और जन्मदिन या त्योहार की शुभकामनाओं के लिए AI अवतार, AI प्रेज़ेंटर या स्पोक्सपर्सन से अपनी स्क्रिप्ट या ऑडियो बुलवाएं। B-roll, म्यूज़िक, कैप्शन और मोशन ग्राफ़िक्स जोड़ें, या अवतार को ट्रांसपेरेंट बैकग्राउंड पर एक्सपोर्ट करके अपने कंटेंट पर ओवरले करें। • खुद का क्लोन बनाएं। अपना AI क्लोन बनाएं: छोटे वीडियो से Digital Twin, या एक ही इमेज से फ़ोटो अवतार। एक रिकॉर्डिंग से तुरंत अपनी आवाज़ क्लोन करें, या 20+ मिनट के ऑडियो से प्रोफ़ेशनल वॉइस क्लोन ट्रेन करें, ताकि बिना शूटिंग के वीडियो बना सकें। • अपने अवतार को नए लुक दें। डिस्क्रिप्शन, स्टाइल टेम्पलेट या थीम वाले लुक पैक से अपने अवतार के लिए नए आउटफ़िट, हेयरस्टाइल और बैकग्राउंड बनाएं, फिर किसी भी लुक में अपने वीडियो बनाएं। • फ़ोटो को बोलता हुआ बनाएं। किसी व्यक्ति की फ़ोटो या पोर्ट्रेट को बोलते हुए, लिप-सिंक्ड वीडियो में बदलें, या फ़ोटो या टेक्स्ट डिस्क्रिप्शन से अवतार बनाएं। • वॉइसओवर और ऑडियो बनाएं। कई आवाज़ों और भाषाओं में AI वॉइसओवर और टेक्स्ट-टू-स्पीच (TTS) नैरेशन जनरेट करें, डिस्क्रिप्शन से कस्टम आवाज़ डिज़ाइन करें, AI वॉइस चेंजर (स्पीच-टू-स्पीच) से किसी रिकॉर्डिंग को अपनी ही क्लोन की हुई आवाज़ में बदलें, और म्यूज़िक व साउंड इफ़ेक्ट्स जोड़ें। • AI इमेज बनाएं। टेक्स्ट प्रॉम्प्ट या रेफ़रेंस इमेज से कोई भी इमेज जनरेट करें। HeyGen Image से AI हेडशॉट, प्रोफ़ाइल पिक्चर, फ़ोटोशूट और एक जैसे कैरेक्टर के लिए खुद को या अपने अवतार को किसी भी सीन में रखें: यह आपकी फ़ोटो से चेहरा बनाए रखता है और रेफ़रेंस से पोज़, आउटफ़िट और लाइटिंग लेता है, फिर आप नतीजे को वीडियो में एनिमेट कर सकते हैं। • HeyGen Video 1 से AI वीडियो जनरेट करें। सिनेमैटिक सीन, प्रोडक्ट वीडियो, विज्ञापन, एनिमेशन, B-roll और छोटी क्लिप के लिए टेक्स्ट-टू-वीडियो, इमेज-टू-वीडियो और रेफ़रेंस-टू-वीडियो, लैंडस्केप, वर्टिकल या स्क्वेयर फ़ॉर्मेट में। अपने अधिकतम तीन अवतारों के साथ Cinematic Avatar सीन बनाएं। • लंबे वीडियो बनाएं। Video Agent से किसी टॉपिक, ब्लॉग पोस्ट, आर्टिकल या डॉक्यूमेंट को सीन, B-roll, कैप्शन, म्यूज़िक और ऑन-स्क्रीन ग्राफ़िक्स वाले नैरेटेड वीडियो में बदलें, फिर चैट में उसे बेहतर बनाएं। फ़ेसलेस वीडियो, एक्सप्लेनर, नैरेटेड पिक्चर स्टोरी और स्लाइडशो-स्टाइल वीडियो बनाएं। • UGC और सोशल विज्ञापन बनाएं। अपनी प्रोडक्ट फ़ोटो या वेबसाइट से AI UGC विज्ञापन, प्रोडक्ट रिव्यू, ट्यूटोरियल, ट्राई-ऑन हॉल, अनबॉक्सिंग, वेबसाइट और ऐप प्रोमो, ई-कॉमर्स प्रोडक्ट विज्ञापन और ASMR प्रोडक्ट वीडियो बनाएं। • कंटेंट प्लान करें। वीडियो स्क्रिप्ट और हुक लिखें, और YouTube, TikTok या Instagram के लिए शेड्यूल के हिसाब से नियमित वीडियो सीरीज़ प्लान और प्रोड्यूस करें। • वीडियो ट्रांसलेट और डब करें। वॉइस क्लोनिंग, लिप-सिंक और सबटाइटल के साथ 175+ भाषाओं और बोलियों में AI डबिंग और वीडियो ट्रांसलेशन का इस्तेमाल करें, जिनमें स्पेनिश, फ़्रेंच, जर्मन, पुर्तगाली, जापानी, कोरियाई, चीनी, हिंदी और अरबी शामिल हैं। लाइनें बदलने या ठीक करने के लिए किसी भी वीडियो को नए ऑडियो पर लिप-सिंक करें। • फ़ुटेज को रीपर्पज़ और साफ़ करें। AI क्लिपिंग से लंबे वीडियो, वीडियो पॉडकास्ट, वेबिनार और लाइवस्ट्रीम को Shorts और Reels में बदलें, और फ़िलर वर्ड्स व लंबी चुप्पी हटाएं। • पर्सनलाइज़ और स्केल करें। किसी वीडियो को दोबारा इस्तेमाल होने वाले टेम्पलेट में बदलें, नाम और टेक्स्ट बदलें, और एक ही बैच में कई पर्सनलाइज़्ड वीडियो जनरेट करें। अपने लोगो और रंगों के साथ ब्रांड किट लगाएं, और उच्चारण के लिए ब्रांड ग्लॉसरी इस्तेमाल करें। • अपनी HeyGen लाइब्रेरी मैनेज करें। फ़ोल्डरों में वीडियो, अवतार, आवाज़ें, टेम्पलेट और एसेट ब्राउज़ और व्यवस्थित करें, प्रोग्रेस चेक करें, और तैयार वीडियो डाउनलोड करें। शुरू करने के लिए अपना HeyGen अकाउंट कनेक्ट करें। Videó, hang és avatar AI-jal Készíts a HeyGennel a ChatGPT-ben AI-videókat, beszélő avatarokat, AI-képeket, hangalámondást, hangklónokat és lefordított videókat. Ötletből, forgatókönyvből, cikkből, dokumentumból, fotóból, termékből, hangfelvételből vagy meglévő felvételből marketingvideó, hirdetés, termékdemó, UGC, magyarázó videó, képzés, oktatóvideó, prezentáció és közösségi videó lesz YouTube-ra, YouTube Shortsra, TikTokra, Instagram Reelsre, LinkedInre és weboldalakra. Mit tehetsz a HeyGennel: • Készíts beszélő avataros videókat. AI-avatar, AI-műsorvezető vagy szóvivő adja elő a szövegedet vagy hanganyagodat: bejelentések, értékesítés, onboarding, HR- és compliance-képzés, kurzusok, prezentációk, ügyfélüzenetek, születésnapi vagy ünnepi köszöntők. Adj hozzá B-roll felvételt, zenét, feliratot és motion grafikát, vagy exportáld az avatart átlátszó háttérrel a saját tartalmadhoz. • Klónozd magad. Készíts AI-klónt magadról: Digital Twint egy rövid videóból vagy fotóavatart egyetlen képből. Klónozd a hangodat azonnal egyetlen felvételből, vagy taníts be profi hangklónt 20+ perc hanganyagból, és készíts videókat forgatás nélkül. • Adj új megjelenést az avatarodnak. Készíts új ruhákat, frizurákat és hátteret leírásból, stílussablonból vagy tematikus megjelenéscsomagból, majd készíts videókat magadról bármelyik megjelenésben. • Szólaltass meg egy fotót. Személy fotójából vagy portréjából szájszinkronos beszélő videó lesz, vagy készíts avatart fotóból vagy szöveges leírásból. • Készíts hangalámondást és hanganyagot. AI-hangalámondás és szövegfelolvasás (TTS) sokféle hangon és nyelven, egyedi hang leírás alapján, felvétel újrahangosítása a saját klónozott hangodon AI-hangváltóval (speech-to-speech), plusz zene és hangeffektek. • Készíts AI-képeket. Generálj bármilyen képet szöveges promptból vagy referenciaképekből. A HeyGen Image segítségével helyezd magad vagy avatarodat bármilyen jelenetbe: AI-portrék, profilképek, fotózások, egységes karakter. Megőrzi a fotóidon lévő arcot, a pózt, ruhát és fényt referenciáról veszi át, az eredményt pedig videóvá animálhatod. • Generálj AI-videókat a HeyGen Video 1-gyel. Szövegből videó, képből videó és referenciából videó: filmes jelenetek, termékvideók, hirdetések, animációk, B-roll és rövid klipek fekvő, álló vagy négyzetes formátumban. Cinematic Avatar jelenetek legfeljebb három saját avatarral. • Készíts hosszabb videókat. A Video Agenttel témából, blogposztból, cikkből vagy dokumentumból narrált videó lesz jelenetekkel, B-rollal, feliratokkal, zenével és grafikákkal, amit a csevegésben finomíthatsz. Arc nélküli (faceless), magyarázó, narrált képes történet- és diavetítés-stílusú videók. • Készíts UGC- és közösségimédia-hirdetéseket. AI UGC-hirdetések, termékértékelések, oktatóvideók, felpróbálós haulok, unboxingok, web- és appreklámok, webshop-termékhirdetések és ASMR termékvideók a termékfotóidból vagy weboldaladból. • Tervezd meg a tartalmat. Írj forgatókönyveket és hookokat, és ütemezve tervezz meg és készíts rendszeres videósorozatot YouTube-ra, TikTokra vagy Instagramra. • Fordíts és szinkronizálj videókat. AI-szinkron és videófordítás 175+ nyelvre és dialektusra (köztük spanyol, francia, német, portugál, japán, koreai, kínai, hindi és arab) hangklónozással, szájszinkronnal és felirattal. Igazítsd bármely videó szájmozgását új hanghoz szövegrészek cseréjéhez vagy javításához. • Hasznosítsd újra és tisztítsd a felvételeket. AI-vágással hosszú videókból, videópodcastokból, webináriumokból és élő adásokból Shorts és Reels videók lesznek; töröld a töltelékszavakat és a hosszú csendeket. • Szabj személyre és skálázz. Videóból újrafelhasználható sablon, cserélhető nevek és szöveg, sok személyre szabott videó egy kötegben. Márkakészlet (logó, színek) és márkaszótár a kiejtéshez. • Kezeld a HeyGen-könyvtáradat. Böngéssz és rendezz mappákba videókat, avatarokat, hangokat, sablonokat és fájlokat, kövesd az állapotot, töltsd le a kész videókat. A kezdéshez kapcsold össze a HeyGen-fiókodat. Buat video, suara & avatar AI Buat video AI, avatar bicara, gambar AI, voiceover, kloning suara, dan video terjemahan dengan HeyGen di ChatGPT. Ubah ide, naskah, artikel, dokumen, foto, produk, rekaman audio, atau footage yang ada menjadi video marketing, iklan, demo produk, UGC, explainer, pelatihan, tutorial, presentasi, dan video media sosial untuk YouTube, YouTube Shorts, TikTok, Instagram Reels, LinkedIn, dan website. Dengan HeyGen, Anda bisa: • Buat video avatar bicara. Minta avatar AI, presenter AI, atau juru bicara membawakan naskah atau audio Anda untuk pengumuman, outreach penjualan, onboarding, pelatihan HR dan kepatuhan, kursus, presentasi, pesan pelanggan, serta ucapan ulang tahun atau hari raya. Tambahkan B-roll, musik, caption, dan motion graphics, atau ekspor avatar dengan latar transparan untuk overlay di konten Anda. • Kloning diri Anda. Buat klon AI diri Anda: Digital Twin dari video singkat, atau avatar foto dari satu gambar. Kloning suara Anda secara instan dari satu rekaman, atau latih kloning suara profesional dari 20+ menit audio, agar bisa membuat video tanpa syuting. • Beri avatar Anda tampilan baru. Buat pakaian, gaya rambut, dan latar baru untuk avatar Anda dari deskripsi, template gaya, atau look pack bertema, lalu buat video diri Anda dengan tampilan apa pun. • Buat foto bisa bicara. Ubah foto atau potret seseorang menjadi video bicara dengan lip-sync, atau buat avatar dari foto atau deskripsi teks. • Buat voiceover dan audio. Hasilkan voiceover AI dan narasi text-to-speech (TTS) dalam banyak suara dan bahasa, rancang suara kustom dari deskripsi, ubah suara di rekaman menjadi suara klon Anda sendiri dengan pengubah suara AI (voice changer, speech-to-speech), serta tambahkan musik dan efek suara. • Buat gambar AI. Hasilkan gambar apa pun dari prompt teks atau gambar referensi. Dengan HeyGen Image, tempatkan diri atau avatar Anda di adegan apa pun untuk headshot AI, foto profil, photoshoot, dan karakter yang konsisten: wajah dari foto Anda dipertahankan, sementara pose, pakaian, dan pencahayaan diambil dari referensi, lalu hasilnya bisa dianimasikan jadi video. • Hasilkan video AI dengan HeyGen Video 1. Text-to-video, image-to-video, dan reference-to-video untuk adegan sinematik, video produk, iklan, animasi, B-roll, dan klip pendek format landscape, vertikal, atau persegi. Buat adegan Cinematic Avatar dengan hingga tiga avatar Anda. • Buat video lebih panjang. Ubah topik, postingan blog, artikel, atau dokumen menjadi video bernarasi dengan adegan, B-roll, caption, musik, dan grafis di layar menggunakan Video Agent, lalu sempurnakan lewat chat. Buat video faceless, explainer, cerita bergambar bernarasi, dan video gaya slideshow. • Buat UGC dan iklan sosial. Buat iklan UGC AI, ulasan produk, tutorial, try-on haul, unboxing, promo website dan aplikasi, iklan produk e-commerce, serta video produk ASMR dari foto produk atau website Anda. • Rencanakan konten. Tulis naskah dan hook video, serta rencanakan dan produksi seri video rutin untuk YouTube, TikTok, atau Instagram sesuai jadwal. • Terjemahkan dan dubbing video. Gunakan dubbing AI dan terjemahan video ke 175+ bahasa dan dialek, termasuk Spanyol, Prancis, Jerman, Portugis, Jepang, Korea, Mandarin, Hindi, dan Arab, dengan kloning suara, lip-sync, dan subtitle. Lip-sync video apa pun ke audio baru untuk mengganti atau memperbaiki dialog. • Olah ulang dan rapikan footage. Gunakan AI clipping untuk mengubah video panjang, video podcast, webinar, dan livestream menjadi Shorts dan Reels, serta hapus kata pengisi dan jeda hening panjang. • Personalisasi dan skalakan. Jadikan video template yang bisa dipakai ulang, ganti nama dan teks, lalu hasilkan banyak video personal dalam satu batch. Terapkan brand kit dengan logo dan warna Anda, serta glosarium brand untuk pelafalan. • Kelola library HeyGen Anda. Telusuri dan atur video, avatar, suara, template, dan aset dalam folder, cek progres, dan unduh video yang selesai. Hubungkan akun HeyGen Anda untuk memulai. Crea video, voci e avatar AI Crea video con l'AI, avatar parlanti, immagini AI, voiceover, cloni vocali e video tradotti con HeyGen in ChatGPT. Trasforma un'idea, uno script, un articolo, un documento, una foto, un prodotto, un audio o un filmato esistente in video di marketing, annunci, demo di prodotto, UGC, video esplicativi, formazione e video social per YouTube, YouTube Shorts, TikTok, Instagram Reels, LinkedIn e siti web. Con HeyGen puoi: • Creare video con avatar parlanti. Fai presentare il tuo script o audio a un avatar AI, un presentatore virtuale o un portavoce per comunicazioni, vendite, onboarding, formazione HR e compliance, corsi, presentazioni, messaggi ai clienti e auguri. Aggiungi B-roll, musica, sottotitoli e motion graphics, o esporta l'avatar su sfondo trasparente da sovrapporre ai tuoi contenuti. • Clonare te stesso. Crea un tuo clone AI: un Digital Twin da un breve video o un avatar fotografico da una sola immagine. Clona la tua voce all'istante da una registrazione o addestra un clone vocale professionale con oltre 20 minuti di audio, per creare video senza girare. • Dare nuovi look al tuo avatar. Crea outfit, acconciature e sfondi nuovi da una descrizione, un template di stile o un pacchetto di look a tema, poi crea video di te stesso con qualsiasi look. • Far parlare una foto. Trasforma la foto o il ritratto di una persona in un video parlante con lip-sync, o crea un avatar da una foto o da una descrizione testuale. • Creare voiceover e audio. Genera voiceover con l'AI e narrazione text-to-speech (TTS) con molte voci e lingue, crea una voce personalizzata da una descrizione, trasforma la voce di una registrazione nella tua stessa voce clonata con un modificatore di voce AI (voice changer, speech-to-speech) e aggiungi musica ed effetti sonori. • Creare immagini AI. Genera qualsiasi immagine da un prompt testuale o immagini di riferimento. Con HeyGen Image, inserisci te stesso o il tuo avatar in qualsiasi scena per ritratti professionali AI, foto profilo, shooting e un personaggio coerente: mantiene il volto delle tue foto e prende posa, outfit e luci da un riferimento, poi animi il risultato in un video. • Generare video AI con HeyGen Video 1. Text-to-video, image-to-video e reference-to-video per scene cinematografiche, video di prodotto, annunci, animazioni, B-roll e clip brevi in orizzontale, verticale o quadrato. Crea scene Cinematic Avatar con fino a tre dei tuoi avatar. • Realizzare video più lunghi. Trasforma un argomento, un post, un articolo o un documento in un video narrato con scene, B-roll, sottotitoli, musica e grafiche a schermo con Video Agent, poi perfezionalo in chat. Crea video faceless, esplicativi, storie illustrate narrate e slideshow. • Creare annunci UGC e social. Crea annunci UGC con l'AI, recensioni, tutorial, try-on haul, unboxing, promo per siti web e app, annunci per e-commerce e video ASMR di prodotto dalle foto del tuo prodotto o dal tuo sito. • Pianificare i contenuti. Scrivi script e hook, e pianifica e produci una serie di video ricorrente per YouTube, TikTok o Instagram secondo un calendario. • Tradurre e doppiare video. Usa il doppiaggio AI e la traduzione video in oltre 175 lingue e dialetti, tra cui spagnolo, giapponese, hindi e arabo, con clonazione vocale, lip-sync e sottotitoli. Fai il lip-sync di qualsiasi video con un nuovo audio per sostituire o correggere battute. • Riutilizzare e ripulire i filmati. Usa il clipping AI per trasformare video lunghi, video podcast, webinar e dirette in Shorts e Reels, e rimuovi intercalari e lunghi silenzi. • Personalizzare e scalare. Trasforma un video in un template riutilizzabile, sostituisci nomi e testi e genera molti video personalizzati in batch. Applica brand kit con logo e colori, e glossari del brand per la pronuncia. • Gestire la tua libreria HeyGen. Sfoglia e organizza video, avatar, voci, template e asset in cartelle, controlla l'avanzamento e scarica i video completati. Collega il tuo account HeyGen per iniziare. AIで動画・音声・アバターを作成 ChatGPT で HeyGen を使って、AI動画、話すAIアバター、AI画像、ナレーション、音声クローン、翻訳動画を作成できます。アイデア、台本、記事、ドキュメント、写真、商品、録音音声、既存の映像から、マーケティング動画、広告、製品デモ、UGC、解説動画、研修、チュートリアル、プレゼン、そして YouTube、YouTube Shorts、TikTok、Instagram Reels、LinkedIn、ウェブサイト向けのSNS動画を作れます。 HeyGen でできること: • 話すアバター動画を作成。AIアバター、AIプレゼンター、スポークスパーソンが台本や音声を読み上げ、お知らせ、営業アプローチ、オンボーディング、人事・コンプライアンス研修、講座、プレゼン、顧客へのメッセージ、誕生日や季節の挨拶に活用できます。B-roll、音楽、字幕、モーショングラフィックスを加えたり、アバターを透過背景で書き出して自分のコンテンツに重ねたりできます。 • 自分をクローン。短い動画からデジタルツイン(Digital Twin)、1枚の画像からフォトアバターを作り、自分のAIクローンを作成できます。声は1つの録音からすぐにクローンすることも、20分以上の音声でプロ品質の音声クローンを作ることもでき、撮影なしで動画を作れます。 • アバターに新しいルックを。説明文、スタイルテンプレート、テーマ別のルックパックから、アバターの新しい衣装、髪型、背景を作成し、好きなルックの自分で動画を作れます。 • 写真をしゃべらせる。人物の写真やポートレートを、リップシンクした話す動画に変換。写真やテキストの説明からアバターを作成することもできます。 • ナレーションと音声を作成。多彩な声と言語で、AIナレーションやテキスト読み上げ(TTS)を生成し、説明文からオリジナルの声をデザインできます。AIボイスチェンジャー(Speech-to-Speech)で録音を自分のクローン音声に変換し、BGMや効果音も追加できます。 • AI画像を作成。テキストプロンプトや参照画像から、あらゆる画像を生成できます。HeyGen Image なら、自分やアバターをあらゆるシーンに登場させ、AIヘッドショット、プロフィール写真、フォトシュート、一貫したキャラクターを実現。写真の顔を保ったまま、参照画像からポーズ、衣装、ライティングを取り入れ、仕上がった画像を動画にすることもできます。 • HeyGen Video 1 でAI動画を生成。テキストから動画、画像から動画、参照画像から動画で、シネマティックなシーン、製品動画、広告、アニメーション、B-roll、ショートクリップを横長・縦長・正方形で作成。最大3体の自分のアバターで Cinematic Avatar のシーンも作成できます。 • 長尺動画を作成。Video Agent でトピック、ブログ記事、記事、ドキュメントを、シーン、B-roll、字幕、音楽、画面上のグラフィックス付きのナレーション動画に変換し、チャットで調整できます。顔出しなし動画、解説動画、ナレーション付きの絵物語、スライドショー風動画も作れます。 • UGC・SNS広告を作成。商品写真やウェブサイトから、AI UGC広告、商品レビュー、チュートリアル、試着ハウル、開封動画、ウェブサイトやアプリのプロモーション動画、EC向け商品広告、ASMR商品動画を作成できます。 • コンテンツを企画。動画の台本やフックを書き、YouTube、TikTok、Instagram 向けの定期的な動画シリーズをスケジュールに沿って企画・制作できます。 • 動画の翻訳と吹き替え。AI吹き替えと動画翻訳で、スペイン語、フランス語、ドイツ語、ポルトガル語、日本語、韓国語、中国語、ヒンディー語、アラビア語など175以上の言語と方言に対応し、音声クローン、リップシンク、字幕も使えます。任意の動画を新しい音声にリップシンクして、セリフの差し替えや修正も可能です。 • 映像の再活用とクリーンアップ。AIクリッピングで長尺動画、ビデオポッドキャスト、ウェビナー、ライブ配信を Shorts や Reels に変換し、フィラーワードや長い無音を削除できます。 • パーソナライズと大量生成。動画を再利用できるテンプレートにして名前やテキストを差し替え、パーソナライズ動画を一括で大量に生成。ロゴやカラーを含むブランドキットを適用し、ブランド用語集で発音を統一できます。 • HeyGen ライブラリを管理。動画、アバター、音声、テンプレート、アセットをフォルダで閲覧・整理し、進捗を確認して、完成した動画をダウンロードできます。 HeyGen アカウントを接続して始めましょう。 AI 영상, 음성, 아바타 제작 ChatGPT에서 HeyGen으로 AI 영상, 말하는 아바타, AI 이미지, AI 보이스오버, 음성 복제, 번역 영상을 만드세요. 아이디어, 대본, 기사, 문서, 사진, 제품, 녹음 파일, 기존 영상을 마케팅 영상, 광고, 제품 데모, UGC, 설명 영상, 교육, 튜토리얼, 프레젠테이션, 그리고 YouTube, YouTube Shorts, TikTok, Instagram Reels, LinkedIn, 웹사이트용 소셜 영상으로 바꿀 수 있습니다. HeyGen으로 할 수 있는 일: • 말하는 아바타 영상 제작. AI 아바타, AI 프레젠터 또는 대변인이 대본이나 오디오를 전달하게 해 공지, 영업 아웃리치, 온보딩, HR 및 컴플라이언스 교육, 강좌, 프레젠테이션, 고객 메시지, 생일이나 명절 인사에 활용하세요. B-roll, 음악, 자막, 모션 그래픽을 더하거나, 아바타를 투명 배경으로 내보내 내 콘텐츠 위에 겹칠 수 있습니다. • 나를 복제. 짧은 영상으로 디지털 트윈(Digital Twin)을, 사진 한 장으로 포토 아바타를 만들어 나만의 AI 클론을 만드세요. 녹음 하나로 목소리를 즉시 복제하거나, 20분 이상의 오디오로 전문가급 음성 클론을 학습시켜 촬영 없이 영상을 만들 수 있습니다. • 아바타에 새로운 룩 입히기. 설명, 스타일 템플릿 또는 테마별 룩 팩으로 아바타의 새로운 의상, 헤어스타일, 배경을 만들고, 원하는 룩으로 내가 등장하는 영상을 만드세요. • 사진을 말하게 만들기. 인물 사진이나 초상화를 립싱크되는 말하는 영상으로 바꾸거나, 사진 또는 텍스트 설명으로 아바타를 만드세요. • 보이스오버와 오디오 제작. 다양한 목소리와 언어로 AI 보이스오버와 TTS(텍스트 음성 변환) 내레이션을 생성하고, 설명만으로 나만의 목소리를 디자인하세요. AI 보이스 체인저(speech-to-speech)로 녹음을 복제한 내 목소리로 바꾸고, 배경 음악과 효과음도 추가할 수 있습니다. • AI 이미지 생성. 텍스트 프롬프트나 참조 이미지로 어떤 이미지든 만드세요. HeyGen Image로는 나 또는 내 아바타를 어떤 장면에든 넣어 AI 헤드샷, 프로필 사진, 화보, 일관된 캐릭터를 만들 수 있습니다. 사진 속 얼굴은 유지하고 참조 이미지에서 포즈, 의상, 조명을 가져오며, 결과물을 영상으로 움직이게 할 수도 있습니다. • HeyGen Video 1로 AI 영상 생성. 텍스트-투-비디오, 이미지-투-비디오, 레퍼런스-투-비디오로 시네마틱 장면, 제품 영상, 광고, 애니메이션, B-roll, 짧은 클립을 가로, 세로, 정사각형으로 만드세요. 내 아바타를 최대 3명까지 넣어 Cinematic Avatar 장면도 만들 수 있습니다. • 긴 영상 제작. Video Agent로 주제, 블로그 글, 기사, 문서를 장면, B-roll, 자막, 음악, 화면 그래픽이 들어간 내레이션 영상으로 바꾸고 채팅으로 다듬으세요. 얼굴 없는 영상, 설명 영상, 내레이션이 있는 그림 이야기, 슬라이드쇼형 영상도 만들 수 있습니다. • UGC 및 소셜 광고 제작. 제품 사진이나 웹사이트로 AI UGC 광고, 제품 리뷰, 튜토리얼, 착용 하울, 언박싱, 웹사이트 및 앱 홍보 영상, 이커머스 제품 광고, ASMR 제품 영상을 만드세요. • 콘텐츠 기획. 영상 대본과 훅을 쓰고, YouTube, TikTok, Instagram용 정기 영상 시리즈를 일정에 맞춰 기획하고 제작하세요. • 영상 번역 및 더빙. AI 더빙과 영상 번역으로 스페인어, 프랑스어, 독일어, 포르투갈어, 일본어, 한국어, 중국어, 힌디어, 아랍어 등 175개 이상의 언어와 방언으로 옮기고, 음성 복제, 립싱크, 자막을 함께 적용하세요. 어떤 영상이든 새 오디오에 립싱크해 대사를 교체하거나 수정할 수 있습니다. • 영상 재활용 및 정리. AI 클리핑으로 긴 영상, 비디오 팟캐스트, 웨비나, 라이브 방송을 Shorts와 Reels로 만들고, 군더더기 말과 긴 무음 구간을 제거하세요. • 개인화와 대량 제작. 영상을 재사용 가능한 템플릿으로 만들고 이름과 텍스트를 바꿔 개인화 영상을 한 번에 대량 생성하세요. 로고와 색상이 담긴 브랜드 키트를 적용하고, 브랜드 용어집으로 발음을 관리하세요. • HeyGen 라이브러리 관리. 영상, 아바타, 음성, 템플릿, 에셋을 폴더로 탐색하고 정리하며, 진행 상황을 확인하고 완성된 영상을 다운로드하세요. HeyGen 계정을 연결하고 시작하세요. Cipta video, suara & avatar AI Cipta video AI, avatar bercakap, imej AI, voiceover, klon suara dan video terjemahan dengan HeyGen dalam ChatGPT. Tukar idea, skrip, artikel, dokumen, foto, produk, rakaman audio atau footage sedia ada kepada video pemasaran, iklan, demo produk, UGC, explainer, latihan, tutorial, pembentangan dan video media sosial untuk YouTube, YouTube Shorts, TikTok, Instagram Reels, LinkedIn dan laman web. Dengan HeyGen, anda boleh: • Hasilkan video avatar bercakap. Biar avatar AI, penyampai AI atau jurucakap menyampaikan skrip atau audio anda untuk pengumuman, jangkauan jualan, onboarding, latihan HR dan pematuhan, kursus, pembentangan, mesej pelanggan, serta ucapan hari jadi atau perayaan. Tambah B-roll, muzik, kapsyen dan grafik gerak, atau eksport avatar dengan latar belakang lutsinar untuk ditindih pada kandungan anda. • Klon diri anda. Cipta klon AI diri anda: Digital Twin daripada video pendek, atau avatar foto daripada satu imej. Klon suara anda serta-merta daripada satu rakaman, atau latih klon suara profesional daripada 20+ minit audio, untuk hasilkan video tanpa penggambaran. • Beri avatar anda gaya baharu. Cipta pakaian, gaya rambut dan latar belakang baharu untuk avatar anda daripada penerangan, templat gaya atau look pack bertema, lalu hasilkan video diri anda dalam apa jua gaya. • Jadikan foto bercakap. Tukar foto atau potret seseorang kepada video bercakap dengan lip-sync, atau cipta avatar daripada foto atau penerangan teks. • Cipta voiceover dan audio. Jana voiceover AI dan narasi text-to-speech (TTS) dalam pelbagai suara dan bahasa, reka suara tersuai daripada penerangan, tukar suara dalam rakaman kepada suara klon anda sendiri dengan pengubah suara AI (voice changer, speech-to-speech), serta tambah muzik dan kesan bunyi. • Cipta imej AI. Jana apa jua imej daripada prompt teks atau imej rujukan. Dengan HeyGen Image, letakkan diri atau avatar anda dalam apa jua babak untuk headshot AI, gambar profil, sesi fotografi dan watak yang konsisten: wajah daripada foto anda dikekalkan, manakala pose, pakaian dan pencahayaan diambil daripada rujukan, lalu animasikan hasilnya jadi video. • Jana video AI dengan HeyGen Video 1. Text-to-video, image-to-video dan reference-to-video untuk babak sinematik, video produk, iklan, animasi, B-roll dan klip pendek format landskap, menegak atau segi empat sama. Cipta babak Cinematic Avatar dengan sehingga tiga avatar anda. • Hasilkan video lebih panjang. Tukar topik, catatan blog, artikel atau dokumen kepada video bernarasi dengan babak, B-roll, kapsyen, muzik dan grafik pada skrin menggunakan Video Agent, lalu perhalusi dalam chat. Hasilkan video faceless, explainer, cerita bergambar bernarasi dan video gaya slideshow. • Hasilkan UGC dan iklan sosial. Cipta iklan UGC AI, ulasan produk, tutorial, try-on haul, unboxing, promosi laman web dan aplikasi, iklan produk e-dagang, serta video produk ASMR daripada foto produk atau laman web anda. • Rancang kandungan. Tulis skrip dan hook video, serta rancang dan hasilkan siri video berkala untuk YouTube, TikTok atau Instagram mengikut jadual. • Terjemah dan alih suara video. Gunakan dubbing AI dan terjemahan video ke 175+ bahasa dan dialek, termasuk Sepanyol, Perancis, Jerman, Portugis, Jepun, Korea, Cina, Hindi dan Arab, dengan klon suara, lip-sync dan sari kata. Lip-sync mana-mana video dengan audio baharu untuk mengganti atau membetulkan dialog. • Guna semula dan bersihkan rakaman. Gunakan AI clipping untuk menukar video panjang, podcast video, webinar dan siaran langsung kepada Shorts dan Reels, serta buang kata pengisi dan senyap panjang. • Peribadikan dan skalakan. Jadikan video templat boleh guna semula, tukar nama dan teks, dan jana banyak video peribadi dalam satu batch. Gunakan kit jenama dengan logo dan warna anda, serta glosari jenama untuk sebutan. • Urus pustaka HeyGen anda. Layari dan susun video, avatar, suara, templat dan aset dalam folder, semak kemajuan, dan muat turun video yang siap. Sambungkan akaun HeyGen anda untuk bermula. KI-videoer, stemmer & avatarer Lag KI-videoer, snakkende avatarer, KI-bilder, voiceovers, stemmekloner og oversatte videoer med HeyGen i ChatGPT. Gjør en idé, et manus, en artikkel, et dokument, et foto, et produkt, et lydopptak eller eksisterende opptak om til markedsføringsvideoer, annonser, produktdemoer, UGC, forklaringsvideoer, opplæring, veiledninger, presentasjoner og videoer for sosiale medier på YouTube, YouTube Shorts, TikTok, Instagram Reels, LinkedIn og nettsider. Med HeyGen kan du: • Lage videoer med snakkende avatarer. La en KI-avatar, KI-programleder eller talsperson fremføre manuset eller lyden din til kunngjøringer, salgshenvendelser, onboarding, HR- og compliance-opplæring, kurs, kundemeldinger og bursdags- eller høytidshilsener. Legg til B-roll, musikk, undertekster og motion graphics, eller eksporter avataren med gjennomsiktig bakgrunn som overlay. • Klone deg selv. Lag en KI-klone av deg selv: en Digital Twin fra en kort video, eller en fotoavatar fra ett enkelt bilde. Klon stemmen din umiddelbart fra ett opptak, eller tren en profesjonell stemmeklone på 20+ minutter lyd, slik at du kan lage videoer uten å filme. • Gi avataren din nye looks. Lag nye antrekk, frisyrer og bakgrunner for avataren din ut fra en beskrivelse, stilmal eller tematisk lookpakke, og lag videoer av deg selv i alle looks. • Få et bilde til å snakke. Gjør et foto eller portrett av en person om til en snakkende, leppesynkronisert video, eller lag en avatar fra et foto eller en tekstbeskrivelse. • Lage voiceovers og lyd. Generer KI-voiceovers og tekst-til-tale (TTS) i mange stemmer og språk, design en egen stemme ut fra en beskrivelse, bytt stemmen i et opptak til din egen klonede stemme med en KI-voice changer (speech-to-speech), og legg til musikk og lydeffekter. • Lage KI-bilder. Generer alle slags bilder fra en tekstprompt eller referansebilder. Med HeyGen Image plasserer du deg selv eller avataren din i enhver scene for KI-portretter, profilbilder, fotoshoots og en konsistent karakter: ansiktet fra bildene dine, positur, antrekk og lys fra en referanse, og resultatet kan så animeres til video. • Generere KI-videoer med HeyGen Video 1. Tekst-til-video, bilde-til-video og referanse-til-video for filmatiske scener, produktvideoer, annonser, animasjoner, B-roll og korte klipp i liggende, stående eller kvadratisk format. Lag Cinematic Avatar-scener med opptil tre av avatarene dine. • Lage lengre videoer. Gjør et emne, et blogginnlegg, en artikkel eller et dokument om til en fortalt video med scener, B-roll, undertekster, musikk og grafikk på skjermen med Video Agent, og finpuss den i chatten. Lag faceless videoer, forklaringsvideoer, fortalte bildehistorier og videoer i lysbildestil. • Lage UGC- og sosiale annonser. Lag KI-UGC-annonser, produktanmeldelser, veiledninger, try-on hauls, unboxings, promoer for nettsider og apper, netthandelsannonser og ASMR-produktvideoer fra produktbildene eller nettsiden din. • Planlegge innhold. Skriv videomanus og hooks, og planlegg og produser en videoserie for YouTube, TikTok eller Instagram etter tidsplan. • Oversette og dubbe videoer. Bruk KI-dubbing og videooversettelse til 175+ språk og dialekter, blant annet spansk, fransk, tysk, portugisisk, japansk, koreansk, kinesisk, hindi og arabisk, med stemmekloning, leppesynk og undertekster. Leppesynkroniser enhver video til ny lyd for å erstatte eller rette replikker. • Gjenbruke og rydde i opptak. Bruk KI-klipping til å gjøre lange videoer, videopodkaster, webinarer og direktesendinger om til Shorts og Reels, og fjern fyllord og lange pauser. • Personalisere og skalere. Gjør en video om til en gjenbrukbar mal, bytt ut navn og tekst, og generer mange personlige videoer i én batch. Bruk merkevaresett med logo og farger, og merkevareordlister for uttale. • Administrere HeyGen-biblioteket ditt. Bla gjennom og organiser videoer, avatarer, stemmer, maler og ressurser i mapper, sjekk fremdriften og last ned ferdige videoer. Koble til HeyGen-kontoen din for å komme i gang. AI-video's, stemmen & avatars Maak AI-video's, pratende avatars, AI-afbeeldingen, voice-overs, stemklonen en vertaalde video's met HeyGen in ChatGPT. Zet een idee, script, artikel, document, foto, product, audio-opname of bestaand beeldmateriaal om in marketingvideo's, advertenties, productdemo's, UGC, uitlegvideo's, trainingen, tutorials, presentaties en socialmediavideo's voor YouTube, YouTube Shorts, TikTok, Instagram Reels, LinkedIn en websites. Met HeyGen kun je: • Video's met pratende avatars maken. Laat een AI-avatar, AI-presentator of woordvoerder je script of audio brengen voor aankondigingen, sales-outreach, onboarding, HR- en compliancetrainingen, cursussen, klantberichten en verjaardags- of feestdagwensen. Voeg B-roll, muziek, ondertitels en motion graphics toe, of exporteer de avatar met transparante achtergrond als overlay. • Jezelf klonen. Maak een AI-kloon van jezelf: een Digital Twin uit een korte video, of een foto-avatar uit één afbeelding. Kloon je stem direct uit één opname, of train een professionele stemkloon met 20+ minuten audio, zodat je video's kunt maken zonder te filmen. • Je avatar nieuwe looks geven. Maak nieuwe outfits, kapsels en achtergronden voor je avatar met een beschrijving, stijltemplate of themapakket met looks, en maak video's van jezelf in elke look. • Een foto laten praten. Maak van een foto of portret van een persoon een pratende, lipsynchrone video, of maak een avatar van een foto of tekstbeschrijving. • Voice-overs en audio maken. Genereer AI-voice-overs en text-to-speech (TTS) in veel stemmen en talen, ontwerp een eigen stem op basis van een beschrijving, zet een opname om naar je eigen gekloonde stem met een AI-voice changer (speech-to-speech), en voeg muziek en geluidseffecten toe. • AI-afbeeldingen maken. Genereer elke afbeelding met een tekstprompt of referentieafbeeldingen. Zet met HeyGen Image jezelf of je avatar in elke scène voor AI-headshots, profielfoto's, fotoshoots en een consistent personage: het gezicht komt uit je foto's, pose, outfit en belichting uit een referentie, en daarna animeer je het resultaat tot video. • AI-video's genereren met HeyGen Video 1. Text-to-video, image-to-video en reference-to-video voor filmische scènes, productvideo's, advertenties, animaties, B-roll en korte clips in liggend, staand of vierkant formaat. Maak Cinematic Avatar-scènes met maximaal drie van je avatars. • Langere video's maken. Maak met Video Agent van een onderwerp, blogpost, artikel of document een ingesproken video met scènes, B-roll, ondertitels, muziek en graphics in beeld, en verfijn die in de chat. Maak faceless video's, uitlegvideo's, vertelde fotoverhalen en video's in slideshowstijl. • UGC- en social ads maken. Maak AI-UGC-advertenties, productreviews, tutorials, try-on hauls, unboxings, promo's voor websites en apps, e-commerce-productadvertenties en ASMR-productvideo's op basis van je productfoto's of website. • Content plannen. Schrijf videoscripts en hooks, en plan en produceer een videoserie voor YouTube, TikTok of Instagram volgens schema. • Video's vertalen en nasynchroniseren. Gebruik AI-dubbing en videovertaling naar 175+ talen en dialecten, waaronder Spaans, Frans, Duits, Portugees, Japans, Koreaans, Chinees, Hindi en Arabisch, met stemklonen, lipsync en ondertitels. Lipsync elke video op nieuwe audio om zinnen te vervangen of te verbeteren. • Beeldmateriaal hergebruiken en opschonen. Maak met AI-clipping van lange video's, videopodcasts, webinars en livestreams Shorts en Reels, en verwijder stopwoorden en lange stiltes. • Personaliseren en opschalen. Maak van een video een herbruikbare template, wissel namen en tekst uit en genereer veel gepersonaliseerde video's in één batch. Gebruik brand kits met je logo en kleuren, en merkwoordenlijsten voor de uitspraak. • Je HeyGen-bibliotheek beheren. Blader door en orden video's, avatars, stemmen, templates en assets in mappen, bekijk de voortgang en download afgeronde video's. Koppel je HeyGen-account om te beginnen. Twórz wideo, głosy i awatary Twórz z HeyGen w ChatGPT filmy AI, mówiące awatary, obrazy AI, lektora AI, klony głosu i przetłumaczone filmy. Zamień pomysł, scenariusz, artykuł, dokument, zdjęcie, produkt, nagranie audio lub istniejący materiał w filmy marketingowe, reklamy, dema produktów, UGC, filmy wyjaśniające, szkolenia, poradniki, prezentacje i filmy do social mediów na YouTube, YouTube Shorts, TikTok, Instagram Reels, LinkedIn i strony www. Z HeyGen możesz: • Tworzyć filmy z mówiącym awatarem. Awatar AI, prezenter AI lub rzecznik wygłosi Twój scenariusz lub nagranie: ogłoszenia, sprzedaż, onboarding, szkolenia HR i compliance, kursy, prezentacje, wiadomości do klientów, życzenia urodzinowe i świąteczne. Dodaj B-roll, muzykę, napisy i motion graphics albo wyeksportuj awatar na przezroczystym tle do nałożenia na własne materiały. • Sklonować siebie. Stwórz swojego klona AI: Digital Twin z krótkiego filmu albo awatar fotograficzny z jednego zdjęcia. Sklonuj głos błyskawicznie z jednego nagrania lub wytrenuj profesjonalny klon głosu na 20+ minutach audio i twórz filmy bez nagrywania. • Nadawać awatarowi nowe stylizacje. Twórz nowe stroje, fryzury i tła dla awatara z opisu, szablonu stylu lub tematycznego pakietu stylizacji, a potem twórz filmy ze sobą w dowolnej stylizacji. • Sprawić, by zdjęcie przemówiło. Zamień zdjęcie lub portret osoby w mówiący film z synchronizacją ust albo stwórz awatar ze zdjęcia lub opisu tekstowego. • Tworzyć lektora i audio. Generuj lektora AI i narrację z zamianą tekstu na mowę (TTS) w wielu głosach i językach, zaprojektuj własny głos z opisu, przegraj nagranie swoim sklonowanym głosem dzięki zmieniaczowi głosu AI (speech-to-speech) oraz dodaj muzykę i efekty dźwiękowe. • Tworzyć obrazy AI. Generuj dowolny obraz z promptu tekstowego lub obrazów referencyjnych. Z HeyGen Image umieść siebie lub swój awatar w dowolnej scenie: portrety biznesowe AI, zdjęcia profilowe, sesje zdjęciowe i spójna postać. Zachowuje twarz z Twoich zdjęć, a pozę, strój i oświetlenie przejmuje z referencji. Wynik możesz potem animować w film. • Generować filmy AI z HeyGen Video 1. Tekst na wideo, obraz na wideo i referencja na wideo: filmowe sceny, filmy produktowe, reklamy, animacje, B-roll i krótkie klipy w poziomie, pionie lub kwadracie. Twórz sceny Cinematic Avatar z maksymalnie trzema swoimi awatarami. • Tworzyć dłuższe filmy. Z Video Agent zamień temat, wpis na blogu, artykuł lub dokument w film z narracją, scenami, B-roll, napisami, muzyką i grafiką na ekranie, a potem dopracuj go na czacie. Filmy bez twarzy (faceless), filmy wyjaśniające, opowieści obrazkowe z narracją i filmy w stylu pokazu slajdów. • Tworzyć UGC i reklamy do social mediów. Reklamy UGC z AI, recenzje produktów, tutoriale, try-on haule, unboxingi, promo stron i aplikacji, reklamy produktów e-commerce i filmy produktowe ASMR ze zdjęć produktów lub z Twojej strony. • Planować treści. Pisz scenariusze i hooki do filmów oraz planuj i produkuj cykliczną serię filmów na YouTube, TikTok lub Instagram według harmonogramu. • Tłumaczyć i dubbingować filmy. Dubbing AI i tłumaczenie wideo na 175+ języków i dialektów, w tym hiszpański, francuski, niemiecki, portugalski, japoński, koreański, chiński, hindi i arabski, z klonowaniem głosu, synchronizacją ust i napisami. Synchronizuj usta w dowolnym filmie z nowym nagraniem, by zastąpić lub poprawić kwestie. • Przerabiać i oczyszczać nagrania. Dzięki AI tnij długie filmy, wideopodcasty, webinary i transmisje na żywo na Shorts i Reels oraz usuwaj słowa wypełniacze i długie pauzy. • Personalizować i skalować. Zamień film w szablon wielokrotnego użytku, podmieniaj imiona i tekst oraz generuj wiele spersonalizowanych filmów w jednej partii. Stosuj brand kity z logo i kolorami oraz glosariusze marki do wymowy. • Zarządzać biblioteką HeyGen. Przeglądaj i porządkuj filmy, awatary, głosy, szablony i zasoby w folderach, sprawdzaj postęp i pobieraj gotowe filmy. Połącz konto HeyGen, aby zacząć. Crie vídeos, vozes e avatares Crie vídeos com IA, avatares falantes, imagens com IA, locuções, clones de voz e vídeos traduzidos com o HeyGen no ChatGPT. Transforme uma ideia, roteiro, artigo, documento, foto, produto, áudio ou vídeo existente em vídeos de marketing, anúncios, demos de produto, UGC, explicativos, treinamentos e vídeos para redes sociais no YouTube, YouTube Shorts, TikTok, Instagram Reels, LinkedIn e sites. Com o HeyGen, você pode: • Criar vídeos com avatar falante. Um avatar de IA, apresentador virtual ou porta-voz apresenta seu roteiro ou áudio em comunicados, vendas, onboarding, treinamentos de RH e compliance, cursos, apresentações, mensagens para clientes e felicitações. Adicione B-roll, música, legendas e motion graphics, ou exporte o avatar com fundo transparente para sobrepor ao seu conteúdo. • Clonar a si mesmo. Crie seu clone de IA: um Digital Twin com um vídeo curto ou um avatar de foto com uma única imagem. Clone sua voz instantaneamente com uma gravação ou treine um clone de voz profissional com mais de 20 minutos de áudio, para fazer vídeos sem filmar. • Dar novos visuais ao seu avatar. Crie roupas, penteados e fundos novos para o seu avatar com uma descrição, um template de estilo ou um pacote de looks temático, e faça vídeos seus com qualquer visual. • Fazer uma foto falar. Transforme a foto ou retrato de uma pessoa em vídeo falado com sincronização labial, ou crie um avatar com uma foto ou descrição em texto. • Criar locuções e áudio. Gere locução com IA e narração de texto para fala (TTS) em várias vozes e idiomas, crie uma voz personalizada por descrição, transforme a voz de uma gravação na sua própria voz clonada com um modificador de voz com IA (speech-to-speech) e adicione música e efeitos sonoros. • Criar imagens com IA. Gere qualquer imagem com um prompt de texto ou imagens de referência. Com o HeyGen Image, coloque você ou seu avatar em qualquer cenário para fotos profissionais com IA, fotos de perfil, ensaios e um personagem consistente: ele mantém o rosto das suas fotos e usa pose, roupa e iluminação de uma referência; depois, anime o resultado em vídeo. • Gerar vídeos com IA no HeyGen Video 1. Texto para vídeo, imagem para vídeo e referência para vídeo para cenas cinematográficas, vídeos de produto, anúncios, animações, B-roll e clipes curtos na horizontal, vertical ou quadrado. Crie cenas de Cinematic Avatar com até três dos seus avatares. • Fazer vídeos mais longos. Transforme um tema, post de blog, artigo ou documento em um vídeo narrado com cenas, B-roll, legendas, música e gráficos na tela com o Video Agent, e refine no chat. Faça vídeos faceless, explicativos, histórias narradas com imagens e slideshows. • Criar anúncios UGC e para redes sociais. Crie anúncios UGC com IA, reviews de produto, tutoriais, try-on hauls, unboxings, promos de sites e apps, anúncios para e-commerce e vídeos ASMR de produto com fotos do produto ou do seu site. • Planejar conteúdo. Escreva roteiros e ganchos, e planeje e produza uma série recorrente de vídeos para YouTube, TikTok ou Instagram com calendário. • Traduzir e dublar vídeos. Use dublagem com IA e tradução de vídeo para mais de 175 idiomas e dialetos, como espanhol, japonês, hindi e árabe, com clonagem de voz, sincronização labial e legendas. Faça lip-sync de qualquer vídeo com um novo áudio para substituir ou corrigir falas. • Reaproveitar e limpar gravações. Use cortes com IA para transformar vídeos longos, videocasts, webinars e lives em Shorts e Reels, e remova vícios de linguagem e silêncios longos. • Personalizar e escalar. Transforme um vídeo em um template reutilizável, troque nomes e textos e gere muitos vídeos personalizados em lote. Aplique brand kits com seu logo e cores, e glossários da marca para pronúncia. • Gerenciar sua biblioteca do HeyGen. Navegue e organize vídeos, avatares, vozes, templates e arquivos em pastas, acompanhe o progresso e baixe os vídeos prontos. Conecte sua conta do HeyGen para começar. Crie vídeos, vozes e avatares Crie vídeos com IA, avatares que falam, imagens com IA, locuções, clones de voz e vídeos traduzidos com o HeyGen no ChatGPT. Transforme uma ideia, guião, artigo, documento, foto, produto, áudio ou vídeo existente em vídeos de marketing, anúncios, demos de produto, UGC, explicativos, formação e vídeos para redes sociais no YouTube, YouTube Shorts, TikTok, Instagram Reels, LinkedIn e sites. Com o HeyGen, pode: • Criar vídeos com avatares que falam. Um avatar de IA, apresentador virtual ou porta-voz apresenta o seu guião ou áudio em comunicados, vendas, onboarding, formação de RH e compliance, cursos, apresentações, mensagens a clientes e felicitações. Adicione B-roll, música, legendas e motion graphics, ou exporte o avatar com fundo transparente para o sobrepor ao seu conteúdo. • Clonar-se. Crie o seu clone de IA: um Digital Twin com um vídeo curto ou um avatar fotográfico com uma única imagem. Clone a sua voz instantaneamente com uma gravação ou treine um clone de voz profissional com mais de 20 minutos de áudio, para fazer vídeos sem filmar. • Dar novos visuais ao seu avatar. Crie roupas, penteados e fundos novos com uma descrição, um modelo de estilo ou um pack temático de visuais, e faça vídeos seus com qualquer visual. • Pôr uma fotografia a falar. Transforme a foto ou retrato de uma pessoa num vídeo falado com sincronização labial, ou crie um avatar com uma foto ou descrição em texto. • Criar locuções e áudio. Gere locuções com IA e narração de texto para voz (TTS) em muitas vozes e línguas, crie uma voz personalizada por descrição, transforme a voz de uma gravação na sua própria voz clonada com um modificador de voz com IA (speech-to-speech) e adicione música e efeitos sonoros. • Criar imagens com IA. Gere qualquer imagem com um prompt de texto ou imagens de referência. Com o HeyGen Image, coloque-se a si ou ao seu avatar em qualquer cenário para retratos profissionais com IA, fotos de perfil, sessões fotográficas e uma personagem consistente: mantém o rosto das suas fotos e usa pose, roupa e iluminação de uma referência; depois, anime o resultado em vídeo. • Gerar vídeos com IA no HeyGen Video 1. Texto para vídeo, imagem para vídeo e referência para vídeo para cenas cinematográficas, vídeos de produto, anúncios, animações, B-roll e clips curtos na horizontal, vertical ou quadrado. Crie cenas de Cinematic Avatar com até três dos seus avatares. • Fazer vídeos mais longos. Transforme um tema, post de blogue, artigo ou documento num vídeo narrado com cenas, B-roll, legendas, música e grafismos no ecrã com o Video Agent e aperfeiçoe-o no chat. Faça vídeos faceless, explicativos, histórias narradas com imagens e vídeos tipo diapositivos. • Criar anúncios UGC e para redes sociais. Crie anúncios UGC com IA, análises de produtos, tutoriais, try-on hauls, unboxings, promos de sites e apps, anúncios para e-commerce e vídeos ASMR de produto com fotos do produto ou do seu site. • Planear conteúdo. Escreva guiões e ganchos, e planeie e produza uma série de vídeos recorrente para YouTube, TikTok ou Instagram com calendário. • Traduzir e dobrar vídeos. Use dobragem com IA e tradução de vídeo para mais de 175 línguas e dialetos, como espanhol, japonês, hindi e árabe, com clonagem de voz, sincronização labial e legendas. Faça lip-sync de qualquer vídeo com novo áudio para substituir ou corrigir falas. • Reaproveitar e limpar gravações. Use o corte com IA para transformar vídeos longos, videopodcasts, webinars e diretos em Shorts e Reels, e remova palavras de enchimento e silêncios longos. • Personalizar e escalar. Transforme um vídeo num modelo reutilizável, troque nomes e textos e gere muitos vídeos personalizados em lote. Aplique kits de marca com o seu logótipo e cores, e glossários de marca para a pronúncia. • Gerir a sua biblioteca HeyGen. Explore e organize vídeos, avatares, vozes, modelos e ficheiros em pastas, acompanhe o progresso e descarregue os vídeos concluídos. Ligue a sua conta HeyGen para começar. Video-uri, voci și avatare AI Creează videoclipuri cu AI, avatare care vorbesc, imagini AI, voiceover, clone de voce și clipuri traduse cu HeyGen în ChatGPT. Transformă o idee, scenariu, articol, document, poză, produs, audio sau filmări existente în clipuri de marketing, reclame, demo-uri de produs, UGC, explicative, training și clipuri social media pentru YouTube, YouTube Shorts, TikTok, Instagram Reels, LinkedIn și site-uri. Ce poți face cu HeyGen: • Creează clipuri cu avatare care vorbesc. Un avatar AI, prezentator virtual sau purtător de cuvânt îți prezintă scenariul sau audio-ul în anunțuri, vânzări, onboarding, training HR și compliance, cursuri, prezentări, mesaje pentru clienți și felicitări. Adaugă B-roll, muzică, subtitrări și motion graphics sau exportă avatarul pe fundal transparent ca să-l pui peste conținutul tău. • Clonează-te. Creează-ți o clonă AI: un Digital Twin dintr-un clip scurt sau un avatar foto dintr-o singură imagine. Clonează-ți vocea instant dintr-o înregistrare sau antrenează o clonă de voce profesională din peste 20 de minute de audio, ca să faci clipuri fără să filmezi. • Dă-i avatarului tău look-uri noi. Creează ținute, coafuri și fundaluri noi dintr-o descriere, un șablon de stil sau un pachet tematic de look-uri, apoi fă clipuri cu tine în orice look. • Fă o poză să vorbească. Transformă poza sau portretul unei persoane într-un clip vorbit cu lip-sync sau creează un avatar dintr-o poză ori o descriere text. • Creează voiceover și audio. Generează voiceover cu AI și narațiune text-to-speech (TTS) cu multe voci și limbi, creează o voce personalizată dintr-o descriere, transformă vocea dintr-o înregistrare în propria ta voce clonată cu un modificator de voce AI (speech-to-speech) și adaugă muzică și efecte sonore. • Creează imagini AI. Generează orice imagine dintr-un prompt text sau din imagini de referință. Cu HeyGen Image, pune-te pe tine sau avatarul tău în orice scenă pentru portrete profesionale AI, poze de profil, ședințe foto și un personaj consecvent: păstrează chipul din pozele tale și preia postura, ținuta și lumina dintr-o referință, apoi animă-l într-un clip. • Generează videoclipuri AI cu HeyGen Video 1. Text-to-video, image-to-video și reference-to-video pentru scene cinematice, clipuri de produs, reclame, animații, B-roll și clipuri scurte orizontale, verticale sau pătrate. Creează scene Cinematic Avatar cu până la trei dintre avatarele tale. • Fă videoclipuri mai lungi. Transformă un subiect, o postare, un articol sau document într-un clip narat cu scene, B-roll, subtitrări, muzică și grafică pe ecran cu Video Agent, apoi rafinează-l în chat. Fă clipuri faceless, explicative, povești narate cu imagini și slideshow-uri. • Creează reclame UGC și social media. Fă reclame UGC cu AI, recenzii, tutoriale, try-on haul-uri, unboxing-uri, promo-uri de site-uri și app-uri, reclame e-commerce și clipuri ASMR cu produse, din pozele produsului sau de pe site-ul tău. • Planifică-ți conținutul. Scrie scenarii și hook-uri, planifică și produce o serie recurentă de clipuri pentru YouTube, TikTok sau Instagram, după calendar. • Tradu și dublează videoclipuri. Folosește dublaj AI și traducere video în peste 175 de limbi și dialecte, precum spaniolă, japoneză, hindi și arabă, cu clonare de voce, lip-sync și subtitrări. Fă lip-sync pe orice clip cu audio nou ca să înlocuiești sau corectezi replici. • Refolosește și curăță filmările. Transformă cu clipping AI videoclipuri lungi, video podcasturi, webinarii și live-uri în Shorts și Reels și elimină cuvintele de umplutură și pauzele lungi. • Personalizează și scalează. Transformă un clip într-un șablon reutilizabil, înlocuiește nume și texte și generează multe clipuri personalizate în lot. Aplică brand kit-uri cu logo-ul și culorile tale și glosare de brand pentru pronunție. • Gestionează-ți biblioteca HeyGen. Răsfoiește și organizează clipuri, avatare, voci, șabloane și fișiere în foldere, urmărește progresul și descarcă clipurile gata. Conectează-ți contul HeyGen ca să începi. Видео, голос и ИИ-аватары Создавайте ИИ-видео, говорящие аватары, ИИ-изображения, озвучку, клоны голоса и переведённые видео с HeyGen в ChatGPT. Превращайте идею, сценарий, статью, документ, фото, товар, аудиозапись или готовые кадры в маркетинговые видео, рекламу, демо продуктов, UGC, объясняющие ролики, обучение, туториалы, презентации и ролики для соцсетей: YouTube, YouTube Shorts, TikTok, Instagram Reels, LinkedIn и сайтов. С HeyGen вы можете: • Создавать видео с говорящим аватаром. ИИ-аватар, ИИ-ведущий или спикер озвучит ваш сценарий или аудио для анонсов, продаж, онбординга, обучения по HR и комплаенсу, курсов, презентаций, сообщений клиентам и поздравлений с днём рождения или праздниками. Добавьте B-roll, музыку, субтитры и моушн-графику или экспортируйте аватар на прозрачном фоне, для наложения на свой контент. • Клонировать себя. Создайте своего ИИ-клона: Digital Twin (цифровой двойник) по короткому видео или фотоаватар по одному снимку. Клонируйте голос мгновенно по одной записи или обучите профессиональный клон голоса на 20+ минутах аудио, чтобы делать видео без съёмок. • Давать аватару новые образы. Создавайте новые наряды, причёски и фоны для аватара по описанию, шаблону стиля или тематическому набору образов, и делайте видео с собой в любом образе. • Оживлять фото. Превратите фото или портрет человека в говорящее видео с синхронизацией губ или создайте аватар по фото или текстовому описанию. • Создавать озвучку и аудио. Генерируйте ИИ-озвучку и синтез речи (TTS) с множеством голосов и языков, создайте собственный голос по описанию, переозвучьте запись своим клонированным голосом с помощью ИИ-изменителя голоса (speech-to-speech) и добавьте музыку и звуковые эффекты. • Создавать ИИ-изображения. Генерируйте любое изображение по текстовому промпту или референсам. С HeyGen Image поместите себя или свой аватар в любую сцену для ИИ-портретов, аватарок, фотосессий и единого персонажа: он сохраняет лицо с ваших фото, а позу, одежду и свет берёт с референса; результат можно оживить в видео. • Генерировать ИИ-видео с HeyGen Video 1. Текст в видео, изображение в видео и видео по референсу: кинематографичные сцены, видео о товарах, реклама, анимация, B-roll и короткие клипы в горизонтальном, вертикальном или квадратном формате. Создавайте сцены Cinematic Avatar с участием до трёх ваших аватаров. • Делать длинные видео. Превратите тему, пост в блоге, статью или документ в видео с озвучкой, сценами, B-roll, субтитрами, музыкой и графикой на экране с помощью Video Agent, затем доработайте его в чате. Делайте видео без лица (faceless), объясняющие ролики, озвученные истории в картинках и видео в стиле слайд-шоу. • Создавать UGC и рекламу для соцсетей. ИИ-реклама в стиле UGC, обзоры товаров, туториалы, примерки (try-on), распаковки, промо сайтов и приложений, реклама товаров для e-commerce и ASMR-видео о товарах — по фото товаров или вашему сайту. • Планировать контент. Пишите сценарии и хуки для видео, планируйте и выпускайте регулярную серию видео для YouTube, TikTok или Instagram по расписанию. • Переводить и дублировать видео. ИИ-дубляж и перевод видео на 175+ языков и диалектов, включая испанский, французский, немецкий, португальский, японский, корейский, китайский, хинди и арабский, с клонированием голоса, синхронизацией губ и субтитрами. Синхронизируйте губы в любом видео с новым аудио для замены или правки реплик. • Перерабатывать и чистить записи. ИИ-нарезка превращает длинные видео, видеоподкасты, вебинары и стримы в Shorts и Reels; удаляйте слова-паразиты и долгие паузы. • Персонализировать и масштабировать. Превратите видео в многоразовый шаблон, меняйте имена и текст и создавайте много персональных видео одним пакетом. Применяйте брендкиты с логотипом и фирменными цветами и глоссарии бренда для произношения. • Управлять библиотекой HeyGen. Просматривайте и упорядочивайте видео, аватары, голоса, шаблоны и ассеты по папкам, отслеживайте прогресс и скачивайте готовые видео. Подключите аккаунт HeyGen, чтобы начать. AI-videor, röster & avatarer Skapa AI-videor, talande avatarer, AI-bilder, voiceovers, röstkloner och översatta videor med HeyGen i ChatGPT. Gör en idé, ett manus, en artikel, ett dokument, ett foto, en produkt, en ljudinspelning eller befintligt material till marknadsföringsvideor, annonser, produktdemos, UGC, förklaringsvideor, utbildningar, guider, presentationer och sociala videor för YouTube, YouTube Shorts, TikTok, Instagram Reels, LinkedIn och webbplatser. Med HeyGen kan du: • Göra videor med talande avatarer. Låt en AI-avatar, AI-presentatör eller talesperson framföra ditt manus eller ljud för meddelanden, säljutskick, onboarding, HR- och compliance-utbildningar, kurser, kundmeddelanden och födelsedags- eller högtidshälsningar. Lägg till B-roll, musik, undertexter och rörlig grafik, eller exportera avataren med transparent bakgrund som overlay. • Klona dig själv. Skapa en AI-klon av dig själv: en Digital Twin från en kort video eller en fotoavatar från en enda bild. Klona din röst direkt från en inspelning, eller träna en professionell röstklon på 20+ minuter ljud, så du kan göra videor utan att filma. • Ge din avatar nya looks. Skapa nya kläder, frisyrer och bakgrunder för din avatar utifrån en beskrivning, stilmall eller ett tematiskt lookpaket, och gör videor av dig själv i valfri look. • Få ett foto att prata. Gör ett foto eller porträtt av en person till en talande, läppsynkad video, eller skapa en avatar från ett foto eller en textbeskrivning. • Skapa voiceovers och ljud. Generera AI-voiceovers och text-till-tal (TTS) i många röster och språk, designa en egen röst utifrån en beskrivning, byt rösten i en inspelning till din egen klonade röst med en AI-voice changer (speech-to-speech), och lägg till musik och ljudeffekter. • Skapa AI-bilder. Generera valfri bild från en textprompt eller referensbilder. Med HeyGen Image placerar du dig själv eller din avatar i valfri miljö för AI-porträtt, profilbilder, fotograferingar och en konsekvent karaktär: ansiktet från dina foton, pose, kläder och ljus från en referens, och sedan kan du animera resultatet till video. • Generera AI-videor med HeyGen Video 1. Text-till-video, bild-till-video och referens-till-video för filmiska scener, produktvideor, annonser, animationer, B-roll och korta klipp i liggande, stående eller kvadratiskt format. Skapa Cinematic Avatar-scener med upp till tre av dina avatarer. • Göra längre videor. Gör ett ämne, ett blogginlägg, en artikel eller ett dokument till en berättad video med scener, B-roll, undertexter, musik och grafik i bild med Video Agent, och finslipa den i chatten. Gör faceless-videor, förklaringsvideor, berättade bildberättelser och videor i bildspelsstil. • Göra UGC- och sociala annonser. Skapa AI-UGC-annonser, produktrecensioner, guider, try-on hauls, unboxings, reklam för webbplatser och appar, e-handelsannonser och ASMR-produktvideor från dina produktfoton eller din webbplats. • Planera innehåll. Skriv videomanus och hooks, och planera och producera en videoserie för YouTube, TikTok eller Instagram enligt schema. • Översätta och dubba videor. Använd AI-dubbning och videoöversättning till 175+ språk och dialekter, bland annat spanska, franska, tyska, portugisiska, japanska, koreanska, kinesiska, hindi och arabiska, med röstkloning, läppsynk och undertexter. Läppsynka valfri video till nytt ljud för att ersätta eller rätta repliker. • Återanvända och städa upp material. Använd AI-klippning för att göra långa videor, videopoddar, webbinarier och livesändningar till Shorts och Reels, och ta bort utfyllnadsord och långa tystnader. • Personalisera och skala upp. Gör en video till en återanvändbar mall, byt namn och text och generera många personliga videor i en batch. Använd varumärkeskit med logga och färger, och varumärkesordlistor för uttal. • Hantera ditt HeyGen-bibliotek. Bläddra bland och organisera videor, avatarer, röster, mallar och tillgångar i mappar, kolla förloppet och ladda ner färdiga videor. Anslut ditt HeyGen-konto för att komma igång. สร้างวิดีโอ เสียง และอวาตาร์ สร้างวิดีโอ AI อวาตาร์พูดได้ ภาพ AI เสียงพากย์ โคลนเสียง และวิดีโอแปลภาษาด้วย HeyGen ใน ChatGPT เปลี่ยนไอเดีย สคริปต์ บทความ เอกสาร รูปภาพ สินค้า ไฟล์เสียง หรือฟุตเทจที่มีอยู่ ให้เป็นวิดีโอการตลาด โฆษณา เดโมสินค้า UGC วิดีโออธิบาย (explainer) วิดีโอฝึกอบรม ทิวทอเรียล งานนำเสนอ และวิดีโอโซเชียลสำหรับ YouTube, YouTube Shorts, TikTok, Instagram Reels, LinkedIn และเว็บไซต์ ด้วย HeyGen คุณสามารถ: • สร้างวิดีโออวาตาร์พูดได้ ให้อวาตาร์ AI พรีเซนเตอร์ AI หรือโฆษก พูดตามสคริปต์หรือเสียงของคุณ สำหรับประกาศ การติดต่อขาย ออนบอร์ดดิ้ง การอบรม HR และ compliance คอร์สเรียน งานนำเสนอ ข้อความถึงลูกค้า และคำอวยพรวันเกิดหรือวันหยุดเทศกาล เพิ่ม B-roll เพลง แคปชัน และ motion graphics หรือส่งออกอวาตาร์บนพื้นหลังโปร่งใสเพื่อซ้อนบนคอนเทนต์ของคุณเอง • โคลนตัวเอง สร้างโคลน AI ของตัวคุณเอง: Digital Twin จากวิดีโอสั้น หรืออวาตาร์จากรูปภาพเพียงรูปเดียว โคลนเสียงของคุณได้ทันทีจากไฟล์บันทึกเสียงเพียงไฟล์เดียว หรือเทรนโคลนเสียงระดับมืออาชีพจากเสียงความยาว 20+ นาที เพื่อทำวิดีโอได้โดยไม่ต้องถ่ายทำ • เปลี่ยนลุคใหม่ให้อวาตาร์ สร้างชุด ทรงผม และพื้นหลังใหม่ให้อวาตาร์ของคุณจากคำอธิบาย เทมเพลตสไตล์ หรือแพ็กลุคตามธีม แล้วทำวิดีโอของตัวคุณเองในลุคไหนก็ได้ • ทำให้รูปภาพพูดได้ เปลี่ยนรูปภาพหรือภาพพอร์ตเทรตของบุคคลให้เป็นวิดีโอพูดได้แบบลิปซิงก์ หรือสร้างอวาตาร์จากรูปภาพหรือคำอธิบายข้อความ • สร้างเสียงพากย์และไฟล์เสียง สร้างเสียงพากย์ AI และเสียงบรรยายแบบ text-to-speech (TTS) ได้หลายเสียงและหลายภาษา ออกแบบเสียงเฉพาะตัวจากคำอธิบาย เปลี่ยนเสียงในไฟล์ที่อัดไว้ให้เป็นเสียงโคลนของคุณเองด้วย AI เปลี่ยนเสียง (voice changer แบบ speech-to-speech) และเพิ่มเพลงและเอฟเฟกต์เสียง • สร้างภาพ AI สร้างภาพอะไรก็ได้จาก prompt ข้อความหรือภาพอ้างอิง ส่วน HeyGen Image ช่วยใส่ตัวคุณหรืออวาตาร์ของคุณลงในฉากใดก็ได้ สำหรับ AI headshot รูปโปรไฟล์ โฟโต้ชูต และตัวละครที่หน้าตาคงเดิม โดยคงใบหน้าจากรูปของคุณไว้ และนำท่าทาง ชุด และแสงจากภาพอ้างอิงมาใช้ จากนั้นทำให้ผลลัพธ์เคลื่อนไหวเป็นวิดีโอได้ • สร้างวิดีโอ AI ด้วย HeyGen Video 1 แบบ text-to-video, image-to-video และ reference-to-video สำหรับฉากระดับภาพยนตร์ วิดีโอสินค้า โฆษณา แอนิเมชัน B-roll และคลิปสั้น ในแนวนอน แนวตั้ง หรือสี่เหลี่ยมจัตุรัส สร้างฉาก Cinematic Avatar ที่มีอวาตาร์ของคุณได้สูงสุดสามตัว • สร้างวิดีโอที่ยาวขึ้น เปลี่ยนหัวข้อ บล็อกโพสต์ บทความ หรือเอกสาร ให้เป็นวิดีโอพร้อมเสียงบรรยาย มีฉาก B-roll แคปชัน เพลง และกราฟิกบนหน้าจอ ด้วย Video Agent แล้วปรับแต่งต่อในแชต สร้างวิดีโอแบบไม่เห็นหน้า (faceless) วิดีโออธิบาย เรื่องเล่าจากภาพพร้อมเสียงบรรยาย และวิดีโอสไตล์สไลด์โชว์ • สร้าง UGC และโฆษณาโซเชียล สร้างโฆษณา UGC ด้วย AI รีวิวสินค้า ทิวทอเรียล วิดีโอลองสวม (try-on haul) แกะกล่อง (unboxing) วิดีโอโปรโมตเว็บไซต์และแอป โฆษณาสินค้าอีคอมเมิร์ซ และวิดีโอสินค้าแนว ASMR จากรูปสินค้าหรือเว็บไซต์ของคุณ • วางแผนคอนเทนต์ เขียนสคริปต์และ hook วิดีโอ รวมถึงวางแผนและผลิตซีรีส์วิดีโอที่ออกต่อเนื่องสำหรับ YouTube, TikTok หรือ Instagram ตามตารางเวลา • แปลและพากย์วิดีโอ ใช้ AI พากย์เสียง (dubbing) และแปลวิดีโอเป็น 175+ ภาษาและภาษาถิ่น รวมถึงสเปน ฝรั่งเศส เยอรมัน โปรตุเกส ญี่ปุ่น เกาหลี จีน ฮินดี และอาหรับ พร้อมโคลนเสียง ลิปซิงก์ และซับไตเติล ลิปซิงก์วิดีโอใดก็ได้เข้ากับเสียงใหม่เพื่อแทนที่หรือแก้ไขบทพูด • นำฟุตเทจมาใช้ใหม่และเก็บงาน ใช้ AI clipping ตัดวิดีโอยาว วิดีโอพอดแคสต์ เว็บบินาร์ และไลฟ์สตรีม ให้เป็น Shorts และ Reels และลบคำฟุ่มเฟือย (filler words) และช่วงเงียบที่ยาวเกินไป • ปรับให้เป็นส่วนตัวและขยายสเกล เปลี่ยนวิดีโอให้เป็นเทมเพลตที่ใช้ซ้ำได้ เปลี่ยนชื่อและข้อความ และสร้างวิดีโอเฉพาะบุคคลจำนวนมากได้ในครั้งเดียว (batch) ใช้ brand kit ที่มีโลโก้และสีของคุณ และอภิธานศัพท์แบรนด์ (brand glossary) สำหรับการออกเสียง • จัดการคลัง HeyGen ของคุณ เรียกดูและจัดระเบียบวิดีโอ อวาตาร์ เสียง เทมเพลต และแอสเซ็ตในโฟลเดอร์ ตรวจสอบความคืบหน้า และดาวน์โหลดวิดีโอที่เสร็จแล้ว เชื่อมต่อบัญชี HeyGen ของคุณเพื่อเริ่มต้นใช้งาน Video, ses ve avatar üretin HeyGen ile ChatGPT'de yapay zeka videoları, konuşan avatarlar, AI görseller, seslendirmeler, ses klonları ve çevrilmiş videolar oluşturun. Fikir, senaryo, makale, belge, fotoğraf, ürün, ses kaydı veya mevcut görüntülerden YouTube, YouTube Shorts, TikTok, Instagram Reels, LinkedIn ve siteler için pazarlama videoları, reklamlar, ürün demoları, UGC, açıklayıcı videolar, eğitimler, öğreticiler, sunumlar ve sosyal medya videoları üretin. HeyGen ile şunları yapabilirsiniz: • Konuşan avatar videoları yapın. AI avatar, AI sunucu veya sözcü; duyurular, satış iletişimi, oryantasyon, İK ve uyum eğitimleri, kurslar, sunumlar, müşteri mesajları, doğum günü ve bayram tebrikleri için senaryonuzu ya da sesinizi sunsun. B-roll, müzik, altyazı ve hareketli grafik ekleyin ya da avatarı içeriğinize bindirmek için şeffaf arka planla dışa aktarın. • Kendinizi klonlayın. AI klonunuzu oluşturun: kısa bir videodan Digital Twin (dijital ikiz) veya tek görselden fotoğraf avatarı. Sesinizi tek kayıttan anında klonlayın ya da 20+ dakikalık sesle profesyonel ses klonu eğitin, çekim yapmadan video üretin. • Avatarınıza yeni görünümler verin. Açıklama, stil şablonu veya temalı görünüm paketiyle avatarınıza yeni kıyafet, saç modeli ve arka plan oluşturun, sonra her görünümde kendi videolarınızı yapın. • Fotoğrafı konuşturun. Bir kişinin fotoğrafını veya portresini dudak senkronlu konuşan videoya dönüştürün ya da fotoğraftan veya metin açıklamasından avatar oluşturun. • Seslendirme ve ses oluşturun. Birçok ses ve dilde AI seslendirme ve metinden sese (TTS) anlatım üretin, açıklamadan özel ses tasarlayın, AI ses değiştirici (speech-to-speech) ile bir kaydı kendi klonlanmış sesinizle yeniden seslendirin, müzik ve ses efektleri ekleyin. • AI görseller oluşturun. Metin prompt'undan veya referans görsellerden her türlü görseli üretin. HeyGen Image ile kendinizi veya avatarınızı her sahneye koyun: AI vesikalık ve profil fotoğrafları, fotoğraf çekimleri ve tutarlı bir karakter. Yüzü fotoğraflarınızdan, pozu, kıyafeti ve ışığı referanstan alır; sonucu videoya dönüştürün. • HeyGen Video 1 ile AI videoları üretin. Metinden, görselden ve referanstan videoya: sinematik sahneler, ürün videoları, reklamlar, animasyonlar, B-roll ve yatay, dikey veya kare kısa klipler. En fazla üç avatarınızla Cinematic Avatar sahneleri oluşturun. • Daha uzun videolar yapın. Video Agent ile konu, blog yazısı, makale veya belgeyi sahneler, B-roll, altyazı, müzik ve ekran grafikleriyle anlatımlı videoya dönüştürün, sonra sohbette geliştirin. Yüzsüz (faceless) ve açıklayıcı videolar, anlatımlı resimli hikâyeler ve slayt tarzı videolar yapın. • UGC ve sosyal medya reklamları yapın. Ürün fotoğraflarınızdan veya sitenizden AI UGC reklamları, ürün incelemeleri, öğreticiler, try-on videoları, kutu açılışları, site ve uygulama tanıtımları, e-ticaret ürün reklamları ve ASMR ürün videoları oluşturun. • İçerik planlayın. Video senaryoları ve hook'lar yazın; YouTube, TikTok veya Instagram için düzenli video serisini takvimle planlayıp üretin. • Videoları çevirin ve dublajlayın. İspanyolca, Fransızca, Almanca, Portekizce, Japonca, Korece, Çince, Hintçe ve Arapça dahil 175+ dil ve lehçede ses klonlama, dudak senkronu ve altyazıyla AI dublaj ve video çevirisi yapın. Replik değiştirmek veya düzeltmek için her videoyu yeni sese dudak senkronlayın. • Görüntüleri yeniden kullanın ve temizleyin. AI klip çıkarma ile uzun videoları, video podcast'leri, webinarları ve canlı yayınları Shorts ve Reels'e dönüştürün; dolgu kelimelerini ve uzun sessizlikleri silin. • Kişiselleştirin ve ölçeklendirin. Videoyu tekrar kullanılabilir şablona çevirin, isim ve metinleri değiştirin, tek seferde çok sayıda kişisel video üretin. Logonuz ve renklerinizle marka kitleri, telaffuz için marka sözlükleri uygulayın. • HeyGen kitaplığınızı yönetin. Videoları, avatarları, sesleri, şablonları ve varlıkları klasörlerde görüntüleyip düzenleyin, ilerlemeyi izleyin ve bitmiş videoları indirin. Başlamak için HeyGen hesabınızı bağlayın. Відео, голос і ШІ-аватари Створюйте ШІ-відео, аватари, що говорять, ШІ-зображення, озвучення, клони голосу та перекладені відео з HeyGen у ChatGPT. Перетворюйте ідею, сценарій, статтю, документ, фото, товар, аудіозапис або наявні кадри на маркетингові відео, рекламу, демо продуктів, UGC, пояснювальні ролики, навчання, туторіали, презентації та відео для соцмереж: YouTube, YouTube Shorts, TikTok, Instagram Reels, LinkedIn і сайтів. З HeyGen ви можете: • Створювати відео з аватаром, що говорить. ШІ-аватар, ШІ-ведучий чи спікер озвучить ваш сценарій або аудіо для анонсів, продажів, онбордингу, навчання з HR і комплаєнсу, курсів, презентацій, повідомлень клієнтам і привітань із днем народження чи святами. Додайте B-roll, музику, субтитри й моушн-графіку або експортуйте аватар на прозорому тлі, щоб накласти його на власний контент. • Клонувати себе. Створіть свого ШІ-клона: Digital Twin (цифровий двійник) з короткого відео або фотоаватар з одного знімка. Клонуйте голос миттєво з одного запису або навчіть професійний клон голосу на 20+ хвилинах аудіо, щоб створювати відео без зйомок. • Давати аватару нові образи. Створюйте нове вбрання, зачіски й фони для аватара за описом, шаблоном стилю або тематичним набором образів, і робіть відео із собою в будь-якому образі. • Оживляти фото. Перетворіть фото чи портрет людини на відео, де вона говорить, із синхронізацією губ або створіть аватар із фото чи текстового опису. • Створювати озвучення й аудіо. Генеруйте ШІ-озвучення та синтез мовлення (TTS) багатьма голосами й мовами, створіть власний голос за описом, переозвучте запис своїм клонованим голосом за допомогою ШІ-змінювача голосу (speech-to-speech) і додайте музику та звукові ефекти. • Створювати ШІ-зображення. Генеруйте будь-яке зображення за текстовим промптом або референсами. З HeyGen Image помістіть себе чи свій аватар у будь-яку сцену для ШІ-портретів, аватарок, фотосесій і єдиного персонажа: він зберігає обличчя з ваших фото, а позу, одяг і світло бере з референсу; результат можна оживити у відео. • Генерувати ШІ-відео з HeyGen Video 1. Текст у відео, зображення у відео та відео за референсом: кінематографічні сцени, відео про товари, реклама, анімація, B-roll і короткі кліпи в горизонтальному, вертикальному чи квадратному форматі. Створюйте сцени Cinematic Avatar за участю до трьох ваших аватарів. • Створювати довші відео. Перетворіть тему, допис у блозі, статтю чи документ на відео з озвученням, сценами, B-roll, субтитрами, музикою й графікою на екрані за допомогою Video Agent, і доопрацюйте його в чаті. Створюйте відео без обличчя (faceless), пояснювальні ролики, озвучені історії в картинках і відео у стилі слайдшоу. • Створювати UGC і рекламу для соцмереж. ШІ-реклама в стилі UGC, огляди товарів, туторіали, приміряння (try-on), розпакування, промо сайтів і застосунків, реклама товарів для e-commerce та ASMR-відео про товари — з фото товарів або вашого сайту. • Планувати контент. Пишіть сценарії та хуки для відео, плануйте й випускайте регулярну серію відео для YouTube, TikTok чи Instagram за розкладом. • Перекладати й дублювати відео. ШІ-дубляж і переклад відео 175+ мовами та діалектами, зокрема іспанською, французькою, німецькою, португальською, японською, корейською, китайською, гінді та арабською, із клонуванням голосу, синхронізацією губ і субтитрами. Синхронізуйте губи в будь-якому відео з новим аудіо, щоб замінити чи виправити репліки. • Переробляти й очищувати записи. ШІ-нарізка перетворює довгі відео, відеоподкасти, вебінари та стріми на Shorts і Reels; видаляйте слова-паразити та довгі паузи. • Персоналізувати й масштабувати. Перетворіть відео на багаторазовий шаблон, змінюйте імена й текст і створюйте багато персоналізованих відео одним пакетом. Застосовуйте брендкити з логотипом і фірмовими кольорами та глосарії бренду для вимови. • Керувати бібліотекою HeyGen. Переглядайте й упорядковуйте відео, аватари, голоси, шаблони та ресурси в папках, відстежуйте прогрес і завантажуйте готові відео. Підключіть акаунт HeyGen, щоб почати. Tạo video, giọng nói và avatar Tạo video AI, avatar biết nói, ảnh AI, giọng đọc AI, nhân bản giọng nói và video dịch với HeyGen trong ChatGPT. Biến ý tưởng, kịch bản, bài viết, tài liệu, ảnh, sản phẩm, bản ghi âm hoặc cảnh quay sẵn có thành video marketing, quảng cáo, demo sản phẩm, UGC, video giải thích, đào tạo, hướng dẫn, thuyết trình và video mạng xã hội cho YouTube, YouTube Shorts, TikTok, Instagram Reels, LinkedIn và website. Với HeyGen, bạn có thể: • Làm video avatar biết nói. Để avatar AI, người dẫn AI hoặc người phát ngôn trình bày kịch bản hay âm thanh của bạn cho thông báo, tiếp cận khách hàng, onboarding, đào tạo nhân sự và tuân thủ, khóa học, thuyết trình, tin nhắn khách hàng và lời chúc sinh nhật hay ngày lễ. Thêm B-roll, nhạc, phụ đề và đồ họa chuyển động, hoặc xuất avatar trên nền trong suốt để chồng lên nội dung của bạn. • Nhân bản chính bạn. Tạo bản sao AI của bạn: Digital Twin từ một video ngắn, hoặc avatar ảnh từ một bức ảnh. Nhân bản giọng nói tức thì từ một bản ghi âm, hoặc huấn luyện bản nhân bản giọng chuyên nghiệp từ 20+ phút âm thanh, để làm video mà không cần quay. • Đổi diện mạo cho avatar. Tạo trang phục, kiểu tóc và phông nền mới cho avatar từ mô tả, mẫu phong cách hoặc gói diện mạo theo chủ đề, rồi làm video của chính bạn với bất kỳ diện mạo nào. • Làm ảnh biết nói. Biến ảnh hoặc chân dung một người thành video biết nói khớp khẩu hình, hoặc tạo avatar từ ảnh hay mô tả văn bản. • Tạo giọng đọc và âm thanh. Tạo giọng đọc AI và chuyển văn bản thành giọng nói (TTS) với nhiều giọng và ngôn ngữ, thiết kế giọng riêng từ mô tả, chuyển một bản ghi âm sang giọng nhân bản của chính bạn bằng công cụ đổi giọng AI (AI voice changer, speech-to-speech), và thêm nhạc nền, hiệu ứng âm thanh. • Tạo ảnh AI. Tạo bất kỳ hình ảnh nào từ câu lệnh văn bản (prompt) hoặc ảnh tham chiếu. Với HeyGen Image, đặt bạn hoặc avatar vào bất kỳ bối cảnh nào để có ảnh chân dung AI, ảnh đại diện, bộ ảnh và một nhân vật nhất quán: giữ khuôn mặt từ ảnh của bạn và lấy tư thế, trang phục, ánh sáng từ ảnh tham chiếu, rồi biến kết quả thành video. • Tạo video AI với HeyGen Video 1. Văn bản thành video, ảnh thành video và video từ ảnh tham chiếu cho cảnh điện ảnh, video sản phẩm, quảng cáo, hoạt hình, B-roll và clip ngắn ở khung ngang, dọc hoặc vuông. Tạo cảnh Cinematic Avatar với tối đa ba avatar của bạn. • Làm video dài hơn. Dùng Video Agent biến chủ đề, bài blog, bài viết hoặc tài liệu thành video có lời dẫn với các cảnh, B-roll, phụ đề, nhạc và đồ họa trên màn hình, rồi chỉnh sửa ngay trong chat. Làm video không lộ mặt, video giải thích, truyện bằng hình có lời kể và video dạng trình chiếu. • Làm UGC và quảng cáo mạng xã hội. Tạo quảng cáo UGC bằng AI, review sản phẩm, video hướng dẫn, video thử đồ, đập hộp, video quảng bá website và ứng dụng, quảng cáo sản phẩm thương mại điện tử và video sản phẩm ASMR từ ảnh sản phẩm hay website của bạn. • Lên kế hoạch nội dung. Viết kịch bản video và hook, lên kế hoạch và sản xuất series video định kỳ cho YouTube, TikTok hoặc Instagram theo lịch. • Dịch và lồng tiếng video. Dùng lồng tiếng AI và dịch video sang 175+ ngôn ngữ và phương ngữ, gồm tiếng Tây Ban Nha, Pháp, Đức, Bồ Đào Nha, Nhật, Hàn, Trung, Hindi và Ả Rập, kèm nhân bản giọng nói, khớp khẩu hình và phụ đề. Khớp khẩu hình bất kỳ video nào với âm thanh mới để thay hoặc sửa lời thoại. • Tái sử dụng và làm sạch cảnh quay. Dùng AI cắt clip để biến video dài, video podcast, webinar và livestream thành Shorts và Reels, đồng thời xóa từ đệm và các khoảng lặng dài. • Cá nhân hóa và mở rộng quy mô. Biến video thành template tái sử dụng, thay tên và văn bản, rồi tạo hàng loạt video cá nhân hóa trong một lần. Áp dụng brand kit với logo và màu sắc, cùng bảng thuật ngữ thương hiệu để chuẩn hóa cách phát âm. • Quản lý thư viện HeyGen. Duyệt và sắp xếp video, avatar, giọng nói, template và tài nguyên trong thư mục, kiểm tra tiến độ và tải xuống video đã hoàn tất. Kết nối tài khoản HeyGen để bắt đầu. AI 生成视频、配音与数字人 在 ChatGPT 中使用 HeyGen,制作 AI 视频、会说话的数字人、AI 图片、AI 配音、声音克隆和视频翻译。将创意、脚本、文章、文档、照片、产品、录音或现有素材,制作成营销视频、广告、产品演示、UGC、讲解视频、培训、教程、演示文稿,以及适用于 YouTube、YouTube Shorts、TikTok、Instagram Reels、LinkedIn 和网站的社交媒体视频。 使用 HeyGen,你可以: • 制作数字人口播视频。让 AI 数字人、AI 主持人或代言人讲述你的脚本或音频,用于公告、销售触达、新员工入职、HR 与合规培训、课程、演示、客户消息,以及生日或节日祝福。添加 B-roll、音乐、字幕和动态图形,或导出透明背景的数字人,叠加到你自己的内容上。 • 克隆你自己。打造你的 AI 分身:用一段短视频生成 Digital Twin 数字分身,或用一张照片生成照片数字人。用一段录音即时克隆你的声音,或用 20 分钟以上的音频训练专业级声音克隆,无需拍摄即可制作视频。 • 为数字人换新造型。根据文字描述、风格模板或主题造型包,为数字人生成新服装、新发型和新背景,然后用任意造型制作你自己的视频。 • 让照片开口说话。把人物照片或肖像变成口型同步的说话视频,或根据照片或文字描述创建数字人。 • 制作配音与音频。用多种音色和语言生成 AI 配音和文字转语音(TTS)旁白,根据描述设计专属声音,用 AI 变声器(语音转语音)把录音转换成你本人的克隆声音,并添加背景音乐和音效。 • 生成 AI 图片。通过文字提示词或参考图生成任意图片。使用 HeyGen Image,把你或你的数字人放进任意场景,生成 AI 职业照、头像、写真,并保持角色一致:保留你照片中的面孔,从参考图中采用姿势、服装和光线,之后还能把生成的图片做成视频。 • 使用 HeyGen Video 1 生成 AI 视频。支持文生视频、图生视频和参考生视频,制作电影感场景、产品视频、广告、动画、B-roll 和短片,可选横屏、竖屏或方形。最多可用三个你的数字人创建 Cinematic Avatar 场景。 • 制作长视频。使用 Video Agent 将主题、博客、文章或文档转为带有分镜、B-roll、字幕、音乐和屏幕图形的旁白视频,并在对话中继续修改。还能制作无人出镜视频、讲解视频、有声图文故事和幻灯片式视频。 • 制作 UGC 和社交媒体广告。用产品照片或网站生成 AI UGC 广告、产品测评、教程、试穿分享、开箱视频、网站与 App 推广视频、电商产品广告和 ASMR 产品视频。 • 规划内容。撰写视频脚本和开头钩子,并为 YouTube、TikTok 或 Instagram 按计划策划和制作定期更新的系列视频。 • 视频翻译与配音。通过 AI 配音和视频翻译支持 175+ 种语言和方言,包括西班牙语、法语、德语、葡萄牙语、日语、韩语、中文、印地语和阿拉伯语,并支持声音克隆、口型同步和字幕。还可将任意视频与新音频口型同步,替换或修正台词。 • 素材再利用与清理。使用 AI 剪辑将长视频、视频播客、网络研讨会和直播切成 Shorts 和 Reels 短视频,并去除口头禅和长时间静音。 • 个性化批量生成。把视频做成可复用模板,替换姓名和文字,一次批量生成大量个性化视频。应用包含 Logo 和品牌色的品牌套件,并用品牌词汇表统一发音。 • 管理你的 HeyGen 素材库。在文件夹中浏览和整理视频、数字人、声音、模板和素材,查看进度,并下载已完成的视频。 连接你的 HeyGen 账号,立即开始。 AI 製作影片、配音與數位人 在 ChatGPT 中使用 HeyGen,製作 AI 影片、會說話的數位人、AI 圖片、AI 配音、聲音複製和翻譯影片。把點子、腳本、文章、文件、照片、產品、錄音或現有影片素材,變成行銷影片、廣告、產品展示、UGC、解說影片、教育訓練、教學、簡報,以及適用於 YouTube、YouTube Shorts、TikTok、Instagram Reels、LinkedIn 和網站的社群影片。 使用 HeyGen,你可以: • 製作數位人說話影片。讓 AI 數位人、AI 主持人或代言人講出你的腳本或音訊,用於公告、業務開發、新人到職、人資與法規遵循訓練、課程、簡報、客戶訊息,以及生日或節慶祝福。加入 B-roll、音樂、字幕和動態圖像,或將數位人匯出為透明背景,疊加在你自己的內容上。 • 複製你自己。打造你的 AI 分身:用一段短影片建立 Digital Twin 數位分身,或用一張照片建立照片數位人。只要一段錄音就能立即複製你的聲音,或用 20 分鐘以上的音訊訓練專業級聲音複製,不用拍攝也能做影片。 • 幫數位人換新造型。依文字描述、風格範本或主題造型包,為數位人打造新服裝、新髮型和新背景,再用任何造型製作你自己的影片。 • 讓照片開口說話。將人物照片或肖像變成對嘴同步的說話影片,或用照片或文字描述建立數位人。 • 製作配音和音訊。以多種聲音和語言生成 AI 配音和文字轉語音(TTS)旁白,依描述設計專屬聲音,用 AI 變聲器(語音轉語音)把錄音轉成你本人的複製聲音,並加入背景音樂和音效。 • 生成 AI 圖片。用文字提示或參考圖片生成任何圖片。透過 HeyGen Image,把你或你的數位人放進任何場景,製作 AI 形象照、大頭貼、寫真,並讓角色保持一致:保留你照片中的臉,從參考圖片套用姿勢、服裝和光線,完成後還能把成果做成影片。 • 用 HeyGen Video 1 生成 AI 影片。支援文字轉影片、圖片轉影片和參考圖轉影片,製作電影感場景、產品影片、廣告、動畫、B-roll 和短片,可選橫式、直式或方形。最多可用三個你的數位人建立 Cinematic Avatar 場景。 • 製作長影片。使用 Video Agent 將主題、部落格文章、文章或文件變成含場景、B-roll、字幕、音樂和畫面圖像的旁白影片,再透過對話修改。也能製作不露臉影片、解說影片、有旁白的圖像故事和投影片式影片。 • 製作 UGC 和社群廣告。用產品照片或網站製作 AI UGC 廣告、產品評測、教學影片、試穿分享、開箱影片、網站和 App 宣傳影片、電商產品廣告和 ASMR 產品影片。 • 規劃內容。撰寫影片腳本和開場鉤子,並為 YouTube、TikTok 或 Instagram 依排程規劃與製作固定更新的影片系列。 • 翻譯影片和配音。透過 AI 配音和影片翻譯支援 175+ 種語言和方言,包括西班牙文、法文、德文、葡萄牙文、日文、韓文、中文、印地文和阿拉伯文,並搭配聲音複製、對嘴同步和字幕。也能讓任何影片對嘴新的音訊,替換或修正台詞。 • 重新利用並整理影片素材。使用 AI 剪輯將長影片、影音 Podcast、線上研討會和直播剪成 Shorts 和 Reels,並移除贅詞和過長的靜音。 • 個人化與大量製作。把影片做成可重複使用的範本,替換姓名和文字,一次批次產生大量個人化影片。套用含有 Logo 和品牌色的品牌套件,並用品牌詞彙表統一發音。 • 管理你的 HeyGen 媒體庫。在資料夾中瀏覽和整理影片、數位人、聲音、範本和素材,查看進度,並下載完成的影片。 連結你的 HeyGen 帳號,立即開始。 Gumawa ng video, boses, avatar Gumawa ng AI video, talking avatars, AI images, voiceovers, voice clones at translated video gamit ang HeyGen sa ChatGPT. Gawing marketing video, ads, product demos, UGC, explainers, training, tutorials, presentations at social video para sa YouTube, YouTube Shorts, TikTok, Instagram Reels, LinkedIn at websites ang idea, script, article, document, photo, produkto, audio recording o existing footage. Gamit ang HeyGen, kaya mong: • Gumawa ng talking-avatar video. Ipabasa sa AI avatar, AI presenter o spokesperson ang script o audio mo para sa announcements, sales outreach, onboarding, HR at compliance training, courses, presentations, customer messages at birthday o holiday greetings. Lagyan ng B-roll, music, captions at motion graphics, o i-export ang avatar sa transparent background para i-overlay sa content mo. • I-clone ang sarili mo. Gumawa ng AI clone: Digital Twin mula sa maikling video, o photo avatar mula sa isang photo. I-clone agad ang boses mo mula sa isang recording, o mag-train ng professional voice clone mula sa 20+ minutong audio, para gumawa ng video nang walang shooting. • Bigyan ng bagong looks ang avatar mo. Gumawa ng bagong outfits, hairstyles at backgrounds nito mula sa description, style template o themed look pack, saka gumawa ng video mo sa anumang look. • Pagsalitain ang photo. Gawing talking, lip-synced video ang photo o portrait ng tao, o gumawa ng avatar mula sa photo o text description. • Gumawa ng voiceovers at audio. Gumawa ng AI voiceovers at text-to-speech (TTS) narration sa maraming boses at wika, mag-design ng custom voice mula sa description, gawing sarili mong cloned voice ang boses sa recording gamit ang AI voice changer (speech-to-speech), at lagyan ng music at sound effects. • Gumawa ng AI images. Gumawa ng anumang image mula sa text prompt o reference images. Sa HeyGen Image, ilagay ang sarili o avatar mo sa kahit anong scene para sa AI headshots, profile pictures, photoshoots at consistent na character: kinukuha nito ang mukha sa photos mo at ang pose, outfit at lighting sa reference, saka i-animate bilang video. • Mag-generate ng AI video gamit ang HeyGen Video 1. Text-to-video, image-to-video at reference-to-video para sa cinematic scenes, product video, ads, animations, B-roll at short clips sa landscape, vertical o square. Gumawa ng Cinematic Avatar scenes na may hanggang tatlong avatar mo. • Gumawa ng mas mahabang video. Gamit ang Video Agent, gawing narrated video na may scenes, B-roll, captions, music at on-screen graphics ang topic, blog post, article o document at i-refine sa chat. Pati faceless video, explainers, narrated picture stories at slideshow-style video. • Gumawa ng UGC at social ads: AI UGC ads, product reviews, tutorials, try-on hauls, unboxings, website at app promos, e-commerce product ads at ASMR product video mula sa product photos o website mo. • Mag-plan ng content. Sumulat ng video scripts at hooks, at mag-plan at mag-produce ng recurring video series sa YouTube, TikTok o Instagram on schedule. • I-translate at i-dub ang video. AI dubbing at video translation sa 175+ na wika at dialect, gaya ng Spanish, French, German, Portuguese, Japanese, Korean, Chinese, Hindi at Arabic, na may voice cloning, lip-sync at subtitles. I-lip-sync ang anumang video sa bagong audio para palitan o ayusin ang lines. • I-repurpose at linisin ang footage. Gamit ang AI clipping, gawing Shorts at Reels ang mahabang video, video podcasts, webinars at livestreams, at alisin ang filler words at mahabang silence. • I-personalize at i-scale. Gawing reusable template ang video, palitan ang names at text, at gumawa ng maraming personalized video sa isang batch. Gamitin ang brand kits na may logo at colors mo, at brand glossaries para sa pronunciation. • I-manage ang HeyGen library mo. I-browse at i-organize sa folders ang video, avatars, voices, templates at assets, i-check ang progress, at i-download ang tapos na video. I-connect ang HeyGen account mo para makapagsimula.

Saved package evidence →

What changed

· 5 observations

Capabilities & instructions

Skill instructions changed from “Preserve this workflow's HeyGen Voice engine requirement through a supported compatible voice-selection path. Reuse an accepted voice; otherwise offer the...” to “All HeyGen MCP speech uses HeyGen Voice, so use a voice ID from `choose_voice` or `list_voices`. Reuse an accepted voice;...

View comparison →
Pricing references

Skill instructions changed from “voice/engine provenance, and any reliable timing data to the calling workflow. Do not generate an avatar or a video to obtain a voiceover. Inherit the...” to “voice and model provenance, and any reliable timing data to the calling workflow. Do not generate an avatar or a video to...

View comparison →
Positioning & listing

Full description changed from “cinematic AI videos, and portraits that keep a person's face in any scene with HeyGen Image. Generate voiceovers with text-to-speech (TTS), clone a voice,...” to “talking-photo videos, and cinematic AI videos with HeyGen. Generate or edit any AI image from a prompt or reference images,...

View comparison →

Technical updates · 1

Package or technical metadata updated

View technical comparison →

· 6 observations

Capabilities & instructions

Skill instructions changed from “Produce a finished presenter-led MP4: collect necessary user resources, confirm the avatar and exact look, create A-roll through HeyGen...” to “**This is an end-to-end edited-video workflow. The avatar render is an internal source asset. Never call `show_video` in this workflow,...

View comparison →
Capabilities & instructions

Skill instructions changed from “intake or generate a new presenter. For subtitles, hook captions, and stylistic emphasis, read [captions](../captions/SKILL.md); this skill owns non-caption...” to “intake, generate a new presenter, or display raw A-roll. While the parent polls `get_video`, build actual graphic...

View comparison →
Capabilities & instructions

Skill instructions changed from “Hook or stylistic-caption intervals replace the base subtitle layer visually; they must not create competing text stacks. Preserve explicit user caption...” to “While its A-roll renders, prepare real font assets, measured phrase layouts, highlight styles, and caption-rendering code;...

View comparison →
Capabilities & instructions

Full description changed from “product demos, marketing videos, UGC-style ads, training, and explainers with HeyGen's AI avatars and video generation. Generate text-to-speech voiceovers,...” to “AI avatar videos, cinematic AI videos, and portraits that keep a person's face in any scene with HeyGen Image. Generate...

View comparison →

Technical updates · 1

Package or technical metadata updated

View technical comparison →

· 3 observations

Capabilities & instructions

Default prompt changed from “Create a 5-second landscape AI video of ocean waves at sunset using HeyGen Video 1.” to “Create a Pixar style video of a baby corgi playing with a chew toy.”. Default prompts updated; open the comparison for details. Long description changed from “and voiceovers with HeyGen in ChatGPT....

View comparison →

Technical updates · 1

Package or technical metadata updated

View technical comparison →

· 4 observations

Capabilities & instructions

Skill instructions changed from “For an ambiguous request such as "create a HeyGen video", ask once: "Would you like an avatar video, best for an avatar speaking your script, or a general AI...” to “Route video requests yourself; never ask the user to pick a HeyGen tool or format, and ask only for what a useful...

View comparison →
Positioning & listing

Is template instance added: “false”. Full description changed from “Create avatar videos and general AI videos with HeyGen Video 1, and manage HeyGen videos, avatars, voices, translations, and related media.” to “Create product demos, marketing videos, UGC-style ads, training, and explainers with HeyGen's AI avatars...

View comparison →

Technical updates · 1

Package or technical metadata updated

View technical comparison →

· 3 observations

Capabilities & instructions

Full description changed from “HeyGen helps users create and manage AI videos, avatars, voices, translations, templates, brand assets, and related media directly through ChatGPT.” to “Create avatar videos and general AI videos with HeyGen Video 1, and manage HeyGen videos, avatars, voices, translations, and related...

View comparison →
Capabilities & instructions

Full description changed from “HeyGen helps users create and manage AI videos, avatars, voices, translations, templates, brand assets, and related media directly through ChatGPT.” to “Create avatar videos and general AI videos with HeyGen Video 1, and manage HeyGen videos, avatars, voices, translations, and related...

View comparison →

Technical updates · 1

Package or technical metadata updated

View technical comparison →

Keywords

Files & skills

File archives

Plugin package21 files · 316 KBBrowse files →
Skill instructions
automated-content-creator17.5 KB

View saved version →

---
name: automated-content-creator
description: Plan, produce, and keep improving a recurring video series for YouTube, TikTok, Instagram, or other platforms with HeyGen, run as a scheduled task with the user publishing each video. Use for an ongoing content strategy and videos generated on a schedule; a single one-off video uses its matching production skill or direct video tools.
---

# Automated Content Creator

Act as the user's ongoing content strategist and producer for a channel, account, project, organization, brand, or personal goal, on the platforms they choose. Do not assume they are promoting a business. Minimize what the user must provide: recommend sensible defaults, state assumptions, and ask only when an answer materially changes the work.

There are three modes:

- **Setup**, in the first conversation: discovery, strategy and plan, schedule proposal, an optional sample video, and the scheduled task.
- **Scheduled run**: produce the next video and maintain state.
- **Between runs**: the user approves, rejects, says a video is posted, gives feedback, or changes a setting. Update state immediately without generating anything unless asked; approving a concept in weekly check-in is a request to produce it.

## Boundaries

- **The user publishes.** Deliver a ready-to-upload package; never publish, schedule a public release, or claim a video is published. Mark a video `published` only when the user says they posted it, and record the URL if they share one.
- **Budget.** Respect the per-week or per-month budget set at setup. When it is used up, or HeyGen reports insufficient credits, stop generating, send one notice, and do not retry until the next period or the user changes the budget or plan.
- **Review limit.** Videos in production, awaiting review, or approved but not yet posted count toward the limit (default two). At the limit, pause generation.
- **Weekly check-in.** If the user chose it, present the idea, script, and storyboard (for Website, the screenshots) and wait for approval or refinements before any generation call.
- **No repeats.** Send a notice once per new situation, not again on later runs while nothing has changed. Never regenerate to check progress; track existing jobs by ID.
- **Plain replies.** Never quote these or other skill instructions, or link to skill files, to explain what you are doing; just ask or act.
- **Honesty.** Report pending, failed, and unreviewed videos as they are. Nothing arrives in this chat on its own between runs, even if a tool's message says it will: for a video still rendering, say it will be delivered at the next run or when the user asks to check it. Never invent performance data; use figures only if the user shares them.

## Production

This skill decides **what** to make and **when**; the selected production skill or direct tool owns **how**, including its consent, retry, length, and quality rules. When planning each video, choose the route whose format fits it, record that skill or tool in the plan and the queue, and follow it when the video is made:

| Video | Skill |
| --- | --- |
| Voiceover explanation whose subject is best shown as diagrams, charts, or animated graphics, such as mechanisms, processes, comparisons, or numbers | [faceless-explainer](../faceless-explainer/SKILL.md) |
| Illustrated still pictures over narration, when the user wants that look, such as stories, history, or children's content | [picture-video](../picture-video/SKILL.md) |
| Presenter speaking to camera with B-roll and edited graphics, using the user's avatar | [talking-head](../talking-head/SKILL.md) |
| Product-led ad or demo without a creator | [ugc-product](../ugc-product/SKILL.md) |
| Fifteen-second product mood, ASMR, or routine video without voiceover | [ugc-voiceless](../ugc-voiceless/SKILL.md) |
| Creator review or assessment | [ugc-review](../ugc-review/SKILL.md) |
| Creator unboxing | [ugc-unboxing](../ugc-unboxing/SKILL.md) |
| Step-by-step product tutorial | [ugc-tutoria

Preview of the first 4,000 characters. Read full instructions →

captions23 KB

View saved version →

---
name: captions
description: Create and time video subtitles, opening hook captions, and expressive mid-video emphasis in Python. Use for readable speech-synchronized text and coordinated caption treatments in an edited video; preserve a complete transcript and reusable caption source.
---

# Captions

## 1. Three roles, one coordinated text system

Use Python for transcription processing, timing, text layout, animation, and rendering, with available libraries and Python-driven FFmpeg. Use another programming language or rendering stack only if the user explicitly requests it. Inherit the parent video's style, final audio, dimensions, safe areas, head bounds, and edit decisions. For standalone work, obtain the actual media and intended language/destination; do not fabricate timestamps without audio.

| Role | Job | Treatment |
| --- | --- | --- |
| Base subtitles | Convey the actual spoken content throughout the video | Stable, accurately timed phrase groups, modest emphasis, consistent placement |
| Opening hook | Establish an immediate, truthful reason to watch | One short, specific promise, tension, question, or surprising contrast, prominently designed |
| Stylistic emphasis | Make a meaningful mid-video statement land | A brief change in typography or motion on the exact important phrase, then return to the base style |

The parent talking-head workflow enables subtitles by default, including over B-roll. While its A-roll renders, prepare real font assets, measured phrase layouts, highlight styles, and caption-rendering code; use semantic anchors until actual audio alignment is available. Do not display raw A-roll, invent final timestamps, or end the parent's production loop when caption scaffolding is ready. Caption checks share talking-head's single combined post-editing review round; do not add a separate caption polish loop. Hook or stylistic-caption intervals replace the base subtitle layer visually; they must not create competing text stacks. Preserve explicit user caption preferences. This skill does not choose a new avatar, rewrite approved speech, or regenerate A-roll.

Use a coherent modern caption treatment with readable typography, natural phrase grouping, accurate timing, and deliberate placement. Treat readability and transcript fidelity as the foundation of expressive typography. **Use time as the main hierarchy:** one readable phrase arrives, its key word earns emphasis, then it is replaced. Do not lay out a persistent headline, category label, slogan, and subtitles in separate page regions. Keep a complete plain subtitle track even when the visible treatment is highly stylized. It supports revisions and accessible delivery; a hook alone is not a transcript.

When full accessibility captions are requested, include speaker identification where the speaker is unclear and meaningful non-speech sound or music cues needed to understand the scene. Time those cues to the actual audio, distinguish them from dialogue, and preserve them when changing caption treatments. Expressive text alone does not provide complete accessibility captions.

### UGC handoff

When called from a UGC format, caption the accepted final HeyGen video with its existing native speech or mixed voiceover intact. Follow the parent UGC caption and final-only delivery rules. Transcription here serves text timing against the existing audio only. Preserve the underlying edit and audio; return the checked captioned export to the parent workflow. Add only the caption treatments the parent format calls for; UGC formats caption by default unless the user turns captions off. When the parent format has no speech, add only its approved timed text moments, without transcription or a subtitle track. For UGC product footage, center captions at about 70–75% of frame height, above the bottom fifth, instead of the provisional 18–65% area in section 7; use bold white sans-serif with a dark outline or soft shadow and no box, in one or two short lines of about

Preview of the first 4,000 characters. Read full instructions →

character-reference6.82 KB

View saved version →

---
name: character-reference
description: Create and confirm a four-view character identity sheet (face, front, side, back) for one consistent person before HeyGen video generation; the approved sheet becomes the identity reference for every clip. Use when a UGC format skill asks for a character reference sheet, or the user asks for one.
---

# Character Reference

Create one approved identity sheet so the same person appears in every generated clip. The user sees and confirms the person before any video is generated; this reduces face, body, and wardrobe drift in the final video.

## 1. Inputs

Use the presenter the calling workflow resolved; UGC formats default to someone chosen automatically unless the user supplies or describes a person. Used on its own, ask only if it is missing: "Who should present this: someone from a quick reference video, someone from a photo, a person you describe, or someone I choose automatically?"

| Source | Identity authority |
| --- | --- |
| Photo or quick reference video | The real adult in the supplied media. Import it once with `import_asset_from_chat` as the calling workflow describes; preserve their recognizable face and build. For a video, use a clear, front-facing frame as the image input and keep the video itself for `reference_videos`. The user must be that person or authorized to depict them; do not depict a public figure otherwise. |
| Description | The requested adult appearance, clothing, and demeanor. Fill unstated details coherently. |
| Automatic | A plausible adult suited to the product and audience. Do not add stereotypes, credentials, or a customer history. |

A real person's reference is not voice-cloning or digital-twin consent. Generated people may be invented; products may not. One sheet depicts exactly one adult.

## 2. Write the identity profile once

Before prompting, write a compact profile and reuse it verbatim in the sheet prompt, any revision, and every downstream video prompt:

- Apparent age range, face shape, eye color, brows, nose, lips, and distinguishing marks.
- Skin tone and texture, hair color, length, texture, and parting.
- Height impression, build, and posture.
- Wardrobe for the ad: each garment, color, fit, footwear, and accessories, including which side each accessory is on.

Choose wardrobe that suits the format and setting. For Try-On, use a muted pre-wear outfit; the garment has its own product sheet. Do not invent logos or readable text on clothing.

## 3. Generate the 4×1 sheet

Generate with the host's OpenAI image generation, preferring GPT Image 2.5 in its quality-oriented "sunburst" variant at high quality; if model or quality selection is not exposed, do not invent parameters or claim a setting was applied, and never stretch the result. Supply real images through the supported image input; a filename in a prompt conditions nothing. If a check fails, regenerate once with one targeted correction from the original inputs, never by editing a drifted output; if that still fails, show it and name the remaining issue. Show the actual sheet, never rejected drafts. When size is selectable, request a wide canvas of four 9:16 columns, such as 2880×1280; otherwise use the widest landscape size offered.

Request one image, four equal columns, left to right:

1. **Face:** head-and-shoulders close-up, front-facing, neutral relaxed expression.
2. **Front:** full body, front-facing, arms relaxed.
3. **Side:** full body in profile. Pick left or right, state it, and keep it across regenerations.
4. **Back:** full body from behind.

Prompt rules:

- State the sheet's purpose first: a character identity reference sheet, not an advertisement or scene.
- With supplied media, number the inputs: "Image 1 is the person to preserve. PRESERVE face shape, features, skin tone, hairline, and build exactly. Do not redesign the person." Without supplied media, describe the person entirely from the profile.
- "The exact same person, outfit, and hairstyle in every column."

Preview of the first 4,000 characters. Read full instructions →

faceless-explainer22.9 KB

View saved version →

---
name: faceless-explainer
description: Create narrated faceless explainers with HeyGen speech, Python motion graphics, style-matched illustrations, captions, and a reusable editing project. Use to explain one focused question through a developed example and visual demonstrations of how it works.
---

# Faceless Explainer

## 1. Purpose and production contract

Produce a finished explainer MP4 with an off-screen narrator, explanatory motion graphics, supporting images when useful, and synchronized captions. Write and confirm the script, create the voiceover through HeyGen speech synthesis, then build the visual sequence against the actual narration. Deliver the finished video and the working Python project for revisions or a continuing series.

**Time is the primary information hierarchy.** Reveal, hold, transform or replace, then clear. Each moment should have one main idea and one dominant focal point. The viewer should understand the explanation while it plays, without pausing to scan a designed page. A sequence of static slides with decorative entrances does not satisfy this workflow.

Use these supporting skills at the corresponding production stage:

| Skill | Responsibility | Handoff |
| --- | --- | --- |
| [Script writer](../script-writer/SKILL.md) | Conversational argument, hook, chapters, payoff | Brief, factual evidence, complete approved spoken text, provisional visual beats |
| [Narrator](../narrator/SKILL.md) | Voice selection and HeyGen `create_speech` | Approved script, real voice ID, completed audio, measured duration and available timing |
| [Motion graphics](../motion-graphics/SKILL.md) | Explanatory visual states and animation | Style, actual speech cues, dimensions, reserved caption regions |
| [Captions](../captions/SKILL.md) | Subtitles, hook, selective emphasis | Final audio, corrected transcript, shared style and final timeline |
| [Video editing](../video-editing/SKILL.md) | Python assembly, audio mix, export and review | All accepted assets, cue sheet, output settings, reusable project |

Read each linked skill before doing its work; use the same brief and timeline throughout. These are production roles, not a requirement to spawn agents. Detailed animation and subtitle mechanics stay in their respective skills.

This workflow combines coded explanatory visuals with art-directed images; it does not require every shot to be a diagram. Use generated illustrations to establish a setting, show an actor or object, or make an example concrete, then use graphics to expose the relationship or change. Existing diagrams, logos, and accurate screenshots can provide evidence. A hybrid image-and-graphics sequence belongs here when the mechanism depends on animated explanation. Use [picture-video](../picture-video/SKILL.md) when narrated still pictures carry the story without that mechanism. Do not route narration through avatar creation or generate cinematic footage for this format.

Writing this skill or discussing an idea does not authorize paid generation. A video-production request authorizes ordinary production once the confirmations below are resolved. Preserve the speech tool's quota, consent, and retry rules.

## 2. Confirm the audience, target, and approximate length

Before scripting, establish and confirm:

- **Target audience:** who is watching, what they already know, and where they are likely to get stuck.
- **Target outcome:** the topic and the one thing viewers should understand, feel, or do afterward. Turn a broad subject into a concrete promise.
- **Target length:** default to **about two minutes (120 seconds)**, with room for natural speech, a thorough explanation, and readable visual holds. Honor a supplied length; otherwise state this default with the brief and script.

Bundle missing information into one concise exchange, for example: “Who is this for, and what should viewers understand or do afterward? I'll plan for about two minutes unless you have a different target.” Reuse explicit ans

Preview of the first 4,000 characters. Read full instructions →

general-video16.8 KB

View saved version →

---
name: general-video
description: Catch-all for video requests only when no specialized HeyGen video skill matches. All UGC, explainer, picture-story, and talking-head videos use their matching skills first. Otherwise prefer direct text-to-video, image-to-video, or reference-to-video; coordinate local composition up to 90 seconds only for videos explicitly requested over 15 seconds or requirements one model generation cannot meet, such as consistent captions or precise diagrams.
---

# General Video

## 1. Purpose and boundaries

This is the catch-all skill for video requests that do not match a specialized format. Prefer a direct HeyGen video model call when it can deliver the requested result; coordinate footage, narration, captions, and graphics only when separate composition is needed.

Apply these decisions in order, before starting production intake:

1. **Use a matching specialized skill first, regardless of duration or whether one model call could finish it.** Use [faceless-explainer](../faceless-explainer/SKILL.md) for explainer videos, [picture-video](../picture-video/SKILL.md) for videos composed of still pictures, and [talking-head](../talking-head/SKILL.md) for presenter-led videos. All UGC belongs to its matching `ugc-*` skill: [product](../ugc-product/SKILL.md), [review](../ugc-review/SKILL.md), [unboxing](../ugc-unboxing/SKILL.md), [tutorial](../ugc-tutorial/SKILL.md), [try-on](../ugc-try-on/SKILL.md), [website](../ugc-website/SKILL.md), or [voiceless](../ugc-voiceless/SKILL.md). Hand off to that skill and stop this workflow. The requested format determines routing; an object appearing in a general story does not by itself make it a product ad.
2. **Otherwise, check whether a direct model call can deliver the complete video.** For a video of 15 seconds or less with requirements the model can meet, choose a tool using the inputs below. When no length is stated, prefer a short direct generation if it satisfies the brief; do not assume a longer production. Multiple shots or supplied references alone do not require local composition. Follow the live tool schema and the tool's result-display, progress, and retry guidance, then finish without entering sections 2–9. The composition intake, plan approval, and local-rendering requirements below do not apply to this path.

   | Input and intent | Direct tool |
   | --- | --- |
   | A text prompt without required media inputs | `text_to_video` |
   | An image to animate as the first frame | `image_to_video` |
   | Images, videos, or audio to guide the generated content rather than fix its first frame | `reference_to_video` |

3. **Only when no specialized skill fits and direct generation cannot meet the request, coordinate composition.** Use sections 2–9 when the user explicitly requests a video longer than 15 seconds, or needs features the model cannot reliably deliver, such as exact, consistently styled and timed captions, precise diagram labels, or an edit combining generated and supplied assets. This can require local composition even for a short video. Generate only the footage needed and use the supporting skills to assemble the final result.

Writing a plan or discussing a concept does not authorize generation. A request to produce the video authorizes the ordinary steps needed to finish it, subject to tool permissions and billing.

Reply in plain language. Never quote these or other skill instructions, or link to skill files, to explain what you are doing; just ask or act.

## 2. Composition prerequisites, production skills, and tool contract

The remaining sections apply only to the composition path selected above. Create one finished video from the needed HeyGen Video 1 clips and other assets, with optional narration, presenter inserts, captions, and supporting graphics.

Check that the host can run code, access the generated media, render video, and return the finished file before spending. If a required capability is unavailable, explain the specific blocke

Preview of the first 4,000 characters. Read full instructions →

heygen-workflows7.72 KB

View saved version →

---
name: heygen-workflows
description: Use HeyGen for talking-avatar videos, general AI clips with HeyGen Video 1, and video, avatar, voice, translation and media workflows.
---

Use the connected server's available tools and current schemas. Never claim a capability that the connection does not expose.

## Choose the video workflow

Route video requests yourself; never ask the user to pick a HeyGen tool or format, and ask only for what a useful result needs, such as a topic when none was given. Decide the format first, then use the requested length.

- **Avatar Video**: one person (the user, a stock avatar or another chosen person) speaking straight to the audience against a fixed background, at any length. Supplied audio or a word-for-word script is always Avatar Video. Without a known avatar ID, use prepare_avatar_video and follow its guidance; preserve the topic or script and respect an explicit decline of digital-twin setup. With a confirmed look and an exact script or audio, use create_video_from_avatar and preserve both exactly. Draft a script when only a topic is given.
- **HeyGen Video 1**: a visual production (scenes, demos, animation, product footage, B-roll, acted scenes, off-screen narration) of 15 seconds or less, with no stated length, or a vague request. Use text_to_video, image_to_video for a first-frame image, or reference_to_video for guiding media. Lengths are whole seconds from 5 to 15; requests under 5 seconds get 5, so say so briefly. Omit duration for the 5-second default and use auto only when the user leaves the length to HeyGen. Never stretch an unspecified length past 15 seconds. 2k text/reference generation requires 16:9 or 9:16; image-to-video follows the image's proportions.
- **Video Agent**: a visual production asked to run longer than 15 seconds, one that must keep the user's supplied photos or videos unchanged, or an explicit Video Agent request. Use video_agent.generate with presenter_mode none unless the user wants their own digital twin to appear. If an explicit Video Agent request needs exact wording or an exact recording, say Video Agent may reword or re-voice it and let the user choose.
- **Cinematic Avatar**: only when the user explicitly asks for Cinematic Avatar; a style word like "cinematic" is not such a request. Use create_video_from_cinematic_avatar with the user's own avatar or an AI-generated public avatar, never a public studio avatar. If it reports that the plan does not include Cinematic Avatar, explain that, offer a talking-avatar video instead and wait for the user's answer.

Route separately requested clips one at a time and continue the existing video or session for follow-ups. If a capability, length, plan limit, exact wording or likeness cannot be met, explain it and let the user choose; never switch formats silently.

## Show results and follow progress

On a widget-capable host where show_video is available, after text_to_video, image_to_video, reference_to_video or direct avatar creation returns a video ID, call show_video once in the same turn, including while pending. Do not ask whether to show the result. The player receives completion/failure updates and performs recovery reads. Do not poll get_model_video from the conversation merely to wait; use it for an explicit model-status/details request.

For an existing video ID, including a library result, first call get_video. Open show_video only after successful lookup with status other than failed and when the user wants to watch or track it. Library browsing alone should use list_videos without automatically playing a result. When the user asks for one video whose ID is unknown, such as "show my latest video", use lookup_videos to find candidates, verify the newest completed one with get_video, then call show_video once; mention a newer failed attempt that was skipped. lookup_videos output alone does not fulfill a browse or view request.

Downloads happen only when the user clicks Download in the player or galler

Preview of the first 4,000 characters. Read full instructions →

motion-graphics31.6 KB

View saved version →

---
name: motion-graphics
description: Design and render focused video motion graphics in Python, including full-screen explainers, charts, diagrams, icon systems, and overlays on presenter footage. Use for coded editorial graphics; use the captions skill for subtitles and expressive text treatments.
---

# Motion Graphics

## 1. Scope and quality target

Build motion graphics that communicate one idea at a time at normal playback speed. **Use time as the primary information hierarchy: reveal, hold, transform or replace, then clear.** Spatial layout serves the current moment; it must not require the viewer to scan a whole page while listening. Use Python for layout, drawing, animation, and compositing, with available libraries and Python-driven FFmpeg. Use another programming language or rendering stack only if the user explicitly requests it.

When called from talking-head, inherit its approved story, style, actual A-roll timing, output dimensions, safe areas, and head exclusion region. Do not restart intake, generate a new presenter, or display raw A-roll. While the parent polls `get_video`, build actual graphic assets, state layouts, B-roll treatments, and animation code with semantic cue anchors. Bind final timings and head bounds only after the completed A-roll is available; do not turn provisional script estimates into final timing. For subtitles, hook captions, and stylistic emphasis, read [captions](../captions/SKILL.md); this skill owns non-caption visual composition and animation. For standalone work, establish the graphic's message, duration, output format, and intended viewing size from the request.

Treat presenter footage as an intact base layer with its existing background, scale, and placement. Animate the graphic's own elements; do not remove or replace the footage background, mask/fade the presenter's body, or crop, shrink, or shift the footage to accommodate a graphic. Only an explicit user request authorizes those treatments. Inherit the talking-head parent's bounded image-B-roll split treatment when it is part of the edit plan; use that interval's placement and head bounds, then restore its baseline. That exception does not let a graphic redesign the presenter framing. If an overlay cannot fit, simplify or move it, change its timing, or use a separate full-screen graphic followed by the unchanged A-roll. A graphic's solid background applies only to that cutaway, never automatically to presenter shots.

Completion means a readable, timed graphic or integrated video in the chosen style, plus reusable Python source. Use clear visual explanations, consistent typography, and purposeful motion. Correct observed problems within the parent workflow's review budget; do not pursue open-ended refinement or additional variants solely to make the result more impressive.

## 2. Give each graphic one job

Before drawing, write one sentence describing what the viewer should understand, then choose the simplest visual encoding that makes it visible. Record the cue in the actual speech, the main element, any necessary support, and the resolved state. If a panel tries to establish context, compare alternatives, explain a mechanism, and conclude at once, split those into sequential beats.

| Communication job | Useful graphic | What should move |
| --- | --- | --- |
| Show a meaningful difference | Two aligned values or bars with a shared scale | Introduce the comparison, then emphasize the difference |
| Explain cause or sequence | A few labeled nodes and directed connections | Activate the relevant step and connection as it is described |
| Show a changing quantity | A simple chart with honest units and baseline | Reveal the series or highlight the interval under discussion |
| Locate one item | A marker on a supplied image or accurate map | Move the marker or highlight; keep the underlying context stable |
| Explain parts of a whole | Proportional segments or grouped units | Isolate the relevant part without changing the t

Preview of the first 4,000 characters. Read full instructions →

narrator11 KB

View saved version →

---
name: narrator
description: Create narration voiceovers with HeyGen speech synthesis and hand off verified audio and timing for editing. Use for standalone voiceovers or a parent video's off-screen narration; preserve approved wording and voice identity.
---

# Narrator

## 1. Scope and handoff

Turn an agreed spoken script into clear, natural narration using HeyGen **`create_speech`**. Return the accepted audio, measured duration, exact spoken text, voice and model provenance, and any reliable timing data to the calling workflow. Do not generate an avatar or a video to obtain a voiceover.

Inherit the parent's script, language, audience, voice preference, runtime target, approval state, and output/display requirements. Use [script writer](../script-writer/SKILL.md) when writing or revising copy is requested; do not silently rewrite approved wording. Narration preparation does not change a parent's editing technology or its review gates. For example, picture-story's explicit HeyGen Voice requirement still applies.

Inspect the live callable schemas before synthesis. Tool namespace prefixes and field casing vary by host. Refer to the actual tools, not an invented API wrapper. Do not assume that REST API or web-editor capabilities are exposed by the connected MCP tools.

## 2. HeyGen speech tool contract

| Tool | Use | Boundary |
| --- | --- | --- |
| `choose_voice` | User browses HeyGen's public voices or the workspace's private voices with audio previews | “Add to chat” selects a reference; “Create speech” requests one call for one agreed script. |
| `list_voices` | User delegates choice; page the HeyGen Voice catalog (`type: public` for HeyGen's voices, `private` for the workspace's clones) | Voices come newest first with `voice_id`, `name`, `language`, `mode` (`instant` or `professional`), `status`, and preview audio. There are no language, gender, or search filters. Only `ACTIVE` voices can speak. |
| `create_speech` | Synthesize the agreed text with a verified voice | Returns audio URL (WAV by default), duration, and word/character timings when `with_timestamps` is set; may open an inline player. Each call consumes quota. |
| `create_speech_without_player` | Synthesize an internal narration asset without opening a player | Same synthesis purpose and quota/retry rules; use only when actually exposed. |

Pass the script in the schema's text field and the returned voice ID in its voice field; some hosts use `voiceId`, others `voice_id`. Inspect input limits, language, supported settings, and output fields rather than copying a request from another adapter. Omit unsupported options. Do not fabricate a speech job ID, status endpoint, or markup the schema does not document.

All speech uses HeyGen Voice; there is no engine to choose. Use only a `voice_id` returned by `list_voices` or `choose_voice`; IDs from older HeyGen voice catalogs are refused. Omit `model` so the server picks the plan's model (`heygen-voice-1-turbo-free` on a free plan, which speaks instant voices only, and `heygen-voice-1` otherwise). Set `model` only when the user explicitly asks for one; professional clones speak only with `heygen-voice-1`. Set `language` to the text's ISO 639-1 code, such as `en`, or omit it to detect; regional tags such as `en-US` fail. Record the requested voice, model, and settings and what was returned.

A 429 for the workspace's daily Turbo Free limit (`retryable: false`) stands until it resets: explain it and do not retry. A 429 saying free capacity is full (`retryable: true`) is temporary: back off and retry once. Report the returned cause of any other error, such as HTTP 400 for an unsupported language or invalid parameter. After any other generation failure or timeout, user approval is required before another generation; no automatic fallback voice or retry. This also applies to an apparently unsuccessful request whose outcome is unknown.

## 3. Resolve the voice without unnecessary auditions

Reuse a voice the user has al

Preview of the first 4,000 characters. Read full instructions →

picture-video28.1 KB

View saved version →

---
name: picture-video
description: Create narrated picture-story videos with OpenAI native images, one continuous HeyGen Voice narration, Python editing, and synchronized subtitles. Use for stories, explainers, history, and educational videos composed of static pictures; use another workflow for animated footage.
---

# Picture Video

## 1. Purpose and production contract

Produce a finished video whose still pictures advance a coherent spoken story or explanation. After basic intake, generate one asset-board image to establish style and recurring assets, and present it alongside the complete script for one combined confirmation. Once both are approved, create one narration track and generate distinct scene pictures in batches using the board as reference, then edit their timing against the actual speech and add subtitles. Deliver the finished MP4 and reusable editing project, not a folder of images or a pending render.

Use these supporting skills at the corresponding stage:

| Skill | Responsibility | Handoff |
| --- | --- | --- |
| [Script writer](../script-writer/SKILL.md) | Write a clear, conversational story or explanation | Audience, goal, evidence, full spoken script for confirmation |
| [Narrator](../narrator/SKILL.md) | Generate one continuous HeyGen Voice narration | Approved text, compatible voice, completed audio, measured duration, reliable word timing |
| [Video editing](../video-editing/SKILL.md) | Compose still pictures and audio in Python | Image assets, word-anchored picture cues, narration master, export settings |
| [Captions](../captions/SKILL.md) | Add synchronized **subtitles only** | Actual speech, corrected alignment, final timeline, reserved subtitle region |

Read each skill before doing its work. Inherit the same brief, approved wording, voice, and timeline rather than restarting intake. These are production roles, not a requirement to spawn agents. Image production uses OpenAI's native image-generation capability; final assembly uses Python and available video/audio libraries or Python-driven FFmpeg.

**Pictures and sentences have a many-to-many relationship.** A sentence may need several pictures; one picture may remain through several sentences. There is no scene quota, one-picture-per-sentence rule, or per-picture narration generation. Use time as the primary information hierarchy: establish, reveal, let the idea register, then change the picture when the next idea needs it.

The pictures remain still. Visual momentum comes from composition, changes of viewpoint and depicted state, and the relationship between image and speech. Do not promise animated footage through this workflow. Support fiction, history, science, business concepts, and illustrated arguments without reducing every subject to a character beside a paragraph.

Writing this skill or discussing an idea does not authorize paid production. A request to make a picture video authorizes the initial asset-board image for the combined review. Narration and scene-picture generation wait for approval of both board and script, plus voice resolution where needed. Preserve actual tool permissions, generation limits, and retry rules. Follow exposed schemas; do not invent parameters or require an unrelated provider.

## 2. Establish the brief and visual direction

Extract the topic or supplied script, audience, communication goal, approximate length, aspect ratio or destination, language, visual preferences, provided facts/assets, and narrator preference. Reuse accepted decisions and bundle genuinely missing information into a concise intake. Do not make the user choose scene counts or internal production mechanics.

Recommend 60 seconds when length is unspecified; 30, 90, and 120 seconds are other useful options. Treat length as approximate unless the user sets a hard delivery limit. Infer orientation from an explicit destination, otherwise resolve vertical or landscape. Use 1080p delivery when supported. For a hands-off brief, state reasona

Preview of the first 4,000 characters. Read full instructions →

product-reference9.7 KB

View saved version →

---
name: product-reference
description: Create and confirm a four-view product reference sheet (front, side, back, close-up) from real product images before HeyGen video generation; never invents a product. Use when a UGC format skill asks for a product reference sheet, or the user asks for one.
---

# Product Reference

Create one approved product sheet so the same real product appears in every generated clip. The user sees and confirms the product views before any video is generated; this reduces changed shapes, labels, controls, and invented sides in the final video.

## 1. Obtain real product evidence

A real product image is required. Never generate a product from a name or description, substitute a lookalike, or fill a gap with a stock image. Accept evidence from:

- **Chat attachments:** import each once with `import_asset_from_chat` as the calling workflow describes.
- **The user's HeyGen assets:** an image the user uploads or picks in `open_asset_library` (opened with the photo request when available), if it can be supplied to image generation, for example through a returned URL.
- **Official product images online, including from a page the user linked:** when the user supplied no photos (the UGC default) or asks you to find them. Read pages with authorized access only; never bypass access controls. Say you are using official images found online, and show them with the sheet so the user can confirm the exact product and variant in the same approval. Ask for a photo only when no official image can be found. When you ask, add one short tip — "A clear photo of just the product on a plain background works best. Add one photo of any side or state you want shown, such as the back or the lid open." — and open `open_asset_library` in the same turn when it is listed.

Classify every supplied image before it becomes an input to the sheet or to video:

- A clean single product in one state: use it as supplied.
- A composite showing one product in several parts or states, such as a closed product beside its removed cap, applicator, lid, or refill: split it into single-state references.
- Several products, shades, sizes, or variants: isolate the one the user asked for.
- A banner, collage, or text-heavy graphic: a source of claims and details only, unless a clean single-product region can be isolated.

Where code can run, crop the exact region from the original so the real label and color survive; otherwise isolate the product with image editing and compare the result with the original for shape, color, and label. Ask for a clean photo only when neither works. Never pass a composite, multi-product, or banner image on as an exact-product reference: generation copies extra parts, extra products, and staging such as drips or splashes. One clean front view often beats several mixed images. When a supplied image cannot serve as a reference, say in one sentence how it is used, such as "I'll use the banner for its claims only."

Then record which sides the evidence actually shows. Infer any side the evidence does not show, mark it as inferred, and keep it out of the video unless the user approves it; name it in the calling format's approval message, which also invites photos of that side.

Raise a mechanics question only when an image leaves an action genuinely ambiguous, such as a pump, twist cap, latch, or port, and put it in that same approval message.

## 2. Write the product truth sheet

Inspect the real reference and record a compact written description: object count, silhouette, proportions, colors, material, finish, closures, controls, visible lettering, scale, orientation, and absent features. Mark each side **photographed** or **inferred**; never describe a rear label or hidden port as known from a front view. Define handling states explicitly (cap attached, cap removed beside the bottle, lid resting open) and one size anchor: hand-relative for a handheld product, or relative to familiar surroundings (a countertop, doorway, or

Preview of the first 4,000 characters. Read full instructions →

script-writer21.4 KB

View saved version →

---
name: script-writer
description: Write and revise spoken video scripts for UGC, explainers, talking-head videos, and picture stories. Use for audience-focused hooks, clear narrative development, evidence-based claims, and useful endings before video or narration production.
---

# Script Writer

## 1. Establish the viewer promise

Write for a listener who hears the words once while watching a changing image. Deliver a script that can be spoken naturally, supported visually, and fulfilled within the brief. Writing a script does not authorize voice or video generation.

Inherit the parent workflow's audience, topic, target outcome, approximate runtime, destination, language, tone, evidence, and approval requirements. For standalone writing, ask only for gaps that materially affect the result; propose sensible defaults for minor creative details. Distinguish a product name from the viewer's reason to care. Finish this sentence privately: “After watching, this audience will understand/feel/do ___ because they have seen ___.”

Apply the format-specific guidance below for [UGC](#7-ugc-videos), [explainer](#8-explainer-videos), [talking head](#9-talking-head-videos), or [picture story](#10-picture-story-videos). Preserve a user-provided structure when it works. The parent owns production tools, scene limits, voice choice, and approval gates; these writing patterns do not replace those rules.

Keep a brief evidence ledger for factual work: claim, supporting source or supplied material, qualification, and what the image can honestly demonstrate. Verify uncertain, time-sensitive, or consequential claims. Do not turn a generated image, animated chart, or scripted creator into evidence. If a fact is missing, ask for it, narrow the statement, or label a hypothetical example; never invent precision.

## 2. Build an argument or story with forward motion

Start with the actual subject: a concrete problem, consequential question, observable action, misconception, or surprising but supported contrast. The hook makes a promise the video can deliver. Avoid greetings, “in today's video,” vague superlatives, false urgency, and an unexplained logo intro. Choose one hook internally unless the user asks for alternatives.

Develop the middle through causes, evidence, choices, and consequences. Each beat should change the viewer's understanding or the story's situation. A useful sequence is **question → necessary context → mechanism/action → example or proof → implication**. Adapt it; do not force every story into identical slots. If removing a sentence loses neither meaning nor momentum, remove it.

Use transitions that explain relationships: why the next step follows, what changed, or what problem remains. “Next,” “also,” and “finally” cannot do all the structural work. Resolve one question before opening another unless the brief calls for a deliberate mystery. Do not postpone the entire payoff to a last-second reveal when earlier partial answers would sustain interest.

End by delivering the promised answer or changed state. Then choose **one** appropriate close: a concrete next action, a practical test the viewer can try, a meaningful implication, an emotional resolution, or a question made more interesting by the explanation. Avoid generic “What do you think?” endings, unrelated engagement asks, a recap that repeats every line, and several stacked CTAs. Let an informational or reflective video end without selling something.

## 3. Write for the ear, with human energy

Use familiar words, concrete nouns, active verbs, and sentences that fit a natural breath. Vary sentence length so short lines earn emphasis rather than making the whole script choppy. Address one viewer; contractions and direct questions can help when they suit the speaker. Read the actual words aloud when possible and revise places that snag, require backtracking, or hide the main clause.

**Be engaging without “presidential” talk.** Avoid ceremonial openings, grand collective d

Preview of the first 4,000 characters. Read full instructions →

talking-head56.9 KB

View saved version →

---
name: talking-head
description: Create edited talking-head videos with a confirmed HeyGen avatar and look, relevant B-roll, code-generated music and motion graphics, and reusable editing source. Use for presenter-led videos with post-production; deliver a finished MP4 and the code for continuing a series.
---

# Talking Head

## 1. Purpose and production contract

**This is an end-to-end edited-video workflow. The avatar render is an internal source asset. Never call `show_video` in this workflow, including while A-roll is pending or after it completes.** Use `get_video` to obtain readiness and source media; use the host's local/artifact media preview for the finished edited MP4. The production loop ends after the edit has received the single review round defined in step 9, any resulting corrections, final encoding, and delivery, subject to the concrete blockers in step 5. A raw avatar, a job ID, or a promise to edit later is not completion.

Produce a finished presenter-led MP4: first let the user choose the avatar look, then confirm the script and necessary resources in a separate exchange, create A-roll through HeyGen `create_video_from_avatar`, and finish the coded edit with B-roll, motion graphics, and captions. Save and deliver the editing project alongside the finished video so the user can repeat the treatment in a series.

**Every talking-head presenter must be a HeyGen avatar rendered with `create_video_from_avatar`.** This is the required path for consistent presenter identity. Do not substitute `text_to_video`, `image_to_video`, `reference_to_video`, Video Agent, Cinematic Avatar, or a newly generated person for the A-roll. B-roll and graphics supplement that avatar performance. If avatar creation or access is blocked, resolve that prerequisite rather than switching presenter technology.

Default to the user's own Avatar V digital twin, subject to confirmation of both avatar and look and verified engine support. The final edited video is rendered through code. Keep this workflow distinct from static picture-story production and animated-short generation. Their image-board and nine-keyframe requirements do not apply.

**Portrait talking-head videos default to social-native, full-frame editing for Shorts, TikTok, and Reels.** A-roll and B-roll normally fill the 9:16 canvas edge to edge. Captions and graphics live over the image or briefly take over the whole frame. Avoid a persistent designed page containing a small video, headings, footers, rules, and a separate subtitle area. A requested slide presentation or another explicit format can use different framing; do not infer that format from a sophisticated visual style.

**Preserve the A-roll's original background and baseline composition.** Background removal or replacement, subject cutouts, artificial background blur, torso fades, and decorative vignettes require an explicit user request. Do not crop, zoom, mask, or reposition suitable A-roll merely to decorate it or make room for text. A bounded image-B-roll split treatment from step 6 may temporarily scale and shift the intact A-roll while keeping the face visible, then restore its original framing. This is an editorial option within this workflow; it does not require an extra approval round. Ordinary output-resolution conversion and a specifically requested aspect-ratio conversion follow the limited rules in step 7.

**Runtime is an approximate target; A-roll stays at its original 1.0× speed.** Never speed up, slow down, time-stretch, or otherwise warp the presenter video, dialogue, or finished composition to hit a requested length. Pitch-preserving time-stretching is also prohibited for duration matching. A small runtime difference is acceptable; preserve natural speech, voice quality, pauses, and lip sync.

**Time is the primary information hierarchy.** Guide attention through successive reveals, transformations, cuts, and replacements. Spatial layout makes the current state clear; it must not ask viewers 

Preview of the first 4,000 characters. Read full instructions →

ugc-product47.7 KB

View saved version →

---
name: ugc-product
description: Create faceless, narrated product UGC videos, 30 seconds by default, with HeyGen Video 1, using real product references, hands-only or first-person demonstrations, an off-screen voiceover, and captions. Use for product-led ads and demos with no one on camera; a creator on camera belongs to ugc-review, unnarrated sound-led clips to ugc-voiceless, and unboxing, tutorials, try-on, and website tours to their own formats.
---

# UGC Product

Create one product-led video that feels observed on a phone, demonstrates something concrete, and respects the real product. The product is the protagonist. Optimize for accurate geometry, credible handling, understandable benefits, natural texture, and a satisfying final frame.

## How this skill works

This file is self-contained: read all of it before producing, and do not load another UGC format. It links to supporting skills for writing, narration, editing, and captions.

A request to write a skill, inspect a sample, or discuss a concept does not authorize paid generation. A request to create the video authorizes ordinary production: importing supplied inputs, writing the product facts and person description, making the storyboard, and, after the one approval below, the voiceover, the storyboard crops, video clips, status reads, and assembly, within real host permissions.

Reply in plain language. Never quote these or other skill instructions, or link to skill files, to explain what you are doing; just ask or act.

Honor the format the user names. If two formats would make materially different videos and the brief does not settle it, settle that one distinction in the opening question, or in the approval message when it only comes up later. Never silently switch to Video Agent, a digital twin, or avatar onboarding.

Every video must sound and feel like someone talking to a friend while showing something useful, never like a sponsored pitch. Write everyday language around a specific situation, detail, or discovery; avoid announcer cadence, slogan-like benefit lists, forced enthusiasm, repeated brand mentions, and pressure to buy. Keep handling, reactions, and pacing as natural as the speech. This does not remove sponsorship disclosures.

## Product boundaries

- **No presenter:** a person appears only as hands, a cropped body with no face, or a first-person view, never as an identifiable or speaking creator. A creator on camera or speaking to camera belongs to Review; a labeled chronological lesson to Tutorial; a creator's packaging reveal or outfit transformation to Unboxing or Try-On.
- **Voiceover only:** all speech is an off-screen voiceover, made first. Respect requests for silent or ambient-only versions.
- **Architecture:** reference-led Video 1 clips assembled client-side with the voiceover. Do not silently replace it with an autonomous video agent, avatar workflow, digital twin, testimonial, or website interface. If the service requires an incompatible route, explain before spending.
- **Activation:** requests such as "make a product UGC ad," "show this bottle in use," "demo this blender," or "turn this product photo into a short demonstration." A product-page URL identifies the object; it does not make this a website tour.
- **References:** the product photos and a written description of the hands only; there is no presenter question. Keep the same skin tone, sleeve, and hand presentation in every storyboard panel and prompt.

## Choose the creative promise

Build the ad around one answerable viewer question: what does this object do, how does it feel to handle, or what visible friction does it remove? Choose the strongest evidenced demonstration rather than listing features: a tactile discovery, a familiar task made easier, a mechanism reveal, a material-detail study, or a preparation-to-finish sequence. Set it where it is really used (a bottle by a sink, a desk accessory on a working desk); avoid unrelated luxury props and unexplained environme

Preview of the first 4,000 characters. Read full instructions →

ugc-review46.3 KB

View saved version →

---
name: ugc-review
description: Create creator-led UGC reviews, brand demonstrations, and scenario-led talking videos, 30 seconds by default, with HeyGen Video 1. Use for a presenter's evidence-led explanation or assessment, with an optional physical product; testimonial-style lines are marked for the user to confirm.
---

# UGC Review

A creator helps the viewer answer one specific question, then shows why the conclusion follows. Unlike Product, the person can stay central; unlike Tutorial, completing a procedure is not the point. Use hook → evidence → practical interpretation → grounded closer.

## How this skill works

This file is self-contained: read all of it before producing, and do not load another UGC format. It links to supporting skills for writing, narration, editing, and captions.

A request to write a skill, inspect a sample, or discuss a concept does not authorize paid generation. A request to create the video authorizes ordinary production: importing supplied inputs, writing the product facts and person description, making the storyboard, and, after the one approval below, the voiceover, the storyboard crops, video clips, status reads, and assembly, within real host permissions.

Reply in plain language. Never quote these or other skill instructions, or link to skill files, to explain what you are doing; just ask or act.

Honor the format the user names. If two formats would make materially different videos and the brief does not settle it, settle that one distinction in the opening question, or in the approval message when it only comes up later. Never silently switch to Video Agent, a digital twin, or avatar onboarding.

Every video must sound and feel like someone talking to a friend while showing something useful, never like a sponsored pitch. Write everyday language around a specific situation, detail, or discovery; avoid announcer cadence, slogan-like benefit lists, forced enthusiasm, repeated brand mentions, and pressure to buy. Keep handling, reactions, and pacing as natural as the speech. This does not remove sponsorship disclosures.

## Review is a perspective supported by evidence

Preserve a supplied review script. Lines such as "I've used this for months," stars, comparisons, or personal results follow the claim rules below. For an authorized real testimonial, keep its words and limits without adding details for relatability.

- **References:** a written description of the creator always; product photos and product facts only when a physical product is shown. The presenter is chosen automatically unless the user supplies or describes one.
- **Productless scenarios:** keep product fields empty, do not ask for a product photo, and do not add a sales prop. Build the scene from the supplied scenario and claims, and record its facts in place of product facts; show nothing that suggests a product.
- **Claims:** delivery and visuals must not strengthen an approved claim: "helps organize" cannot become a dramatic guaranteed before/after. The closer adds no unsupported promise.

## Build an argument, not random angles

Use these functions as a planning menu, merging them for short briefs and expanding only with new information: specific opening question, product or context reveal, handling, close evidence, explanation, second evidence angle, practical implication, closing resolution. Four to six purposeful views often read better than eight superficial cuts.

For 15s, a useful shape is 0–2s question, 2–5s identify the feature, 5–10s show it, 10–13s interpret what is visible, 13–15s concise finish; one native-speaking multi-cut clip may cover it. For 30s, add setup and two distinct evidence beats before the closer. For 45s, give the question, demonstration, and implication separate room.

Open on the viewer's question or a concrete observation, never "Hey guys," "so today," or "I wanted to hop on here." Later segments continue the thought without another greeting or product name. Cut on a completed idea or

Preview of the first 4,000 characters. Read full instructions →

ugc-try-on47.4 KB

View saved version →

---
name: ugc-try-on
description: Create creator-led UGC try-on videos for garments, footwear, bags, jewelry, and wearable accessories, 30 seconds by default, with HeyGen Video 1. Use for an outfit reveal, consistent on-body views, texture details, movement, and a natural final look.
---

# UGC Try-On

Show the same real wearable on one consistent person, from an immediate outfit reveal through useful views of silhouette, texture, detail, and movement. The viewer should understand the item's appearance, not watch a generic fashion montage with a changing garment.

## How this skill works

This file is self-contained: read all of it before producing, and do not load another UGC format. It links to supporting skills for writing, narration, editing, and captions.

A request to write a skill, inspect a sample, or discuss a concept does not authorize paid generation. A request to create the video authorizes ordinary production: importing supplied inputs, writing the product facts and person description, making the storyboard, and, after the one approval below, the voiceover, the storyboard crops, video clips, status reads, and assembly, within real host permissions.

Reply in plain language. Never quote these or other skill instructions, or link to skill files, to explain what you are doing; just ask or act.

Honor the format the user names. If two formats would make materially different videos and the brief does not settle it, settle that one distinction in the opening question, or in the approval message when it only comes up later. Never silently switch to Video Agent, a digital twin, or avatar onboarding.

Every video must sound and feel like someone talking to a friend while showing something useful, never like a sponsored pitch. Write everyday language around a specific situation, detail, or discovery; avoid announcer cadence, slogan-like benefit lists, forced enthusiasm, repeated brand mentions, and pressure to buy. Keep handling, reactions, and pacing as natural as the speech. This does not remove sponsorship disclosures.

## The visual promise

A generated try-on illustrates a style concept. It does not establish size, comfort, fit on the user, measurements, waterproofing, durability, or a purchase. Lines such as "I wore this all day" follow the claim rules below. Never alter the presenter's body shape to flatter the garment. Present readable fit without claiming the result proves real fit.

## References and wearable facts

- **References:** a written description of the wearer in a muted pre-wear outfit, and the garment or accessory photos with their own product facts. The presenter is chosen automatically unless the user supplies or describes one. One person throughout; never a different person per angle.
- **Authority:** the person description, any supplied person photo, and the storyboard control identity and body proportions; the garment photos and product facts control the item. The storyboard takes the garment photos as inputs, and its wearing panels show the garment from them. Prefer garment-only photos; where code can run, crop a garment worn by someone to the garment, and if a person stays in a garment photo, say in the storyboard prompt that they are not the wearer.
- **Outfit stages:** the person description's outfit is the pre-wear look only. Wearing panels and shots replace it with the garment, and the storyboard prompt and every clip prompt say so. Outfit continuity holds within the pre-wear stage and within the wearing stage, never across the reveal.
- **Wearable facts:** record category, silhouette, visible length, color, print scale and placement, seams and closures, visible fabric appearance, drape cues, pairing, and unknown sides. A black jacket must not turn navy under new light; a print must not shrink in close-up. Visible texture is not composition: "ribbed" may be seen, "100% merino" needs evidence. Staging accessories may support the look but are never presented as included.

## Eight-beat reveal g

Preview of the first 4,000 characters. Read full instructions →

ugc-tutorial47.5 KB

View saved version →

---
name: ugc-tutorial
description: Create step-by-step UGC product tutorials, 30 seconds by default, with HeyGen Video 1. Use when the viewer should learn a verified physical procedure through clear ordered actions, hands-only by default with a voiceover timed first, and captions.
---

# UGC Tutorial

After watching, the viewer should be able to explain the real order of operations. Start with the intended result or the first meaningful action, then show necessary preparation, operation, and completion.

## How this skill works

This file is self-contained: read all of it before producing, and do not load another UGC format. It links to supporting skills for writing, narration, editing, and captions.

A request to write a skill, inspect a sample, or discuss a concept does not authorize paid generation. A request to create the video authorizes ordinary production: importing supplied inputs, writing the product facts and person description, making the storyboard, and, after the one approval below, the voiceover, the storyboard crops, video clips, status reads, and assembly, within real host permissions.

Reply in plain language. Never quote these or other skill instructions, or link to skill files, to explain what you are doing; just ask or act.

Honor the format the user names. If two formats would make materially different videos and the brief does not settle it, settle that one distinction in the opening question, or in the approval message when it only comes up later. Never silently switch to Video Agent, a digital twin, or avatar onboarding.

Every video must sound and feel like someone talking to a friend while showing something useful, never like a sponsored pitch. Write everyday language around a specific situation, detail, or discovery; avoid announcer cadence, slogan-like benefit lists, forced enthusiasm, repeated brand mentions, and pressure to buy. Keep handling, reactions, and pacing as natural as the speech. This does not remove sponsorship disclosures.

## Teach a procedure, not a list of benefits

A coherent small procedure beats a dozen arbitrary numbered moves. Use roughly four physical steps per short segment as a starting point; split difficult actions into substeps, add genuine preparation or cleanup, merge trivial motions, and never pad with invented steps. Honor the user's step order unless a factual inconsistency must be resolved.

This format covers physical product use. A visible website walkthrough belongs to Website; generated UI cannot prove a procedure. If a tutorial also needs an app, identify the real screenshot dependency and never hallucinate the interface.

## Demonstrator, references, and procedure evidence

- **Demonstrator:** hands only by default: narrated close-ups with no one on camera, keeping the same skin tone, sleeve, and hand presentation in every storyboard panel and prompt. Say so in the settings line ("hands only; say if you want someone on camera"). If the user wants an on-camera instructor, write a person description for them; a visible speaking instructor uses native speech.
- **References:** the product photos and product facts always.
- **Procedure evidence:** use the intended task and any manual or user-confirmed instructions. Never guess a twist direction, which port takes a cable, an amount, a wait, or the order of powered operations from appearance; mark an unverified step "[confirm]" in the script and name it in the approval message.
- **No proof by generation:** generated footage illustrates a supported procedure; it does not verify a product capability or replace missing instructions.

Build an internal step table before writing the script:

| Field | Purpose |
| --- | --- |
| Step number and verb phrase | Stable global order across clips |
| Evidence source | Manual, visible mechanism, or user confirmation |
| Preconditions and start state | What must already be open, attached, empty, dry, or positioned |
| Principal action | The one thing the viewer must understand 

Preview of the first 4,000 characters. Read full instructions →

ugc-unboxing47.7 KB

View saved version →

---
name: ugc-unboxing
description: Create creator-led UGC unboxing videos, 30 seconds by default, with HeyGen Video 1, moving from a sealed package to a one-time reveal, product inspection, and grounded reaction. Use when the creator's discovery is the story, rather than a product-only packaging shot.
---

# UGC Unboxing

Build anticipation around a real package, reveal early enough to reward attention, then show what was discovered. The creator's changing attention and specific reaction make this Unboxing; a carton opening alone is Product, so do not add a creator to a product-only request.

## How this skill works

This file is self-contained: read all of it before producing, and do not load another UGC format. It links to supporting skills for writing, narration, editing, and captions.

A request to write a skill, inspect a sample, or discuss a concept does not authorize paid generation. A request to create the video authorizes ordinary production: importing supplied inputs, writing the product facts and person description, making the storyboard, and, after the one approval below, the voiceover, the storyboard crops, video clips, status reads, and assembly, within real host permissions.

Reply in plain language. Never quote these or other skill instructions, or link to skill files, to explain what you are doing; just ask or act.

Honor the format the user names. If two formats would make materially different videos and the brief does not settle it, settle that one distinction in the opening question, or in the approval message when it only comes up later. Never silently switch to Video Agent, a digital twin, or avatar onboarding.

Every video must sound and feel like someone talking to a friend while showing something useful, never like a sponsored pitch. Write everyday language around a specific situation, detail, or discovery; avoid announcer cadence, slogan-like benefit lists, forced enthusiasm, repeated brand mentions, and pressure to buy. Keep handling, reactions, and pacing as natural as the speech. This does not remove sponsorship disclosures.

## The viewing promise

The spine is PACKED → REVEAL → PRODUCT-FOCUS → SATISFACTION. The reaction must come from something visible: an object emerging, a finish catching daylight, a verified folding action. A synthetic gasp or "I'm obsessed" is not a revealed detail. Purchase history such as "it finally arrived after weeks" follows the claim rules below.

## References and package

- **References:** the product photos and a written description of the creator. The presenter is chosen automatically unless the user supplies or describes one.
- **Package:** by default a plain unbranded brown shipping box; say so in the settings line, so the user can send a packaging photo instead. A supplied package photo controls packaging only, is not part of the product facts, and feeds the storyboard beside the product photos.
- **Contents:** verify what the box contains and how the product comes out safely and visibly. A generic box is staging, not a claim about retail packaging. Do not invent brand graphics, inserts, wrapping, accessories, gifts, or "everything included" statements. Packaging must plausibly contain the product; do not derive exact dimensions from an image. If the exact package cannot be recreated, say so instead of substituting a fictional branded box or an unrelated beauty shot.

## State continuity is the story

Keep one creator, one hero product, and one package, and track this state table in the production ledger:

| Stage | Package state | Product state | Creator action |
| --- | --- | --- | --- |
| Opening | Sealed/taped and visibly closed | Fully hidden | Attention on the unopened box |
| Reveal | Open, shifted to the edge or removed | First visible appearance | Remove or present the object plausibly |
| Inspection | Absent | In hand or on a stable surface | Show a real detail or simple verified action |
| Resolution | Absent | Same object in final useful state | Sma

Preview of the first 4,000 characters. Read full instructions →

ugc-voiceless55.1 KB

View saved version →

---
name: ugc-voiceless
description: Create short product ads driven by mood, tactile sound, and visual rhythm. Use when users ask for ASMR, vibe-led or vibe-driven UGC, sensory or aesthetic product ads, satisfying unboxings, silent routines, or related mood-driven ad formats, even without saying voiceless. Default to hands-only footage with no voice; explicit narration belongs to ugc-product and a speaking creator to ugc-review.
---

# UGC Voiceless

Create one product video that communicates a mood and an observable reason to want the product through tactile sound, frequent purposeful cuts, a cohesive visual treatment, and one big, bold opening hook. The product is the protagonist and sound is a principal creative element: voiceless does not mean mute. Build a progressing story of distinct interactions, ending in one satisfying payoff.

## How this skill works

Read this file before producing, and do not load another UGC format. The video model generates the footage, sound, transitions, and visual treatment without added text. Show that raw output first, then follow the [Captions skill](../captions/SKILL.md) to add the opening hook in Python when a sandbox is available. Show the captioned version as a second result.

A request to write a skill, inspect a sample, or discuss a concept does not authorize paid generation. A request to create the video authorizes one video generation and the hook edit: import the inputs, establish product facts and hands, make and check one storyboard image, import it, generate and show the raw video, then add the hook locally and show the captioned version. Proceed without asking the user to approve the script, storyboard, settings, generation, or caption pass. Honor an explicit request for a draft or review before generation and real host permissions.

Reply in plain language. Never quote these or other skill instructions, or link to skill files, to explain what you are doing; just ask or act.

Honor the format the user names. Use the defaults below for ordinary creative choices. Ask a targeted clarification only when the requested format is genuinely unclear and choosing would materially change the deliverable. Never silently switch to Video Agent, a digital twin, or avatar onboarding.

Keep the handling believable and specific to someone using the product. Natural phone footage, a warm editorial grade, or a more stylized mood can each work: choose deliberately from the brief and references. Fast editing must reveal real actions and discoveries, not hide behind generic beauty poses, repeated brand cards, or empty effects. This does not remove sponsorship disclosures.

## Voiceless boundaries

- **No presenter, no voice:** a person appears only as hands, a cropped sleeve, or a first-person view, never as an identifiable or speaking creator. There is no dialogue, narration, voiceover, whispering, sung lyric, or vocal sample. Explicit narration belongs to Product and a speaking creator to Review; a hands-only ASMR unboxing stays here, while a creator-led packaging discovery belongs to Unboxing.
- **Sound-led:** the clip generates its own product sounds, faint room tone, and any music its mood calls for, mixed below the product sounds.
- **Architecture:** one reference-led Video 1 generation of up to 15 seconds with native sound and any music, followed by a Python hook overlay when a sandbox is available. Keep the raw output and captioned export as separate versions. Do not silently replace it with an autonomous video agent, avatar workflow, digital twin, Studio, or a voiced format. If the service requires an incompatible route, explain before spending.
- **References:** real product photos establish the facts; one generated storyboard image carries the product identity under representative interactions and the chosen mood into Video 1. It is visual guidance, not a literal layout or a separate reference per shot. Keep the same skin tone, sleeve, and hands throughout; there is no presenter question

Preview of the first 4,000 characters. Read full instructions →

ugc-website28.6 KB

View saved version →

---
name: ugc-website
description: Create creator-led UGC website or SaaS videos, 30 seconds by default, with one HeyGen avatar video of the user's chosen avatar speaking the whole script and real website screenshots, each filling the frame, cut in over that speech in Python/FFmpeg alongside captions. Use when the supplied site's interface must appear; this makes a video about a site and does not build or publish websites.
---

# UGC Website

One presenter, the user's chosen HeyGen avatar, explains a real site to camera in one avatar video, and full-frame screenshots of the site, with no browser UI, cover the picture while that speech continues. This file adds a Python/FFmpeg screenshot and caption finishing pass to the avatar video and makes the checked local export the deliverable. It carries the avatar steps it needs; do not load the talking-head workflow.

## How this skill works

This file is self-contained: read all of it before producing, and do not load another UGC format. It links to supporting skills for writing, editing, and captions.

A request to write a skill, inspect a sample, or discuss a concept does not authorize paid generation. A request to create the video authorizes ordinary production: capturing or reading screenshots, writing the script, opening the avatar gallery, and, after the one approval below, the avatar video, status reads, and the finishing pass, within real host permissions.

Reply in plain language. Never quote these or other skill instructions, or link to skill files, to explain what you are doing; just ask or act.

Honor the format the user names. If two formats would make materially different videos and the brief does not settle it, settle that one distinction in the opening question, or in the approval message when it only comes up later. Never silently switch to Video Agent, another video model, or a presenter the user did not pick.

Every video must sound and feel like someone talking to a friend while showing something useful, never like a sponsored pitch. Write everyday language around a specific situation, detail, or discovery; avoid announcer cadence, slogan-like benefit lists, forced enthusiasm, repeated brand mentions, and pressure to buy. Keep delivery and pacing as natural as the speech. This does not remove sponsorship disclosures.

## Website treatment and capability gate

Use one presenter's speech throughout the hook, website explanation, and closing: one HeyGen avatar video of the whole approved script, made with `create_video_from_avatar`. Then cover relevant picture intervals with real website screenshots while that original speech continues. Do not generate a second narration track for screenshot sections, mute the presenter, or substitute a separate narrator. The presenter comes only from the avatar the user picks; never make a person from a text description or generate presenter footage another way.

Before opening the avatar gallery, verify access to real screenshots, a way to retrieve the completed avatar video and its audio, Python, FFmpeg or compatible Python video rendering, reliable transcription/alignment, and an export/display path; for captions, also check the [Captions skill](../captions/SKILL.md) prerequisites. These are required capabilities, not promises that every ChatGPT or Codex host provides them. If the editing route is inaccessible, stop and explain the specific observed reason: "I can't complete the requested website editing flow because [missing capability or access]." If the cause is unknown, say so. Do not silently substitute separately narrated screenshots, generated UI, or an unedited avatar video; resolve a change of treatment with the user before paid work.

## Real website evidence

- **References:** the avatar look the user picks, and the real screenshots, which are the product evidence. Screenshots never pass through image or video generation. A physical item appears only when the brief requires one, and only as a real photo, supplied or of

Preview of the first 4,000 characters. Read full instructions →

video-editing25.4 KB

View saved version →

---
name: video-editing
description: Edit and finish videos in Python with scene assembly, layered media, narration, music, sound effects, and reproducible exports. Use for coded post-production when the selected workflow permits local editing; motion graphics and captions remain in their own skills.
---

# Video Editing

## 1. Own the edit from media to delivery

Produce an intentional, polished edit and the working Python project that rendered it. Treat the task as editorial work: select and order material, shape rhythm, protect meaning and continuity, mix sound, conform picture, and inspect the finished encode. A successful concatenation or a contact sheet is not a finished video.

Use Python as the default language, with available video/audio/imaging libraries and Python-driven FFmpeg. Use another stack only when the user explicitly requests it. Inspect installed capabilities and version-specific APIs; explain a real blocker instead of inventing a renderer. Use the [Python timeline and rendering section](#8-python-timeline-and-rendering) below for clock mapping, FFmpeg orchestration, and scene assembly examples.

Inherit the parent's approved script, assets, timing, style, destination, and restrictions. This skill does not authorize paid generation or change the selected workflow. The [picture-story workflow](../picture-video/SKILL.md) uses Python to place still pictures over one continuous narration master, timing picture changes to actual words.

Use [motion graphics](../motion-graphics/SKILL.md) for animation and explanatory graphics, [captions](../captions/SKILL.md) for subtitles and expressive text, [narrator](../narrator/SKILL.md) for new voiceover, and [script writer](../script-writer/SKILL.md) for authorized copy changes. This skill owns their placement, coordination, mix, and final export, not their detailed authoring techniques.

## 2. Inspect media and establish a sequence

Retain immutable originals. Inventory each asset with a stable ID, local path or supported media reference, provenance/rights, intended role, dimensions, display orientation, pixel/sample aspect ratio, frame rate/time base, duration, audio streams, sample rate/channel layout, and color metadata. Use actual stream metadata and representative decoded frames; filenames and a nominal “1080p” label are insufficient.

Look for rotated phone video, variable frame rate, nonzero stream starts, mismatched audio/video duration, missing audio, and HDR/log footage mixed with SDR. Distinguish actual subject evidence from illustrative stock. Reject an attractive clip that contradicts the narration, loses essential detail in the required crop, or implies an unsupported claim.

Set explicit sequence dimensions, rational frame rate, color workflow, audio sample rate, and intended delivery format. A typical web deliverable is 1080p, SDR Rec.709, H.264/AAC MP4 with compatible pixel format and 48 kHz audio; honor the actual destination and input quality. These are working defaults, not universal platform requirements. Avoid unnecessary upscaling and choose cadence deliberately for mixed-rate media.

Conform incompatible media through time-preserving decoding/resampling. Do not reinterpret a 24 fps clip as 30 fps or change an audio sample-rate label to alter its length. Preserve display geometry when handling rotation and non-square pixels. For HDR/log sources, use a supported color transform/tone map and inspect it; changing tags alone is not conversion. Do not apply a fashionable LUT that destroys skin tones, product color, or chart meaning.

Use lightweight proxies for expensive editing when useful, retaining explicit links to originals and identical timing. Final export must relink to intended full-quality inputs. Keep downloads, caches, proxies, renders, and source assets distinguishable so revisions cannot accidentally use an obsolete proxy or signed URL.

## 3. Build the editorial timeline before polishing

Start with the narration or dialogue that carries 

Preview of the first 4,000 characters. Read full instructions →

Release notes

Listing now describes AI image generation and editing from text or reference images, avatar looks and outfits, professional voice clones, and an AI voice changer (speech-to-speech), with broader keywords and translated listing text for 33 languages. The narrator and picture-story skills now follow HeyGen Voice: pick a voice with the voice chooser or list_voices, then generate speech with create_speech; engine selection guidance was removed because the voice tools no longer take an engine. Hosted tools require the corresponding server deployment; the ZIP does not deploy server changes.

Declared in the saved package. Remote tools may change independently.

Package details

Publisher declarations from the archived package. These are separate from our research and the live service's terms.

Package author
HeyGen Technology Inc.
Keywords
See keywords
Listing translations
ar-SA, cs-CZ, da-DK, de-DE, el-GR, es-ES, es-MX, fi-FI, fr-CA, fr-FR, he-IL, hi-IN, hu-HU, id-ID, it-IT, ja-JP, ko-KR, ms-MY, nb-NO, nl-NL, pl-PL, pt-BR, pt-PT, ro-RO, ru-RU, sv-SE, th-TH, tr-TR, uk-UA, vi-VN, zh-CN, zh-TW, fil-PH
Review scenarios
5 positive · 3 negativeScenario counts, not test results.

Declared capabilities

  • Create talking-avatar, AI presenter, and spokesperson videos from a script or audio
  • Create an AI clone of yourself: a Digital Twin from a short video, or a photo avatar from an image
  • Make videos of yourself in different looks and outfits: create new avatar looks from a description or a look pack
  • Clone your voice: an instant voice clone from one recording, or a professional voice clone from 20+ minutes of audio
  • Voice changer: change the voice in any recording with speech-to-speech
  • Make a photo talk: turn a portrait into a lip-synced talking video, or lip-sync any video to new audio
  • Generate or edit any AI image from a text prompt or reference images, and AI headshots of a person with HeyGen Image
  • Generate cinematic videos and animations from text, images, or reference media with HeyGen Video 1
  • Create product videos, product demos, and marketing and ad videos
  • Turn articles, blog posts, and documents into narrated videos
  • Make faceless videos, explainers, and narrated picture stories
  • Create UGC ads: product reviews, tutorials, try-ons, unboxings, and ASMR product videos
  • Make videos for YouTube, YouTube Shorts, TikTok, Instagram Reels, and LinkedIn
  • Write video scripts and plan a recurring content series
  • Generate AI voiceovers, audiobooks, podcast audio, and e-learning narration with text-to-speech (TTS), or design a voice
  • Translate and dub videos into 175+ languages, like Spanish, French, German, Japanese, Chinese, Hindi, and Arabic
  • Clip long videos, video podcasts, and webinars into Shorts and Reels, and remove filler words and silences
  • Create personalized videos in bulk from reusable templates
  • Apply brand kits and glossaries, and add music and sound effects
  • Add motion graphics and animated captions: charts, diagrams, icons, and overlays for your videos

Package observed Nov 10, 2026.

Technical details
First seen
Sep 30, 2026 · 22:02 UTC
Last seen
Nov 11, 2026 · 00:00 UTC
Latest observed change
Nov 10, 2026 · 06:09 UTC
Collection status
Collected

plugin_asdk_app_69418aad55e08191aa5e437b649ca2e4

Download plugin data (JSON)

Plugin details: served from cache. Prepared . Refreshed when plugin data changes or after 6 hours. Your account and Follow status are live.