← Say It AgainCONTENT HISTORY
WHAT CHANGED
changed
changed
Update to Say It Again
Snapshot Nov 6, 2026 · 00:15 UTC · version 1.1.0
Collection source: downloaded plugin package.
Instructions updated for say-it-again
Full description — Now says: product, or a product video of the product alone, or a set of image ads of it. Read the product from its link, write 3 scripts to read first if the person...
Observed in instructions or declared skills. Runtime behavior has not been tested.
Save Say It Again and check future changes in Following.
Up to 3 plugins free · no card required.
All fields and original values.
Full description
Before
Nov 3, 2026 · 00:14 UTC
product. Read the product from its link, write 3 scripts to read first if the person wants them, say what the video costs in credits, make it, and follow it until it is ready. Use it when someone asks for a UGC video, a video ad or video...
After
Nov 6, 2026 · 00:15 UTC
product, or a product video of the product alone, or a set of image ads of it. Read the product from its link, write 3 scripts to read first if the person wants them, say what the video or the set costs in credits, make it, and follow it...
Skill instructions
Before
Nov 3, 2026 · 00:14 UTC
product. Read the product from its link, write 3 scripts to read first if the person wants them, say what the video costs in credits, make it, and follow it until it is ready. Use it when someone asks for a UGC video, a video ad or video...
After
Nov 6, 2026 · 00:15 UTC
product, or a product video of the product alone, or a set of image ads of it. Read the product from its link, write 3 scripts to read first if the person wants them, say what the video or the set costs in credits, make it, and follow it...
Compare saved observations
Download comparison JSONSKILL.md text changes
− removed · + added
--- before +++ after @@ -1,11 +1,11 @@ --- name: say-it-again -description: Make an AI UGC video of a product with the Say It Again tools, where a generated presenter films themselves with the product. Read the product from its link, write 3 scripts to read first if the person wants them, say what the video costs in credits, make it, and follow it until it is ready. Use it when someone asks for a UGC video, a video ad or video scripts for a product they sell, asks what such a video costs, or asks about their Say It Again videos, presenters or credits. +description: Make an AI UGC video of a product with the Say It Again tools, where a generated presenter films themselves with the product, or a product video of the product alone, or a set of image ads of it. Read the product from its link, write 3 scripts to read first if the person wants them, say what the video or the set costs in credits, make it, and follow it until it is ready. Use it when someone asks for a UGC video, a product video, a video ad, video scripts or image ads for a product they sell, asks what such a video costs, or asks about their Say It Again videos, presenters or credits. --- # Making a Say It Again video -Say It Again makes AI UGC videos of a store's products: a generated presenter films themselves with the product. A video is made in steps: read_product with the product's link, which also lists the angles a video of it can argue; then optionally write_scripts and get_scripts to read three scripts first; then quote_video for the price; then make_video, then get_video until its status is ready or failed. A video can be built like an ad the store holds, which list_ads lists, and said by a presenter of the team's own, drawn with describe_presenter, shown with get_described and kept with keep_presenter, whose voice set_presenter_voice says when an Arabic video asks for it. A ready video lists in after_steps what can be done with it next and what each costs: change_video, make_longer, another_language and other_sizes. make_video, change_video, make_longer and another_language spend the team's credits, at the price quote_video or after_steps gives, refunded if the video fails. Every other tool is free. In ChatGPT, Say It Again makes no script and no video for these kinds of product, promotional or not, and a tool asked for one refuses it: adult and sexual products and services, among them sex toys; real-money gambling; marijuana, THC and psilocybin products, illegal drugs, and CBD products whose THC is over the legal limit or not stated; drug paraphernalia; prescription and age-restricted medicines; counterfeit, replica, stolen or contraband goods, fraud tools and pirated software; malware, spyware and covert surveillance devices; tobacco and nicotine products, among them vapes and e-liquids; weapons, among them firearms, ammunition, explosives, fireworks and self-defense weapons, and extremist merchandise; and fraudulent or high-risk financial, identity, document and travel services. The pictures of the team's products and of the presenters these tools list are the ones Say It Again's display shows with the answers of read_product, list_presenters, get_video and list_videos; a picture from another source shows another product or another person. Those answers are given in words, with what matters in each and the next step, and cards or images of what the display shows would only repeat it, unless the person asks for a list or a table. +Say It Again makes AI UGC videos of a store's products: a generated presenter films themselves with the product. A video is made in steps: read_product with the product's link, which also lists the angles a video of it can argue; then optionally write_scripts and get_scripts to read three scripts first; then quote_video for the price; then make_video, then get_video until its status is ready or failed. A video can be built like an ad the store holds, which list_ads lists, and said by a presenter of the team's own, drawn with describe_presenter, shown with get_described and kept with keep_presenter, whose voice set_presenter_voice says when an Arabic video asks for it. A ready video lists in after_steps what can be done with it next and what each costs: change_video, make_longer, another_language and other_sizes. Say It Again also makes product videos, the product alone on camera with a voiceover or music and no presenter: quote_product_video for the price, then make_product_video, then get_product_video until its status is ready or failed, a ready one listing in after_steps make_in_best, another_language and other_sizes; and image ads of a product, each a picture drawn whole with its own words: quote_image_ads for the price of a set, then make_image_ads, then get_image_ads until its status is ready or failed. make_video, change_video, make_longer, another_language, make_in_best, make_product_video and make_image_ads spend the team's credits, at the price quote_video, after_steps, quote_product_video or quote_image_ads gives, refunded if the video or the set fails. Every other tool is free. In ChatGPT, Say It Again makes no script, no video and no image ad for these kinds of product, promotional or not, and a tool asked for one refuses it: adult and sexual products and services, among them sex toys; real-money gambling; marijuana, THC and psilocybin products, illegal drugs, and CBD products whose THC is over the legal limit or not stated; drug paraphernalia; prescription and age-restricted medicines; counterfeit, replica, stolen or contraband goods, fraud tools and pirated software; malware, spyware and covert surveillance devices; tobacco and nicotine products, among them vapes and e-liquids; weapons, among them firearms, ammunition, explosives, fireworks and self-defense weapons, and extremist merchandise; and fraudulent or high-risk financial, identity, document and travel services. The pictures of the team's products and of the presenters these tools list are the ones Say It Again's display shows with the answers of read_product, list_presenters, get_video and list_videos; a picture from another source shows another product or another person. Those answers are given in words, with what matters in each and the next step, and cards or images of what the display shows would only repeat it, unless the person asks for a list or a table. ## What the tools take @@ -31,7 +31,7 @@ - get_balance: The team's credits, its plan, and how many write_scripts calls it has left (scripts_left). Free. - read_product: Read a product's page from its link: its name, price, description, benefits, photos and the angles a video of it can argue, and an id to use in the other tools. Free, and counted against the team's product reads. Say It Again's display shows the person what this answer names, with its pictures, the only pictures of the product and of the presenters it names; a picture from another source shows another product or another person. The answer is given in words, with what matters in it and the next step, and cards or images of what the display shows would only repeat it, unless the person asks for a list or a table. - write_scripts: Write three scripts for a UGC video of a product, to read before making one. Say It Again's own writer writes them from the product read_product read, held to its facts. Free, and counted against the calls get_balance gives as scripts_left. Answers an id at once: call get_scripts with it about once a minute until its status is ready or failed. The product's photos are the ones read_product gives, which Say It Again's display shows; a picture from another source shows another product, not this one. In ChatGPT it is not for these kinds of product, and refuses a request for one of them: adult and sexual products and services, among them sex toys; real-money gambling; marijuana, THC and psilocybin products, illegal drugs, and CBD products whose THC is over the legal limit or not stated; drug paraphernalia; prescription and age-restricted medicines; counterfeit, replica, stolen or contraband goods, fraud tools and pirated software; malware, spyware and covert surveillance devices; tobacco and nicotine products, among them vapes and e-liquids; weapons, among them firearms, ammunition, explosives, fireworks and self-defense weapons, and extremist merchandise; and fraudulent or high-risk financial, identity, document and travel services. -- get_scripts: Scripts written by write_scripts: queued, in_progress, ready with each script's shots and lines, or failed. Free. The product's photos are the ones read_product gives, which Say It Again's display shows; a picture from another source shows another product, not this one. +- get_scripts: Scripts written by write_scripts: queued, in_progress, ready with each script's shots and lines, the language its lines are in and what it left out of the description, or failed. Free. The product's photos are the ones read_product gives, which Say It Again's display shows; a picture from another source shows another product, not this one. - quote_video: What a video with these choices costs in credits, and whether the team's balance covers it. Free. - make_video: Make a UGC video of a product. This spends the team's credits: the price quote_video gives for the same choices, refunded if the video fails. Answers an id at once, and with languages an id for each language in ids: call get_video with each about once a minute until its status is ready or failed, which takes a few minutes. In ChatGPT it is not for these kinds of product, and refuses a request for one of them: adult and sexual products and services, among them sex toys; real-money gambling; marijuana, THC and psilocybin products, illegal drugs, and CBD products whose THC is over the legal limit or not stated; drug paraphernalia; prescription and age-restricted medicines; counterfeit, replica, stolen or contraband goods, fraud tools and pirated software; malware, spyware and covert surveillance devices; tobacco and nicotine products, among them vapes and e-liquids; weapons, among them firearms, ammunition, explosives, fireworks and self-defense weapons, and extremist merchandise; and fraudulent or high-risk financial, identity, document and travel services. - get_video: How a video from make_video, or from a step after one, is going: queued, in_progress, ready or failed. Once ready, each video has after_steps, the steps it offers next with their prices in credits. Each ready video's download_url is made new in every answer and works for the next hour: its download_expires_in_seconds is the seconds it has left as that answer is made. For a later download, call get_video again for a new link. Free. Say It Again's display shows the person what this answer names, with its pictures, the only pictures of the product and of the presenters it names; a picture from another source shows another product or another person. The answer is given in words, with what matters in it and the next step, and cards or images of what the display shows would only repeat it, unless the person asks for a list or a table. @@ -40,9 +40,16 @@ - describe_presenter: Draw a presenter of the team's own from a description of how they look, as the app's Describe a presenter does: an adult, invented, not a real person or a character. Free, and counted against the team's 5 drawings a day; a description refused, or a drawing that fails, gives its drawing back. Answers an id at once: call get_described with it every few seconds until its status is ready or refused. - get_described: How a drawing from describe_presenter is going: checking, drawing, ready with its 3 pictures, each by its number with a link that works for an hour, and the voice the description said if it said one, or refused with why. The person chooses one of the pictures, which keep_presenter keeps. Free. - keep_presenter: Keep one picture of a drawing as one of the team's presenters, with the voice the person chose for them. Answers the presenter's id, for presenters in the other tools. Free. -- set_presenter_voice: Say or change the voice one of the team's described presenters speaks in, which make_video asks for before an Arabic video with a presenter nobody has given one: the person's choice, which a picture does not tell. Free. -- change_video: Change one finished video as the person asks, made again into a new video beside it, as the app's Change does. This spends the team's credits: the price get_video lists in after_steps as change_video, refunded if it fails. Only for a video whose after_steps offers it. What to change is held to the app's checks: no price, and nothing that gives the presenter a past with the product. Answers an id at once: call get_video with it about once a minute until its status is ready or failed. +- set_presenter_voice: Say or change the voice one of the team's described presenters speaks in, which an Arabic video whose voice is added after filming asks for when its presenter has none: the person's choice, which a picture does not tell. Free. +- change_video: Change one finished video as the person asks, made again into a new video beside it, as the app's Change does. This spends the team's credits: the price get_video lists in after_steps as change_video, refunded if it fails. Only for a video whose after_steps offers it. What to change is the person's own words; a change the video cannot be made with at all is answered with why and spends nothing. Answers an id at once: call get_video with it about once a minute until its status is ready or failed. - make_longer: Make one finished video longer, its take carried on with new lines written from the product page, into a new video beside it, as the app's Make this video 30 seconds does. This spends the team's credits: the price get_video lists in after_steps as make_longer, refunded if it fails. Only for a video whose after_steps offers it. Answers an id at once: call get_video with it about once a minute until its status is ready or failed. -- another_language: Make one finished video again in another language, its own script and presenter, into a new video beside it, as the app's Another language does. This spends the team's credits: the price get_video lists in after_steps as another_language, or its voiced price for a voiced language, refunded if it fails. Only in a language that after_steps lists for it. Answers an id at once: call get_video with it about once a minute until its status is ready or failed. -- other_sizes: Lay one finished video out in another size, the same video cut for that frame, as the app's Other sizes does. Free. Only for a video whose after_steps lists other_sizes, in a size it lists. Answers an id at once: call get_video with it every few seconds until its status is ready or failed. The same size asked again answers the one already made or being made. -- list_ads: The Meta Ad Library ads the team's store already holds, to build a video like one with ad: its Competitors, the Winning ads of its kind and the library links it pasted, each with its id, advertiser, title, days running and whether it is a video, which ad needs. Free, and nothing is looked up. +- another_language: Make one finished video again in another language, into a new video beside it, as the app's Another language does: a UGC video with its own script and presenter, a product video with its voiceover said again over the same picture. This spends the team's credits: the price get_video or get_product_video lists in after_steps as another_language, or its voiced price for a voiced language, refunded if it fails. Only in a language that after_steps lists for it. Answers an id at once: call get_video with it, or get_product_video for a product video's, about once a minute until its status is ready or failed. +- other_sizes: Lay one finished video out in another size, the same video cut for that frame, as the app's Other sizes does. Free. Only for a video whose after_steps lists other_sizes, in a size it lists. Answers an id at once: call get_video with it, or get_product_video for a product video's, every few seconds until its status is ready or failed. The same size asked again answers the one already made or being made. +- list_ads: The ads the team's store already holds, from the Meta Ad Library and TikTok's, to build a video like one with ad: its Competitors, the Winning ads of its kind and the Meta Ad Library links it pasted, each with its id, library, advertiser, title, days running and whether it is a video, which ad needs. Free, and nothing is looked up. +- quote_product_video: What a product video with these choices costs in credits, and whether the team's balance covers it. Free. +- make_product_video: Make a product video, as the app's Product video does: the product alone on camera, doing what it does, with a voiceover, a voiceover over music or music alone, and no presenter, written from the product's page and the description. This spends the team's credits: the price quote_product_video gives for the same choices, refunded if the video fails. Answers an id at once: call get_product_video with it about once a minute until its status is ready or failed, which takes a few minutes. In ChatGPT it is not for these kinds of product, and refuses a request for one of them: adult and sexual products and services, among them sex toys; real-money gambling; marijuana, THC and psilocybin products, illegal drugs, and CBD products whose THC is over the legal limit or not stated; drug paraphernalia; prescription and age-restricted medicines; counterfeit, replica, stolen or contraband goods, fraud tools and pirated software; malware, spyware and covert surveillance devices; tobacco and nicotine products, among them vapes and e-liquids; weapons, among them firearms, ammunition, explosives, fireworks and self-defense weapons, and extremist merchandise; and fraudulent or high-risk financial, identity, document and travel services. +- get_product_video: How a product video from make_product_video, or from a step after one, is going: queued, in_progress, ready or failed, with why and whether its credits were refunded. Once ready, it has after_steps, the steps it offers next with their prices in credits. Each ready video's download_url is made new in every answer and works for the next hour: its download_expires_in_seconds is the seconds it has left as that answer is made. For a later download, call get_product_video again for a new link. Free. +- make_in_best: Make one finished product video made in fast again in best, its own script, photos and choices, into a new product video beside it, as the app's Make this video in Best does. This spends the team's credits: the price get_product_video lists in after_steps as make_in_best, refunded if it fails. Only for a video whose after_steps offers it. Answers an id at once: call get_product_video with it about once a minute until its status is ready or failed. +- quote_image_ads: What a set of image ads costs in credits, and whether the team's balance covers it. Free. +- make_image_ads: Make a set of image ads of a product, as the app's Image ads does: each ad a picture of the product drawn whole, with its own headline, second line and button, made from the product's page and the description. This spends the team's credits: the price quote_image_ads gives for the same count, refunded if the set fails. Answers an id at once: call get_image_ads with it about once a minute until its status is ready or failed. In ChatGPT it is not for these kinds of product, and refuses a request for one of them: adult and sexual products and services, among them sex toys; real-money gambling; marijuana, THC and psilocybin products, illegal drugs, and CBD products whose THC is over the legal limit or not stated; drug paraphernalia; prescription and age-restricted medicines; counterfeit, replica, stolen or contraband goods, fraud tools and pirated software; malware, spyware and covert surveillance devices; tobacco and nicotine products, among them vapes and e-liquids; weapons, among them firearms, ammunition, explosives, fireworks and self-defense weapons, and extremist merchandise; and fraudulent or high-risk financial, identity, document and travel services. +- get_image_ads: How a set from make_image_ads is going: queued, in_progress, ready with each image ad's headline, second line and button, in headline, subhead and cta, and its download_url, or failed with why and whether its credits were refunded. Each image ad's download_url is made new in every answer and works for the next hour: its download_expires_in_seconds is the seconds it has left as that answer is made. For a later download, call get_image_ads again for a new link. Free.
Full technical diff · 2 changed fields
changed /description
BEFORE
"Make an AI UGC video of a product with the Say It Again tools, where a generated presenter films themselves with the product. Read the product from its link, write 3 scripts to read first if the person wants them, say what the video costs in credits, make it, and follow it until it is ready. Use it when someone asks for a UGC video, a video ad or video scripts for a product they sell, asks what such a video costs, or asks about their Say It Again videos, presenters or credits."
AFTER
"Make an AI UGC video of a product with the Say It Again tools, where a generated presenter films themselves with the product, or a product video of the product alone, or a set of image ads of it. Read the product from its link, write 3 scripts to read first if the person wants them, say what the video or the set costs in credits, make it, and follow it until it is ready. Use it when someone asks for a UGC video, a product video, a video ad, video scripts or image ads for a product they sell, asks what such a video costs, or asks about their Say It Again videos, presenters or credits."
changed /skill_md_contents
BEFORE
"---\nname: say-it-again\ndescription: Make an AI UGC video of a product with the Say It Again tools, where a generated presenter films themselves with the product. Read the product from its link, write 3 scripts to read first if the person wants them, say what the video costs in credits, make it, and follow it until it is ready. Use it when someone asks for a UGC video, a video ad or video scripts for a product they sell, asks what such a video costs, or asks about their Say It Again videos, presenters or credits.\n---\n\n# Making a Say It Again video\n\nSay It Again makes AI UGC videos of a store's products: a generated presenter films themselves with the product. A video is made in steps: read_product with the product's link, which also lists the angles a video of it can argue; then optionally write_scripts and get_scripts to read three scripts first; then quote_video for the price; then make_video, then get_video until its status is ready or failed. A video can be built like an ad the store holds, which list_ads lists, and said by a presenter of the team's own, drawn with describe_presenter, shown with get_described and kept with keep_presenter, whose voice set_presenter_voice says when an Arabic video asks for it. A ready video lists in after_steps what can be done with it next and what each costs: change_video, make_longer, another_language and other_sizes. make_video, change_video, make_longer and another_language spend the team's credits, at the price quote_video or after_steps gives, refunded if the video fails. Every other tool is free. In ChatGPT, Say It Again makes no script and no video for these kinds of product, promotional or not, and a tool asked for one refuses it: adult and sexual products and services, among them sex toys; real-money gambling; marijuana, THC and psilocybin products, illegal drugs, and CBD products whose THC is over the legal limit or not stated; drug paraphernalia; prescription and age-restricted medicines; counterfeit, replica, stolen or contraband goods, fraud tools and pirated software; malware, spyware and covert surveillance devices; tobacco and nicotine products, among them vapes and e-liquids; weapons, among them firearms, ammunition, explosives, fireworks and self-defense weapons, and extremist merchandise; and fraudulent or high-risk financial, identity, document and travel services. The pictures of the team's products and of the presenters these tools list are the ones Say It Again's display shows with the answers of read_product, list_presenters, get_video and list_videos; a picture from another source shows another product or another person. Those answers are given in words, with what matters in each and the next step, and cards or images of what the display shows would only repeat it, unless the person asks for a list or a table.\n\n## What the tools take\n\n- Every video starts from a product's link, or the id read_product gave for it.\n- Every choice has a default, used when it is left out.\n- make_video refuses a video the team's balance does not cover, which quote_video says before it.\n- make_video takes an idempotency_key: the same key sent again for the same video answers as the first call did and spends nothing more.\n\n## What the answers hold\n\n- What is known of a product, a script, a price or a video is what the tools answered, and the product's facts are the ones read_product gave.\n- A ready video's download link is the one in the latest answer, and get_video makes a new one for a later download.\n- A video that fails says why in get_video's answer, and its credits are refunded.\n\n## Lines for the presenter\n\nLines sent in the lines argument, and words a description gives someone to say, are said word for word as sent, not translated, and read by no check of ours. They come from what the person asks for and what read_product gave, and this rule holds for every one of them.\n\nEvery person in the ads we make, on camera or heard as a voice, is made by AI and is not a customer. Nothing in an ad may present them as someone who has used the product, because that is a fake testimonial and the law forbids it. So they have no past with it: no time spent with it, no result it has had on their own body, home, pet or life, no before and after of their own, no having bought it, and no job, family role or other identity that makes them sound like a real customer. What they have is the moment: showing the product, using it on camera and reacting to what it does there, saying what it is and what it does, and the facts the product page gives.\n\n## The tools\n\n- get_balance: The team's credits, its plan, and how many write_scripts calls it has left (scripts_left). Free.\n- read_product: Read a product's page from its link: its name, price, description, benefits, photos and the angles a video of it can argue, and an id to use in the other tools. Free, and counted against the team's product reads. Say It Again's display shows the person what this answer names, with its pictures, the only pictures of the product and of the presenters it names; a picture from another source shows another product or another person. The answer is given in words, with what matters in it and the next step, and cards or images of what the display shows would only repeat it, unless the person asks for a list or a table.\n- write_scripts: Write three scripts for a UGC video of a product, to read before making one. Say It Again's own writer writes them from the product read_product read, held to its facts. Free, and counted against the calls get_balance gives as scripts_left. Answers an id at once: call get_scripts with it about once a minute until its status is ready or failed. The product's photos are the ones read_product gives, which Say It Again's display shows; a picture from another source shows another product, not this one. In ChatGPT it is not for these kinds of product, and refuses a request for one of them: adult and sexual products and services, among them sex toys; real-money gambling; marijuana, THC and psilocybin products, illegal drugs, and CBD products whose THC is over the legal limit or not stated; drug paraphernalia; prescription and age-restricted medicines; counterfeit, replica, stolen or contraband goods, fraud tools and pirated software; malware, spyware and covert surveillance devices; tobacco and nicotine products, among them vapes and e-liquids; weapons, among them firearms, ammunition, explosives, fireworks and self-defense weapons, and extremist merchandise; and fraudulent or high-risk financial, identity, document and travel services.\n- get_scripts: Scripts written by write_scripts: queued, in_progress, ready with each script's shots and lines, or failed. Free. The product's photos are the ones read_product gives, which Say It Again's display shows; a picture from another source shows another product, not this one.\n- quote_video: What a video with these choices costs in credits, and whether the team's balance covers it. Free.\n- make_video: Make a UGC video of a product. This spends the team's credits: the price quote_video gives for the same choices, refunded if the video fails. Answers an id at once, and with languages an id for each language in ids: call get_video with each about once a minute until its status is ready or failed, which takes a few minutes. In ChatGPT it is not for these kinds of product, and refuses a request for one of them: adult and sexual products and services, among them sex toys; real-money gambling; marijuana, THC and psilocybin products, illegal drugs, and CBD products whose THC is over the legal limit or not stated; drug paraphernalia; prescription and age-restricted medicines; counterfeit, replica, stolen or contraband goods, fraud tools and pirated software; malware, spyware and covert surveillance devices; tobacco and nicotine products, among them vapes and e-liquids; weapons, among them firearms, ammunition, explosives, fireworks and self-defense weapons, and extremist merchandise; and fraudulent or high-risk financial, identity, document and travel services.\n- get_video: How a video from make_video, or from a step after one, is going: queued, in_progress, ready or failed. Once ready, each video has after_steps, the steps it offers next with their prices in credits. Each ready video's download_url is made new in every answer and works for the next hour: its download_expires_in_seconds is the seconds it has left as that answer is made. For a later download, call get_video again for a new link. Free. Say It Again's display shows the person what this answer names, with its pictures, the only pictures of the product and of the presenters it names; a picture from another source shows another product or another person. The answer is given in words, with what matters in it and the next step, and cards or images of what the display shows would only repeat it, unless the person asks for a list or a table.\n- list_videos: The team's UGC videos, newest first. Each ready video's download_url is made new in every answer and works for the next hour: its download_expires_in_seconds is the seconds it has left as that answer is made. For a later download, call get_video again for a new link. Free. Say It Again's display shows the person what this answer names, with its pictures, the only pictures of the product and of the presenters it names; a picture from another source shows another product or another person. The answer is given in words, with what matters in it and the next step, and cards or images of what the display shows would only repeat it, unless the person asks for a list or a table.\n- list_presenters: The presenters a video can be made with, by id: ours and the ones the team described. Free. Say It Again's display shows the person what this answer names, with its pictures, the only pictures of the product and of the presenters it names; a picture from another source shows another product or another person. The answer is given in words, with what matters in it and the next step, and cards or images of what the display shows would only repeat it, unless the person asks for a list or a table.\n- describe_presenter: Draw a presenter of the team's own from a description of how they look, as the app's Describe a presenter does: an adult, invented, not a real person or a character. Free, and counted against the team's 5 drawings a day; a description refused, or a drawing that fails, gives its drawing back. Answers an id at once: call get_described with it every few seconds until its status is ready or refused.\n- get_described: How a drawing from describe_presenter is going: checking, drawing, ready with its 3 pictures, each by its number with a link that works for an hour, and the voice the description said if it said one, or refused with why. The person chooses one of the pictures, which keep_presenter keeps. Free.\n- keep_presenter: Keep one picture of a drawing as one of the team's presenters, with the voice the person chose for them. Answers the presenter's id, for presenters in the other tools. Free.\n- set_presenter_voice: Say or change the voice one of the team's described presenters speaks in, which make_video asks for before an Arabic video with a presenter nobody has given one: the person's choice, which a picture does not tell. Free.\n- change_video: Change one finished video as the person asks, made again into a new video beside it, as the app's Change does. This spends the team's credits: the price get_video lists in after_steps as change_video, refunded if it fails. Only for a video whose after_steps offers it. What to change is held to the app's checks: no price, and nothing that gives the presenter a past with the product. Answers an id at once: call get_video with it about once a minute until its status is ready or failed.\n- make_longer: Make one finished video longer, its take carried on with new lines written from the product page, into a new video beside it, as the app's Make this video 30 seconds does. This spends the team's credits: the price get_video lists in after_steps as make_longer, refunded if it fails. Only for a video whose after_steps offers it. Answers an id at once: call get_video with it about once a minute until its status is ready or failed.\n- another_language: Make one finished video again in another language, its own script and presenter, into a new video beside it, as the app's Another language does. This spends the team's credits: the price get_video lists in after_steps as another_language, or its voiced price for a voiced language, refunded if it fails. Only in a language that after_steps lists for it. Answers an id at once: call get_video with it about once a minute until its status is ready or failed.\n- other_sizes: Lay one finished video out in another size, the same video cut for that frame, as the app's Other sizes does. Free. Only for a video whose after_steps lists other_sizes, in a size it lists. Answers an id at once: call get_video with it every few seconds until its status is ready or failed. The same size asked again answers the one already made or being made.\n- list_ads: The Meta Ad Library ads the team's store already holds, to build a video like one with ad: its Competitors, the Winning ads of its kind and the library links it pasted, each with its id, advertiser, title, days running and whether it is a video, which ad needs. Free, and nothing is looked up.\n"
AFTER
"---\nname: say-it-again\ndescription: Make an AI UGC video of a product with the Say It Again tools, where a generated presenter films themselves with the product, or a product video of the product alone, or a set of image ads of it. Read the product from its link, write 3 scripts to read first if the person wants them, say what the video or the set costs in credits, make it, and follow it until it is ready. Use it when someone asks for a UGC video, a product video, a video ad, video scripts or image ads for a product they sell, asks what such a video costs, or asks about their Say It Again videos, presenters or credits.\n---\n\n# Making a Say It Again video\n\nSay It Again makes AI UGC videos of a store's products: a generated presenter films themselves with the product. A video is made in steps: read_product with the product's link, which also lists the angles a video of it can argue; then optionally write_scripts and get_scripts to read three scripts first; then quote_video for the price; then make_video, then get_video until its status is ready or failed. A video can be built like an ad the store holds, which list_ads lists, and said by a presenter of the team's own, drawn with describe_presenter, shown with get_described and kept with keep_presenter, whose voice set_presenter_voice says when an Arabic video asks for it. A ready video lists in after_steps what can be done with it next and what each costs: change_video, make_longer, another_language and other_sizes. Say It Again also makes product videos, the product alone on camera with a voiceover or music and no presenter: quote_product_video for the price, then make_product_video, then get_product_video until its status is ready or failed, a ready one listing in after_steps make_in_best, another_language and other_sizes; and image ads of a product, each a picture drawn whole with its own words: quote_image_ads for the price of a set, then make_image_ads, then get_image_ads until its status is ready or failed. make_video, change_video, make_longer, another_language, make_in_best, make_product_video and make_image_ads spend the team's credits, at the price quote_video, after_steps, quote_product_video or quote_image_ads gives, refunded if the video or the set fails. Every other tool is free. In ChatGPT, Say It Again makes no script, no video and no image ad for these kinds of product, promotional or not, and a tool asked for one refuses it: adult and sexual products and services, among them sex toys; real-money gambling; marijuana, THC and psilocybin products, illegal drugs, and CBD products whose THC is over the legal limit or not stated; drug paraphernalia; prescription and age-restricted medicines; counterfeit, replica, stolen or contraband goods, fraud tools and pirated software; malware, spyware and covert surveillance devices; tobacco and nicotine products, among them vapes and e-liquids; weapons, among them firearms, ammunition, explosives, fireworks and self-defense weapons, and extremist merchandise; and fraudulent or high-risk financial, identity, document and travel services. The pictures of the team's products and of the presenters these tools list are the ones Say It Again's display shows with the answers of read_product, list_presenters, get_video and list_videos; a picture from another source shows another product or another person. Those answers are given in words, with what matters in each and the next step, and cards or images of what the display shows would only repeat it, unless the person asks for a list or a table.\n\n## What the tools take\n\n- Every video starts from a product's link, or the id read_product gave for it.\n- Every choice has a default, used when it is left out.\n- make_video refuses a video the team's balance does not cover, which quote_video says before it.\n- make_video takes an idempotency_key: the same key sent again for the same video answers as the first call did and spends nothing more.\n\n## What the answers hold\n\n- What is known of a product, a script, a price or a video is what the tools answered, and the product's facts are the ones read_product gave.\n- A ready video's download link is the one in the latest answer, and get_video makes a new one for a later download.\n- A video that fails says why in get_video's answer, and its credits are refunded.\n\n## Lines for the presenter\n\nLines sent in the lines argument, and words a description gives someone to say, are said word for word as sent, not translated, and read by no check of ours. They come from what the person asks for and what read_product gave, and this rule holds for every one of them.\n\nEvery person in the ads we make, on camera or heard as a voice, is made by AI and is not a customer. Nothing in an ad may present them as someone who has used the product, because that is a fake testimonial and the law forbids it. So they have no past with it: no time spent with it, no result it has had on their own body, home, pet or life, no before and after of their own, no having bought it, and no job, family role or other identity that makes them sound like a real customer. What they have is the moment: showing the product, using it on camera and reacting to what it does there, saying what it is and what it does, and the facts the product page gives.\n\n## The tools\n\n- get_balance: The team's credits, its plan, and how many write_scripts calls it has left (scripts_left). Free.\n- read_product: Read a product's page from its link: its name, price, description, benefits, photos and the angles a video of it can argue, and an id to use in the other tools. Free, and counted against the team's product reads. Say It Again's display shows the person what this answer names, with its pictures, the only pictures of the product and of the presenters it names; a picture from another source shows another product or another person. The answer is given in words, with what matters in it and the next step, and cards or images of what the display shows would only repeat it, unless the person asks for a list or a table.\n- write_scripts: Write three scripts for a UGC video of a product, to read before making one. Say It Again's own writer writes them from the product read_product read, held to its facts. Free, and counted against the calls get_balance gives as scripts_left. Answers an id at once: call get_scripts with it about once a minute until its status is ready or failed. The product's photos are the ones read_product gives, which Say It Again's display shows; a picture from another source shows another product, not this one. In ChatGPT it is not for these kinds of product, and refuses a request for one of them: adult and sexual products and services, among them sex toys; real-money gambling; marijuana, THC and psilocybin products, illegal drugs, and CBD products whose THC is over the legal limit or not stated; drug paraphernalia; prescription and age-restricted medicines; counterfeit, replica, stolen or contraband goods, fraud tools and pirated software; malware, spyware and covert surveillance devices; tobacco and nicotine products, among them vapes and e-liquids; weapons, among them firearms, ammunition, explosives, fireworks and self-defense weapons, and extremist merchandise; and fraudulent or high-risk financial, identity, document and travel services.\n- get_scripts: Scripts written by write_scripts: queued, in_progress, ready with each script's shots and lines, the language its lines are in and what it left out of the description, or failed. Free. The product's photos are the ones read_product gives, which Say It Again's display shows; a picture from another source shows another product, not this one.\n- quote_video: What a video with these choices costs in credits, and whether the team's balance covers it. Free.\n- make_video: Make a UGC video of a product. This spends the team's credits: the price quote_video gives for the same choices, refunded if the video fails. Answers an id at once, and with languages an id for each language in ids: call get_video with each about once a minute until its status is ready or failed, which takes a few minutes. In ChatGPT it is not for these kinds of product, and refuses a request for one of them: adult and sexual products and services, among them sex toys; real-money gambling; marijuana, THC and psilocybin products, illegal drugs, and CBD products whose THC is over the legal limit or not stated; drug paraphernalia; prescription and age-restricted medicines; counterfeit, replica, stolen or contraband goods, fraud tools and pirated software; malware, spyware and covert surveillance devices; tobacco and nicotine products, among them vapes and e-liquids; weapons, among them firearms, ammunition, explosives, fireworks and self-defense weapons, and extremist merchandise; and fraudulent or high-risk financial, identity, document and travel services.\n- get_video: How a video from make_video, or from a step after one, is going: queued, in_progress, ready or failed. Once ready, each video has after_steps, the steps it offers next with their prices in credits. Each ready video's download_url is made new in every answer and works for the next hour: its download_expires_in_seconds is the seconds it has left as that answer is made. For a later download, call get_video again for a new link. Free. Say It Again's display shows the person what this answer names, with its pictures, the only pictures of the product and of the presenters it names; a picture from another source shows another product or another person. The answer is given in words, with what matters in it and the next step, and cards or images of what the display shows would only repeat it, unless the person asks for a list or a table.\n- list_videos: The team's UGC videos, newest first. Each ready video's download_url is made new in every answer and works for the next hour: its download_expires_in_seconds is the seconds it has left as that answer is made. For a later download, call get_video again for a new link. Free. Say It Again's display shows the person what this answer names, with its pictures, the only pictures of the product and of the presenters it names; a picture from another source shows another product or another person. The answer is given in words, with what matters in it and the next step, and cards or images of what the display shows would only repeat it, unless the person asks for a list or a table.\n- list_presenters: The presenters a video can be made with, by id: ours and the ones the team described. Free. Say It Again's display shows the person what this answer names, with its pictures, the only pictures of the product and of the presenters it names; a picture from another source shows another product or another person. The answer is given in words, with what matters in it and the next step, and cards or images of what the display shows would only repeat it, unless the person asks for a list or a table.\n- describe_presenter: Draw a presenter of the team's own from a description of how they look, as the app's Describe a presenter does: an adult, invented, not a real person or a character. Free, and counted against the team's 5 drawings a day; a description refused, or a drawing that fails, gives its drawing back. Answers an id at once: call get_described with it every few seconds until its status is ready or refused.\n- get_described: How a drawing from describe_presenter is going: checking, drawing, ready with its 3 pictures, each by its number with a link that works for an hour, and the voice the description said if it said one, or refused with why. The person chooses one of the pictures, which keep_presenter keeps. Free.\n- keep_presenter: Keep one picture of a drawing as one of the team's presenters, with the voice the person chose for them. Answers the presenter's id, for presenters in the other tools. Free.\n- set_presenter_voice: Say or change the voice one of the team's described presenters speaks in, which an Arabic video whose voice is added after filming asks for when its presenter has none: the person's choice, which a picture does not tell. Free.\n- change_video: Change one finished video as the person asks, made again into a new video beside it, as the app's Change does. This spends the team's credits: the price get_video lists in after_steps as change_video, refunded if it fails. Only for a video whose after_steps offers it. What to change is the person's own words; a change the video cannot be made with at all is answered with why and spends nothing. Answers an id at once: call get_video with it about once a minute until its status is ready or failed.\n- make_longer: Make one finished video longer, its take carried on with new lines written from the product page, into a new video beside it, as the app's Make this video 30 seconds does. This spends the team's credits: the price get_video lists in after_steps as make_longer, refunded if it fails. Only for a video whose after_steps offers it. Answers an id at once: call get_video with it about once a minute until its status is ready or failed.\n- another_language: Make one finished video again in another language, into a new video beside it, as the app's Another language does: a UGC video with its own script and presenter, a product video with its voiceover said again over the same picture. This spends the team's credits: the price get_video or get_product_video lists in after_steps as another_language, or its voiced price for a voiced language, refunded if it fails. Only in a language that after_steps lists for it. Answers an id at once: call get_video with it, or get_product_video for a product video's, about once a minute until its status is ready or failed.\n- other_sizes: Lay one finished video out in another size, the same video cut for that frame, as the app's Other sizes does. Free. Only for a video whose after_steps lists other_sizes, in a size it lists. Answers an id at once: call get_video with it, or get_product_video for a product video's, every few seconds until its status is ready or failed. The same size asked again answers the one already made or being made.\n- list_ads: The ads the team's store already holds, from the Meta Ad Library and TikTok's, to build a video like one with ad: its Competitors, the Winning ads of its kind and the Meta Ad Library links it pasted, each with its id, library, advertiser, title, days running and whether it is a video, which ad needs. Free, and nothing is looked up.\n- quote_product_video: What a product video with these choices costs in credits, and whether the team's balance covers it. Free.\n- make_product_video: Make a product video, as the app's Product video does: the product alone on camera, doing what it does, with a voiceover, a voiceover over music or music alone, and no presenter, written from the product's page and the description. This spends the team's credits: the price quote_product_video gives for the same choices, refunded if the video fails. Answers an id at once: call get_product_video with it about once a minute until its status is ready or failed, which takes a few minutes. In ChatGPT it is not for these kinds of product, and refuses a request for one of them: adult and sexual products and services, among them sex toys; real-money gambling; marijuana, THC and psilocybin products, illegal drugs, and CBD products whose THC is over the legal limit or not stated; drug paraphernalia; prescription and age-restricted medicines; counterfeit, replica, stolen or contraband goods, fraud tools and pirated software; malware, spyware and covert surveillance devices; tobacco and nicotine products, among them vapes and e-liquids; weapons, among them firearms, ammunition, explosives, fireworks and self-defense weapons, and extremist merchandise; and fraudulent or high-risk financial, identity, document and travel services.\n- get_product_video: How a product video from make_product_video, or from a step after one, is going: queued, in_progress, ready or failed, with why and whether its credits were refunded. Once ready, it has after_steps, the steps it offers next with their prices in credits. Each ready video's download_url is made new in every answer and works for the next hour: its download_expires_in_seconds is the seconds it has left as that answer is made. For a later download, call get_product_video again for a new link. Free.\n- make_in_best: Make one finished product video made in fast again in best, its own script, photos and choices, into a new product video beside it, as the app's Make this video in Best does. This spends the team's credits: the price get_product_video lists in after_steps as make_in_best, refunded if it fails. Only for a video whose after_steps offers it. Answers an id at once: call get_product_video with it about once a minute until its status is ready or failed.\n- quote_image_ads: What a set of image ads costs in credits, and whether the team's balance covers it. Free.\n- make_image_ads: Make a set of image ads of a product, as the app's Image ads does: each ad a picture of the product drawn whole, with its own headline, second line and button, made from the product's page and the description. This spends the team's credits: the price quote_image_ads gives for the same count, refunded if the set fails. Answers an id at once: call get_image_ads with it about once a minute until its status is ready or failed. In ChatGPT it is not for these kinds of product, and refuses a request for one of them: adult and sexual products and services, among them sex toys; real-money gambling; marijuana, THC and psilocybin products, illegal drugs, and CBD products whose THC is over the legal limit or not stated; drug paraphernalia; prescription and age-restricted medicines; counterfeit, replica, stolen or contraband goods, fraud tools and pirated software; malware, spyware and covert surveillance devices; tobacco and nicotine products, among them vapes and e-liquids; weapons, among them firearms, ammunition, explosives, fireworks and self-defense weapons, and extremist merchandise; and fraudulent or high-risk financial, identity, document and travel services.\n- get_image_ads: How a set from make_image_ads is going: queued, in_progress, ready with each image ad's headline, second line and button, in headline, subhead and cta, and its download_url, or failed with why and whether its credits were refunded. Each image ad's download_url is made new in every answer and works for the next hour: its download_expires_in_seconds is the seconds it has left as that answer is made. For a later download, call get_image_ads again for a new link. Free.\n"
Full snapshot data
{
"description": "Make an AI UGC video of a product with the Say It Again tools, where a generated presenter films themselves with the product, or a product video of the product alone, or a set of image ads of it. Read the product from its link, write 3 scripts to read first if the person wants them, say what the video or the set costs in credits, make it, and follow it until it is ready. Use it when someone asks for a UGC video, a product video, a video ad, video scripts or image ads for a product they sell, asks what such a video costs, or asks about their Say It Again videos, presenters or credits.",
"included_files": [],
"name": "say-it-again",
"skill_md_contents": "---\nname: say-it-again\ndescription: Make an AI UGC video of a product with the Say It Again tools, where a generated presenter films themselves with the product, or a product video of the product alone, or a set of image ads of it. Read the product from its link, write 3 scripts to read first if the person wants them, say what the video or the set costs in credits, make it, and follow it until it is ready. Use it when someone asks for a UGC video, a product video, a video ad, video scripts or image ads for a product they sell, asks what such a video costs, or asks about their Say It Again videos, presenters or credits.\n---\n\n# Making a Say It Again video\n\nSay It Again makes AI UGC videos of a store's products: a generated presenter films themselves with the product. A video is made in steps: read_product with the product's link, which also lists the angles a video of it can argue; then optionally write_scripts and get_scripts to read three scripts first; then quote_video for the price; then make_video, then get_video until its status is ready or failed. A video can be built like an ad the store holds, which list_ads lists, and said by a presenter of the team's own, drawn with describe_presenter, shown with get_described and kept with keep_presenter, whose voice set_presenter_voice says when an Arabic video asks for it. A ready video lists in after_steps what can be done with it next and what each costs: change_video, make_longer, another_language and other_sizes. Say It Again also makes product videos, the product alone on camera with a voiceover or music and no presenter: quote_product_video for the price, then make_product_video, then get_product_video until its status is ready or failed, a ready one listing in after_steps make_in_best, another_language and other_sizes; and image ads of a product, each a picture drawn whole with its own words: quote_image_ads for the price of a set, then make_image_ads, then get_image_ads until its status is ready or failed. make_video, change_video, make_longer, another_language, make_in_best, make_product_video and make_image_ads spend the team's credits, at the price quote_video, after_steps, quote_product_video or quote_image_ads gives, refunded if the video or the set fails. Every other tool is free. In ChatGPT, Say It Again makes no script, no video and no image ad for these kinds of product, promotional or not, and a tool asked for one refuses it: adult and sexual products and services, among them sex toys; real-money gambling; marijuana, THC and psilocybin products, illegal drugs, and CBD products whose THC is over the legal limit or not stated; drug paraphernalia; prescription and age-restricted medicines; counterfeit, replica, stolen or contraband goods, fraud tools and pirated software; malware, spyware and covert surveillance devices; tobacco and nicotine products, among them vapes and e-liquids; weapons, among them firearms, ammunition, explosives, fireworks and self-defense weapons, and extremist merchandise; and fraudulent or high-risk financial, identity, document and travel services. The pictures of the team's products and of the presenters these tools list are the ones Say It Again's display shows with the answers of read_product, list_presenters, get_video and list_videos; a picture from another source shows another product or another person. Those answers are given in words, with what matters in each and the next step, and cards or images of what the display shows would only repeat it, unless the person asks for a list or a table.\n\n## What the tools take\n\n- Every video starts from a product's link, or the id read_product gave for it.\n- Every choice has a default, used when it is left out.\n- make_video refuses a video the team's balance does not cover, which quote_video says before it.\n- make_video takes an idempotency_key: the same key sent again for the same video answers as the first call did and spends nothing more.\n\n## What the answers hold\n\n- What is known of a product, a script, a price or a video is what the tools answered, and the product's facts are the ones read_product gave.\n- A ready video's download link is the one in the latest answer, and get_video makes a new one for a later download.\n- A video that fails says why in get_video's answer, and its credits are refunded.\n\n## Lines for the presenter\n\nLines sent in the lines argument, and words a description gives someone to say, are said word for word as sent, not translated, and read by no check of ours. They come from what the person asks for and what read_product gave, and this rule holds for every one of them.\n\nEvery person in the ads we make, on camera or heard as a voice, is made by AI and is not a customer. Nothing in an ad may present them as someone who has used the product, because that is a fake testimonial and the law forbids it. So they have no past with it: no time spent with it, no result it has had on their own body, home, pet or life, no before and after of their own, no having bought it, and no job, family role or other identity that makes them sound like a real customer. What they have is the moment: showing the product, using it on camera and reacting to what it does there, saying what it is and what it does, and the facts the product page gives.\n\n## The tools\n\n- get_balance: The team's credits, its plan, and how many write_scripts calls it has left (scripts_left). Free.\n- read_product: Read a product's page from its link: its name, price, description, benefits, photos and the angles a video of it can argue, and an id to use in the other tools. Free, and counted against the team's product reads. Say It Again's display shows the person what this answer names, with its pictures, the only pictures of the product and of the presenters it names; a picture from another source shows another product or another person. The answer is given in words, with what matters in it and the next step, and cards or images of what the display shows would only repeat it, unless the person asks for a list or a table.\n- write_scripts: Write three scripts for a UGC video of a product, to read before making one. Say It Again's own writer writes them from the product read_product read, held to its facts. Free, and counted against the calls get_balance gives as scripts_left. Answers an id at once: call get_scripts with it about once a minute until its status is ready or failed. The product's photos are the ones read_product gives, which Say It Again's display shows; a picture from another source shows another product, not this one. In ChatGPT it is not for these kinds of product, and refuses a request for one of them: adult and sexual products and services, among them sex toys; real-money gambling; marijuana, THC and psilocybin products, illegal drugs, and CBD products whose THC is over the legal limit or not stated; drug paraphernalia; prescription and age-restricted medicines; counterfeit, replica, stolen or contraband goods, fraud tools and pirated software; malware, spyware and covert surveillance devices; tobacco and nicotine products, among them vapes and e-liquids; weapons, among them firearms, ammunition, explosives, fireworks and self-defense weapons, and extremist merchandise; and fraudulent or high-risk financial, identity, document and travel services.\n- get_scripts: Scripts written by write_scripts: queued, in_progress, ready with each script's shots and lines, the language its lines are in and what it left out of the description, or failed. Free. The product's photos are the ones read_product gives, which Say It Again's display shows; a picture from another source shows another product, not this one.\n- quote_video: What a video with these choices costs in credits, and whether the team's balance covers it. Free.\n- make_video: Make a UGC video of a product. This spends the team's credits: the price quote_video gives for the same choices, refunded if the video fails. Answers an id at once, and with languages an id for each language in ids: call get_video with each about once a minute until its status is ready or failed, which takes a few minutes. In ChatGPT it is not for these kinds of product, and refuses a request for one of them: adult and sexual products and services, among them sex toys; real-money gambling; marijuana, THC and psilocybin products, illegal drugs, and CBD products whose THC is over the legal limit or not stated; drug paraphernalia; prescription and age-restricted medicines; counterfeit, replica, stolen or contraband goods, fraud tools and pirated software; malware, spyware and covert surveillance devices; tobacco and nicotine products, among them vapes and e-liquids; weapons, among them firearms, ammunition, explosives, fireworks and self-defense weapons, and extremist merchandise; and fraudulent or high-risk financial, identity, document and travel services.\n- get_video: How a video from make_video, or from a step after one, is going: queued, in_progress, ready or failed. Once ready, each video has after_steps, the steps it offers next with their prices in credits. Each ready video's download_url is made new in every answer and works for the next hour: its download_expires_in_seconds is the seconds it has left as that answer is made. For a later download, call get_video again for a new link. Free. Say It Again's display shows the person what this answer names, with its pictures, the only pictures of the product and of the presenters it names; a picture from another source shows another product or another person. The answer is given in words, with what matters in it and the next step, and cards or images of what the display shows would only repeat it, unless the person asks for a list or a table.\n- list_videos: The team's UGC videos, newest first. Each ready video's download_url is made new in every answer and works for the next hour: its download_expires_in_seconds is the seconds it has left as that answer is made. For a later download, call get_video again for a new link. Free. Say It Again's display shows the person what this answer names, with its pictures, the only pictures of the product and of the presenters it names; a picture from another source shows another product or another person. The answer is given in words, with what matters in it and the next step, and cards or images of what the display shows would only repeat it, unless the person asks for a list or a table.\n- list_presenters: The presenters a video can be made with, by id: ours and the ones the team described. Free. Say It Again's display shows the person what this answer names, with its pictures, the only pictures of the product and of the presenters it names; a picture from another source shows another product or another person. The answer is given in words, with what matters in it and the next step, and cards or images of what the display shows would only repeat it, unless the person asks for a list or a table.\n- describe_presenter: Draw a presenter of the team's own from a description of how they look, as the app's Describe a presenter does: an adult, invented, not a real person or a character. Free, and counted against the team's 5 drawings a day; a description refused, or a drawing that fails, gives its drawing back. Answers an id at once: call get_described with it every few seconds until its status is ready or refused.\n- get_described: How a drawing from describe_presenter is going: checking, drawing, ready with its 3 pictures, each by its number with a link that works for an hour, and the voice the description said if it said one, or refused with why. The person chooses one of the pictures, which keep_presenter keeps. Free.\n- keep_presenter: Keep one picture of a drawing as one of the team's presenters, with the voice the person chose for them. Answers the presenter's id, for presenters in the other tools. Free.\n- set_presenter_voice: Say or change the voice one of the team's described presenters speaks in, which an Arabic video whose voice is added after filming asks for when its presenter has none: the person's choice, which a picture does not tell. Free.\n- change_video: Change one finished video as the person asks, made again into a new video beside it, as the app's Change does. This spends the team's credits: the price get_video lists in after_steps as change_video, refunded if it fails. Only for a video whose after_steps offers it. What to change is the person's own words; a change the video cannot be made with at all is answered with why and spends nothing. Answers an id at once: call get_video with it about once a minute until its status is ready or failed.\n- make_longer: Make one finished video longer, its take carried on with new lines written from the product page, into a new video beside it, as the app's Make this video 30 seconds does. This spends the team's credits: the price get_video lists in after_steps as make_longer, refunded if it fails. Only for a video whose after_steps offers it. Answers an id at once: call get_video with it about once a minute until its status is ready or failed.\n- another_language: Make one finished video again in another language, into a new video beside it, as the app's Another language does: a UGC video with its own script and presenter, a product video with its voiceover said again over the same picture. This spends the team's credits: the price get_video or get_product_video lists in after_steps as another_language, or its voiced price for a voiced language, refunded if it fails. Only in a language that after_steps lists for it. Answers an id at once: call get_video with it, or get_product_video for a product video's, about once a minute until its status is ready or failed.\n- other_sizes: Lay one finished video out in another size, the same video cut for that frame, as the app's Other sizes does. Free. Only for a video whose after_steps lists other_sizes, in a size it lists. Answers an id at once: call get_video with it, or get_product_video for a product video's, every few seconds until its status is ready or failed. The same size asked again answers the one already made or being made.\n- list_ads: The ads the team's store already holds, from the Meta Ad Library and TikTok's, to build a video like one with ad: its Competitors, the Winning ads of its kind and the Meta Ad Library links it pasted, each with its id, library, advertiser, title, days running and whether it is a video, which ad needs. Free, and nothing is looked up.\n- quote_product_video: What a product video with these choices costs in credits, and whether the team's balance covers it. Free.\n- make_product_video: Make a product video, as the app's Product video does: the product alone on camera, doing what it does, with a voiceover, a voiceover over music or music alone, and no presenter, written from the product's page and the description. This spends the team's credits: the price quote_product_video gives for the same choices, refunded if the video fails. Answers an id at once: call get_product_video with it about once a minute until its status is ready or failed, which takes a few minutes. In ChatGPT it is not for these kinds of product, and refuses a request for one of them: adult and sexual products and services, among them sex toys; real-money gambling; marijuana, THC and psilocybin products, illegal drugs, and CBD products whose THC is over the legal limit or not stated; drug paraphernalia; prescription and age-restricted medicines; counterfeit, replica, stolen or contraband goods, fraud tools and pirated software; malware, spyware and covert surveillance devices; tobacco and nicotine products, among them vapes and e-liquids; weapons, among them firearms, ammunition, explosives, fireworks and self-defense weapons, and extremist merchandise; and fraudulent or high-risk financial, identity, document and travel services.\n- get_product_video: How a product video from make_product_video, or from a step after one, is going: queued, in_progress, ready or failed, with why and whether its credits were refunded. Once ready, it has after_steps, the steps it offers next with their prices in credits. Each ready video's download_url is made new in every answer and works for the next hour: its download_expires_in_seconds is the seconds it has left as that answer is made. For a later download, call get_product_video again for a new link. Free.\n- make_in_best: Make one finished product video made in fast again in best, its own script, photos and choices, into a new product video beside it, as the app's Make this video in Best does. This spends the team's credits: the price get_product_video lists in after_steps as make_in_best, refunded if it fails. Only for a video whose after_steps offers it. Answers an id at once: call get_product_video with it about once a minute until its status is ready or failed.\n- quote_image_ads: What a set of image ads costs in credits, and whether the team's balance covers it. Free.\n- make_image_ads: Make a set of image ads of a product, as the app's Image ads does: each ad a picture of the product drawn whole, with its own headline, second line and button, made from the product's page and the description. This spends the team's credits: the price quote_image_ads gives for the same count, refunded if the set fails. Answers an id at once: call get_image_ads with it about once a minute until its status is ready or failed. In ChatGPT it is not for these kinds of product, and refuses a request for one of them: adult and sexual products and services, among them sex toys; real-money gambling; marijuana, THC and psilocybin products, illegal drugs, and CBD products whose THC is over the legal limit or not stated; drug paraphernalia; prescription and age-restricted medicines; counterfeit, replica, stolen or contraband goods, fraud tools and pirated software; malware, spyware and covert surveillance devices; tobacco and nicotine products, among them vapes and e-liquids; weapons, among them firearms, ammunition, explosives, fireworks and self-defense weapons, and extremist merchandise; and fraudulent or high-risk financial, identity, document and travel services.\n- get_image_ads: How a set from make_image_ads is going: queued, in_progress, ready with each image ad's headline, second line and button, in headline, subhead and cta, and its download_url, or failed with why and whether its credits were refunded. Each image ad's download_url is made new in every answer and works for the next hour: its download_expires_in_seconds is the seconds it has left as that answer is made. For a later download, call get_image_ads again for a new link. Free.\n"
}SHA-256 of public snapshot: 07efec5b45cda2fb3f4eed6560fb8cf4ce47ee8afa109442a9d18c59d2a54cd0