ProsodyAI
ProsodyAI v1.0.0
Speech and video from text
From the developer
Declared capabilities
- Text to speech in 59 languages
- Video from a description
- Reusable characters
Cost & access
ProsodyAI sells nothing inside ChatGPT and starts no checkout. Users sign in to an existing ProsodyAI account, and each request uses the allowance of that account's current plan.
Declared limitations
- Voice cloning is not offered: ProsodyAI has no tool that copies a real person's voice. The model should decline and may offer one of the built-in voices instead, without calling generate_speech with a claimed celebrity voice.
- Files uploaded to the chat cannot be edited: edit_video accepts only job ids of videos ProsodyAI made for this account. The model should explain this and offer to make a new video instead, without calling edit_video.
- Nothing is sold inside ChatGPT and there is no purchase tool. The model should say that credits cannot be bought here and that requests use the existing plan; it may call get_account to show what is left, but must not start a purchase.
Onboarding example
Read this paragraph aloud in Turkish with a warm, calm voice.
Sources & dates
Developer declarations; not independently tested. Listing last checked Nov 13, 2026. Package observed Nov 13, 2026.
Description
From the marketplace listing
ProsodyAI turns text into speech and descriptions into video, on your own ProsodyAI account. Speech: 59 languages with OpenAI or Gemini voices. Describe the delivery in plain words, such as "warm and unhurried" or "excited sports commentator", and get a download link. Video: describe a scene and ProsodyAI renders a clip with Veo, Seedance or Wan 3.0. A clip takes a few minutes; ask for its status and you get the link when it is ready. Characters: create a character from a description, approve its front view, and reuse it so the same person appears across clips. Edits: add a voiceover to a video ProsodyAI made, with optional burned-in subtitles; merge clips, trim, remove silences or make a GIF. Account: see your plan and what is left this month. Who it is for: creators, marketers and teams who need narration, voiceovers and short clips without leaving the conversation. Limitations: you sign in with a ProsodyAI account, and every request uses that account's plan and its allowance; video needs video seconds on the account. Nothing is sold inside ChatGPT. There is no voice cloning: speech uses ProsodyAI's built-in voices. Edits work only on videos ProsodyAI made for you, not on files uploaded to the chat. Download links stay valid for 7 days, and results also appear in your history at prosodyai.ai/history.
Language: English · Automatically detected from descriptions.
Changes
No changes recorded yet. Follow this plugin to keep track of future changes.
First seen Nov 13, 2026. Last seen Nov 13, 2026.
Similar plugins
Find competitors to follow as you develop your plugin.
-
Turn your own script, article, lesson or story into a narrated MP3, paced for listening in the delivery style you describe and read by a ...
Shared terms: speech, text, character, creator
-
OceanToken puts 500+ AI models behind one account and one prepaid balance: GPT, Claude, Gemini, DeepSeek and Qwen for text; GPT Image, Se...
Shared terms: speech, video, download, gemini
-
Turn a story idea into an animated short in anime, cartoon, chibi, storybook or 3D style, with recurring characters, dialogue and narrati...
Shared terms: video, text, character, creator
-
Transcribe public videos and audio into timestamped text, summaries and subtitles.
Shared terms: video, text, minute, subtitle
-
Generate and edit on-brand images, videos, speech, and branded graphics with Creative Claw.
Shared terms: video, character, clip, creator
Keywords
Files & skills
File archives
Skill instructions
get-started2.46 KB
---
name: get-started
description: Help a user who just installed ProsodyAI sign in, see what their account can do, and make a first piece of speech or video. Use when the user runs setup, asks how ProsodyAI works, or asks what they can make with it.
---
Use this skill to get a new ProsodyAI user from installation to a first result.
Explicit instructions from the user take priority over these steps; skip any
step the user does not want.
1. **Sign-in.** The first ProsodyAI tool call opens ProsodyAI's sign-in page.
The user signs in with an existing ProsodyAI account (email and password,
Google or Apple) and approves the connection. Never ask for a password or a
code in the chat.
2. **Check the account.** Call `get_account` and tell the user their plan and
what is left this month (premium characters, video seconds, images). Report
only the figures the tool returns.
3. **Offer a first task.** Suggest one or two of these, in the user's language:
- Speech: "Read this in Turkish with a warm, unhurried voice: ...".
`list_voices` shows the voices for a language; `generate_speech` takes the
text, the language code and the delivery in plain words.
- Video: "Make a 5-second video of ...". `list_video_options` shows what the
plan can make; `generate_video` starts the clip and `get_job` returns the
link when it is finished (usually a few minutes).
- Edits of a video ProsodyAI made: a voiceover with optional subtitles,
merge, trim, remove silences or GIF, through `edit_video`.
- Characters: `create_character`, then `approve_character`, then use its id
in `generate_video` to keep the same person across clips.
4. **Before spending.** `generate_speech`, `generate_video`, `edit_video`,
`create_character` and `approve_character` use the account's allowance.
Confirm the text, voice or video settings with the user before calling them
when the request is ambiguous.
5. **Results.** Give the download link the tool returns. Links stay valid for
7 days; results also appear at https://prosodyai.ai/history.
Do not:
- Offer voice cloning or imitate a real person's voice; ProsodyAI has only its
built-in voices.
- Offer to edit files uploaded to the chat; `edit_video` works only on videos
ProsodyAI made for this account.
- Sell, recommend or start a purchase of plans or credits. If a tool says the
plan or allowance does not cover a request, relay that explanation as it is.
- Invent voice ids, job ids, links or allowance figures.
Release notes
First release: speech in 59 languages, video with Veo, Seedance and Wan 3.0, reusable characters, video edits (voiceover with subtitles, merge, trim, remove silences, GIF) and the account's plan and allowance.
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
- ProsodyAI
- Keywords
- See keywords
- Getting started skill
- ./skills/get-started/SKILL.md
- Commerce declaration
- Does not support commerceThis does not establish whether access is free or paid.
- Review scenarios
- 5 positive · 3 negativeScenario counts, not test results.
Declared capabilities
- Text to speech in 59 languages
- Video from a description
- Reusable characters
- Voiceovers and subtitles on generated videos
- Merge, trim, remove silences, GIF
- Plan and allowance
Package observed Nov 13, 2026.
Technical details
- First seen
- Nov 13, 2026 · 00:00 UTC
- Last seen
- Nov 13, 2026 · 00:00 UTC
- Collection status
- Collected
plugin_asdk_app_6ae439a44a0881918ad76e63b99d5885
Download plugin data (JSON)Plugin details: freshly prepared. Prepared . Refreshed when plugin data changes or after 6 hours. Your account and Follow status are live.