Talking avatar and AI presenter
Give one portrait a clear message
Talking Avatar & AI Presenter Video turns one portrait and a short script or speech track into a talking-head presenter clip. It voices the script in a library voice or uses your own recording, then delivers one MP4 of up to 15 seconds where the face moves with the speech, for explainers, announcements, lessons, and product messages. Talking Avatar & AI Presenter Video works in Claude Code, Codex, Cursor, and other agents that run Skills.
Install Talking Avatar & AI Presenter Video and tell me when I need to sign in: https://beatra.ai/skills/talking-avatar-video/install.md
For agents:Install guideMarkdown version
Send it to WorkBuddy, Codex, Claude Code, or another agent to install. Sign in once the first time you use it.GitHub ↗Docs ↗
One portrait, one voice-led presenter clip
Prepare the speech
Use a supplied speech track or turn a short script into reviewable narration before the video stage.
Direct a credible shot
Keep expression, head movement, camera, and background restrained, then review identity and mouth timing honestly.
How it is made
Build the clip around speech that fits
Use a supplied speech track or select a voice for a short script, check the actual audio length, and shape it for the presenter clip.
Make the script easy to say · Review generated narration before video · Match clip length to actual speech
Keep the performance focused
Direct the eyes, expression, posture, gentle movement, framing, and background around one clear message.
Use one stable portrait · Avoid competing movement · Review identity and mouth timing
Explainers, product messages, training, and announcements
Product explainers
Present a short feature, offer, or launch message without a new camera shoot.
Training and lessons
Deliver a compact onboarding point, course introduction, or internal update.
Announcements and social
Turn a prepared message into a human-facing announcement or talking-head post.
Inputs and outputs
Input · Image — One portrait of the presenter
- Formats
- JPG, PNG
- Specifications
- 1 image per request
Input · Text — A short script to narrate
Input · Audio — Speech track you recorded (optional)
- Formats
- MP3, WAV
- Specifications
- 2–15 s; up to 15 MB each
Output · Video — Talking-head presenter clip driven by the speech
- Formats
- MP4
- Specifications
- 1 video per request; up to 15 s
Output · Audio — Narration made from your script
- Formats
- MP3
| Input or output | Type | Formats | Specifications |
|---|---|---|---|
| Input | Image — One portrait of the presenter | JPG, PNG | 1 image per request |
| Input | Text — A short script to narrate | — | — |
| Input | Audio — Speech track you recorded (optional) | MP3, WAV | 2–15 s; up to 15 MB each |
| Output | Video — Talking-head presenter clip driven by the speech | MP4 | 1 video per request; up to 15 s |
| Output | Audio — Narration made from your script | MP3 | — |
Specifications last checked · Sources: Model catalog · Documentation · Terms of Service
Install tested in Claude Code, Codex, Gemini CLI, GitHub Copilot CLI, Grok CLI, and Antigravity CLI. All results
Questions
What do I need to start?
One portrait and either a speech track you recorded or a short script plus a voice.
Can I use my own recorded audio?
Yes. An MP3 or WAV recording of 2 to 15 seconds, up to 15 MB, drives the presenter directly.
How is the presenter clip made?
The face is animated from your portrait, and the speech drives the mouth.
Related Skills
