Digital human founder video
Keep the founder on camera every week
Founder IP Avatar Studio turns one founder or expert portrait and a weekly script into a talking-head video animated from that portrait and spoken in the person's cloned voice. The first week can clone the voice from a 10-second to 5-minute sample, and later weeks reuse it. Founder IP Avatar Studio works in Claude Code, Codex, Cursor, and other agents that run Skills.
Install Founder IP Avatar Studio and tell me when I need to sign in: https://beatra.ai/skills/founder-ip-avatar-studio/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 likeness, a weekly presenter clip
Keep one stable face
Use a single portrait so every weekly update looks like the same founder or expert.
Speak in that person's voice
Clone that person's voice or prepare narration, then drive a clear talking-head performance.
Ship a weekly clip
Turn each new script into the next founder update, explainer, or brand announcement.
How it is made
Build the presenter around a face people already know
Use one clear founder or expert portrait and keep framing, expression, and background restrained from week to week.
Use one stable portrait · Keep the same framing · Hold expression to the message
Let the clip speak in a voice that matches the face
Clone that person's voice or prepare a short script, then review the narration before the presenter clip.
Use the person's own voice · Make the weekly script easy to say · Hear the narration first
Turn this week's script into the next update
Direct a stable talking-head, then reuse the same likeness and voice as the series continues.
Keep one message per clip · Review identity and mouth timing · Reuse the same face and voice next week
Founder updates, expert explainers, announcements
Founder weekly updates
Publish a talking-head founder series without booking a new camera day.
Expert explainers
Let a specialist walk through one idea in their own face and voice.
Brand announcements
Put a digital human spokesperson in front of a launch or customer message.
Inputs and outputs
Input · Image — Founder or expert portrait
- Formats
- JPG, PNG
- Specifications
- 1 image per request
Input · Text — The weekly script
Input · Audio — Voice sample for the cloned voice
- Specifications
- 10–300 s; up to 20 MB each
Output · Video — Talking-head video animated from the founder's portrait, in the cloned voice
- Formats
- MP4
| Input or output | Type | Formats | Specifications |
|---|---|---|---|
| Input | Image — Founder or expert portrait | JPG, PNG | 1 image per request |
| Input | Text — The weekly script | — | — |
| Input | Audio — Voice sample for the cloned voice | — | 10–300 s; up to 20 MB each |
| Output | Video — Talking-head video animated from the founder's portrait, in the cloned voice | MP4 | — |
Specifications last checked · Sources: Model catalog · Documentation · Terms of Service
Questions
What do I need to start?
One clear founder or expert portrait and this week's script. Later weeks only need the next script.
What does the voice sample need to be?
A clean recording of the person speaking, 10 seconds to 5 minutes long and up to 20 MB.
What is this for?
Weekly founder updates, expert explainers, and brand announcements presented by one founder or expert.
Related Skills
