Hiring talking-head
Put the role on camera without a shoot day
Hiring Avatar Studio turns one HR or founder portrait and a job brief into a talking-head hiring video for each open role, covering the role, the requirements, and the next step. The first role can clone the presenter's voice from a 10-second to 5-minute sample, and later openings reuse it. Hiring Avatar Studio works in Claude Code, Codex, Cursor, and other agents that run Skills.
Install Hiring Avatar Studio and tell me when I need to sign in: https://beatra.ai/skills/hiring-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 hiring clip per role
Keep one stable face
Use a single HR or founder portrait so every open role looks like the same person.
Speak the job clearly
Clone or pick a voice, then walk through the role, requirements, and next step.
Repeat as roles open
Reuse the same likeness and voice when the next job brief is ready.
How it is made
Build the hiring clip around a face candidates already trust
Use one clear HR or founder portrait and keep framing, expression, and background restrained from role to role.
Use one stable portrait · Keep the same framing · Hold expression to the role
Let the clip say what the role actually is
Prepare the JD or a short script, then review the narration before the talking-head.
Keep the brief easy to say · Hear the narration first · Split a long script into sequential clips
Turn the next brief into the next clip
Direct a stable talking-head, then reuse the same likeness and voice as roles continue to open.
Keep one role per clip · Review identity and mouth timing · Reuse the same face and voice next role
Open roles, job posts, and career-page clips
Job posting clips
Turn a JD into a talking-head candidates can watch on the careers page.
Founder hiring messages
Let a founder walk through why this role matters, in their own face.
New openings
When the next role opens, reuse the same portrait and voice with the new brief.
Inputs and outputs
Input · Image — HR or founder portrait
- Formats
- JPG, PNG
- Specifications
- 1 image per request
Input · Text — Job brief for each open role
Input · Audio — Voice sample for the cloned voice (optional)
- Specifications
- 10–300 s; up to 20 MB each
Output · Video — One talking-head hiring video per open role
- Formats
- MP4
| Input or output | Type | Formats | Specifications |
|---|---|---|---|
| Input | Image — HR or founder portrait | JPG, PNG | 1 image per request |
| Input | Text — Job brief for each open role | — | — |
| Input | Audio — Voice sample for the cloned voice (optional) | — | 10–300 s; up to 20 MB each |
| Output | Video — One talking-head hiring video per open role | MP4 | — |
Specifications last checked · Sources: Model catalog · Documentation · Terms of Service
Questions
What do I need to start?
One clear HR or founder portrait and the job brief or script. Later roles only need the next brief.
What does the voice sample need to be?
A clean recording of the presenter speaking, 10 seconds to 5 minutes long and up to 20 MB.
What is this for?
One talking-head hiring video per open role for job posts, careers pages, and founder hiring messages.
Related Skills
