---
title: "Talking-Head Video Avatar: A Week of Scripts, Your Cloned Voice and a Digital Twin from One Photo"
summary: "A week of five talking-video topics and the first video's segmented script written first, then your cloned voice and your photo in captioned talking-head videos of up to two minutes."
url: "https://beatra.ai/en/skills/avatar-presenter"
language: "en"
version: "0.1.1"
last_verified: "2026-11-09"
---

[Skills](https://beatra.ai/en/skills) · [Video & animation](https://beatra.ai/en/skills/categories/video-animation)

# Write the week, then let your digital twin say it

Talking-Head Video Avatar writes five talking-video topics, the first video's segmented script, titles, hashtags, and cover text first. Your cloned voice and your photo then turn each script into a captioned talking-head MP4 of up to two minutes, in your photo's orientation, with the narration files and SRT captions alongside. Talking-Head Video Avatar works in Claude Code, Codex, Cursor, and other agents that run Skills.

```text
Install Talking-Head Video Avatar and tell me when I need to sign in: https://beatra.ai/skills/avatar-presenter/install.md
```

Send it to WorkBuddy, Codex, Claude Code, or another agent to install. Sign in once the first time you use it.

[install.md](https://beatra.ai/skills/avatar-presenter/install.md) · [Docs](https://docs.beatra.ai/en/docs/capabilities)

## A week of talking videos without filming

### The week is written first

Five topics with opening hooks and a script ready to read aloud arrive in the first reply.

### Your voice in every video

Clone your voice once and every video after it sounds like you.

### Your photo presents

A front-facing photo from the shoulders up speaks each script, with captions, in videos of up to two minutes.

## How it is made

### Start · The week on paper

Five topics with the day, the purpose, and a three-second hook, and video 1's script in numbered segments with pauses, counts, and time ranges.

- Five topics and opening hooks
- A script ready to read aloud
- Two titles, hashtags, and cover text

### Voice · Cloned from your own recording

Send a clean recording of yourself speaking; the clone is made once and every later video uses it.

### Video · Your photo, speaking

Your photo speaks the script segment by segment, joined into one captioned video of up to two minutes in the photo's shape.

## Who posts with a digital twin

### Founders and owners

Post every week as yourself without booking a shoot.

### Local shops

Gyms, salons, and restaurants tell nearby customers why to drop by, in the owner's voice.

### Knowledge creators

Turn the questions your audience asks into scripts your digital twin answers.

### Creators who skip filming

Your photo and your voice do the talking when there is no time to film.

## Inputs and outputs

| Input or output | Type | Formats | Specifications |
| --- | --- | --- | --- |
| Input | Image — A front-facing photo from the shoulders up | JPG, PNG, WEBP | 1 image per request |
| Input | Audio — Voice sample with one clear speaker | MP3, WAV | 10–300 s; up to 20 MB each |
| Input | Text — Your niche or the topics you want to talk about | — | — |
| Output | Text — Weekly topics, segmented script, titles, hashtags, and cover text | — | editable |
| Output | Video — Captioned talking-head video in your photo's orientation | MP4 | up to 120 s; aspect ratios 9:16, 3:4, 1:1, 16:9 |
| Output | Audio — Narration files | MP3 | — |
| Output | Text — Captions | SRT | — |

Specifications last checked 2026-11-09 · Sources: [Model catalog](https://docs.beatra.ai/en/docs/models) · [Documentation](https://docs.beatra.ai/en/docs/mcp-tools) · [Terms of Service](https://beatra.ai/en/terms)

## Questions

### What do I start with?

Who you are and what you offer. Add dates, the platform, and the length you want if you know them.

### How should I prepare the photo and the recording?

A front-facing photo from the shoulders up in even light, and 10 seconds to 5 minutes of yourself speaking clearly, under 20 MB.

### How long is each video, and what shape?

Up to two minutes, with captions from your script. The video takes your photo's orientation, so a vertical photo makes a vertical video.

## Related Skills

- [Beatra AI Video Studio](https://beatra.ai/en/skills/beatra-ai-video-studio): Make product videos, ad creative, social clips, or b-roll, then check motion and stability before any edit.
- [Class Intro Video Maker](https://beatra.ai/en/skills/class-intro-director): Get the first-person script, storyboard, and class questions, then the portrait, the music, and a short video for your slides.
- [Digital Teacher Lecture Video](https://beatra.ai/en/skills/course-lecturer): Get the script cut into timed segments with board notes, then a talking-avatar teacher presenting it in the teacher's own voice.
- [Course Video Studio](https://beatra.ai/en/skills/course-video-studio): Prepare one teacher voice, then publish a stable presenter clip for each lesson.

[More Video & animation Skills](https://beatra.ai/en/skills/categories/video-animation)
