Talking Avatar Video Skill

👉 See also Multilingual Voiceover Skill

Turn one portrait and a short script into a talking avatar video, from inside Claude Code, Cursor, Codex, Windsurf, Cline, or OpenClaw.

Important

Rendering needs a Beatra account and uses credits. The skill itself is free to install.

Question	Answer
What it does	Turn one portrait and a short script or speech track into a directed talking-avatar video for explainers, announcements, lessons, and product messages.
Models	MiniMax Speech 2.8 HD, MiniMax Speech 2.8 Turbo, Wan 2.7, Wan 3.0 Video, MiniMax H3, Seedance 2.0 Mini, HappyHorse 1.1, Seedance 2.0 Fast, Seedance 2.0, Wan 3.0 Video Prime, Seedance 2.5
Requirements	Python 3.10+ and an agent that loads `SKILL.md`
Cost	Free to install. Each render uses credits on your Beatra account, and paid steps run only when you ask for that exact render or approve its card.
Works with	Claude Code, Cursor, Codex, Windsurf, Cline, OpenClaw

A fictional presenter portrait (left) and a frame from the talking-avatar clip it became (right), driven by a short synthesized English line. AI-generated with Beatra.

Skill	Entry point	Version
`talking-avatar-video`	SKILL.md	0.3.4

This repository is published automatically from beatra-ai/beatra-skills. Report issues there.

Install

With the skills CLI:

npx skills add beatra-ai/talking-avatar-video-skill

As a Claude Code plugin:

claude plugin marketplace add beatra-ai/talking-avatar-video-skill
claude plugin install talking-avatar-video@talking-avatar-video-skill

As a Codex plugin:

codex plugin marketplace add beatra-ai/talking-avatar-video-skill
codex plugin add talking-avatar-video@talking-avatar-video-skill

As a GitHub Copilot CLI plugin:

copilot plugin marketplace add beatra-ai/talking-avatar-video-skill
copilot plugin install talking-avatar-video@talking-avatar-video-skill

As a Gemini CLI extension:

gemini extensions install https://github.com/beatra-ai/talking-avatar-video-skill

With the GitHub CLI:

gh skill install beatra-ai/talking-avatar-video-skill talking-avatar-video

Or clone this repository and copy skills/talking-avatar-video into ~/.claude/skills/ for Claude Code, ~/.cursor/skills/ for Cursor, ~/.agents/skills/ for Codex, ~/.codeium/windsurf/skills/ for Windsurf, ~/.cline/skills/ for Cline, or ~/.openclaw/skills/ for OpenClaw.

Or paste this into your agent:

Install the talking-avatar-video skill from https://github.com/beatra-ai/talking-avatar-video-skill (folder skills/talking-avatar-video), then follow its SKILL.md to connect my Beatra account.

Examples

▶ Watch the full video (MP4)

Full talking-avatar clip with voice: a fictional product educator says "Hi! In thirty seconds, I'll show you how our new planner app saves your mornings." AI-generated with Beatra.

Ask your agent:

Use ./presenter.jpg as the presenter and have her say this line to camera in a warm, natural voice: "Hi! In thirty seconds, I'll show you how our new planner app saves your mornings." Keep the shot steady and the expression friendly.

Prompt:

A friendly presenter speaks directly to camera with a warm, natural delivery: steady eye line into the lens, restrained friendly expression, subtle natural head movement and occasional blinks, relaxed shoulders. Locked-off stable camera, plain studio background stays unchanged, same face, hair and green sweater throughout.

Technical Specifications & Output Limits

As of 2026-10-18. Live list: https://docs.beatra.ai/en/docs/models

Uploads — up to 100 MB per file; the per-model input limits below also apply
Text to speech — 2 models (MiniMax Speech 2.8 HD, MiniMax Speech 2.8 Turbo); FLAC, MP3, OPUS, PCM, WAV; 40 languages; sample rates 8, 16, 22.05, 24, 32, 44.1 kHz; up to 50000 characters per request
- Languages (ISO 639 codes): zh, yue, en, es, fr, ru, de, pt, ar, it, ja, ko, id, vi, tr, nl, uk, th, pl, ro, el, cs, fi, hi, bg, da, he, ms, fa, sk, sv, hr, fil, hu, no, sl, ca, nn, ta, af
Image to video — 9 models (Wan 2.7, Wan 3.0 Video, MiniMax H3, Seedance 2.0 Mini, HappyHorse 1.1, Seedance 2.0 Fast, Seedance 2.0, Wan 3.0 Video Prime, Seedance 2.5); 480p to 4K; 2–30 s; aspect ratios 16:9, 1:1, 21:9, 3:4, 4:3, 9:16; MOV, MP4
- 4K: Seedance 2.0, up to 15 s
- 30 s: Wan 3.0 Video, Wan 3.0 Video Prime, Seedance 2.5, up to 1080p
- Native audio: Wan 2.7, MiniMax H3

Why use Beatra instead of calling model APIs directly

One account for every model this skill uses — Text to speech 2; Image to video 9 (MiniMax Speech 2.8 HD, MiniMax Speech 2.8 Turbo, Wan 2.7, Wan 3.0 Video, MiniMax H3, Seedance 2.0 Mini, HappyHorse 1.1, Seedance 2.0 Fast, Seedance 2.0, Wan 3.0 Video Prime, Seedance 2.5) (as of 2026-10-18), behind one Beatra sign-in; no keys from individual model providers to manage.
You decide what gets paid for — Paid renders run only when you ask for that exact render or approve its card, which shows the live credit estimate.
Direction before rendering — the skill plans, directs, and reviews the work, then renders it on Beatra.
Files you can verify — every file under skills/ matches the release archive on cdn.beatra.ai byte for byte, checked by SHA-256 before each push.
Updates you control — no self-updater; update with the tool you installed it with.
Runs in your agent — Claude Code, Cursor, Codex, Windsurf, Cline, OpenClaw.

What you get

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.

Use cases

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.

FAQ

What do I need to start?

One portrait and either a supplied speech track or a short script plus a voice choice.

Can I use my own recorded audio?

Yes, when its type and length fit a currently supported video route.

How are lip sync and presenter consistency reviewed?

The speech drives facial motion, and the finished clip is reviewed for mouth timing, identity, voice clarity, and motion stability before choosing the most useful adjustment.

Updates and security

Since the 2026-10 release, this skill contains no self-updater: it runs only the files you installed and never replaces them on its own. Update it with the tool you installed it with — npx skills update talking-avatar-video or gh skill update talking-avatar-video. Details: references/updates-and-security.md inside the skill.

License

MIT-0 — free to use, modify, and redistribute, including commercially. No attribution required. Same terms as these skills carry on ClawHub.