Skip to main content
affpapa.org
RU EN
skill CX Codex

ai-avatar-video · 101-skills — Claude Code skill: talking-head video

A skill for making AI avatar and talking-head videos through the inference.sh CLI. Useful for presenter clips, UGC ads and dubbing.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓ 
npx skills add 101-skills/superpowers --skill ai-avatar-video -a claude-code
Open on GitHub

What ai-avatar-video does

The skill documents the belt CLI from inference.sh: turning a portrait plus a text script into an avatar video, syncing lips to an existing audio track, dubbing footage into another language. It ships as a set of commands and parameters covering several models. The recommended one is pruna/p-video-avatar, which handles speech synthesis itself, offers 30 voices across 10 languages and supports 1080p. Other options are bytedance/omnihuman-1-5 for scenes with several people, falai/fabric-1-0 and falai/pixverse-lipsync.

Models without built-in TTS — OmniHuman and PixVerse — need speech generated as a separate step, using inworld/text-to-speech-2, ElevenLabs or infsh/kokoro-tts. Dubbing takes a longer chain: transcribe with infsh/fast-whisper-large-v3, translate, synthesize the new voice, then sync lips with infsh/latentsync-1-6. The portrait itself can come from pruna/p-image at whatever aspect ratio you need.

You have to log in before anything runs: belt login. Without that, belt app run calls go nowhere. The skill is scoped to Bash(belt *), so the agent drives the CLI directly rather than through a separate API client.

What it helps with

  • turn a headshot and a script into a talking avatar clip
  • dub a video into another language with matching lips
  • generate a presenter portrait and animate it in one go
  • produce a first-person UGC-style ad
  • swap the audio in existing footage while keeping facial motion

Example prompts for the agent

  • Create a talking avatar video from portrait.jpg with the line "Hi, this is our product demo"
  • Dub this clip into English and sync the lips with infsh/latentsync-1-6
  • Generate a UGC-style portrait with pruna/p-image and animate it speaking in first person

How to install ai-avatar-video

1Skills CLI (Vercel)

npx skills add 101-skills/superpowers --skill ai-avatar-video -a claude-code

2Manually: put the files in place

~/.claude/skills/ai-avatar-video/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/ai-avatar-video/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about ai-avatar-video

How do I install ai-avatar-video in Claude Code?

Run npx skills add 101-skills/superpowers --skill ai-avatar-video -a claude-code. The skill lands at ~/.claude/skills/ai-avatar-video/SKILL.md.

What does ai-avatar-video do?

It covers avatar video generation through the belt CLI: portrait plus script to avatar, lipsync from audio, and dubbing. It includes commands for several models and step chains for TTS.

Do I need an API key to use the skill?

You need to authenticate first with belt login. Model runs through belt app run will not work without it.

Similar skills

Everything for AI and ML →

ai-avatar-video by other authors comes first.

ai-avatar-video prime-skills Generates AI avatar and lip-sync videos via the RunComfy CLI. Routes requests across OmniHuman, Wan 2-7, HappyHorse, and Seedance v2 based on your task. CX Codex +1 379,900installs skill-creator official anthropics Creates and refines skills, then tests them with prompts, evaluations, and performance checks. 414,180installs writing-for-agents Matt Pocock Guidance for writing skills and agent-facing documents. Use it when editing AGENTS.md, CLAUDE.md, or reference files reached from them. 466,719installs media-use heygen-com Finds or generates media for HyperFrames videos, including voiceovers, music, cutouts, and color grades. Stores files locally in assets. CX Codex +1 1,100,000installs mcp-builder official anthropics This skill walks through building an MCP server in TypeScript or Python, from reading the protocol spec to writing tests and evaluation questions. 130,949installs subagent-driven-development Jesse Vincent This skill runs an implementation plan through fresh subagents for independent tasks and reviews each result. Use it for multi-step work in one session. CX Codex 237,746installs orchestration stablyai Coordinates supervised Orca workers with task DAGs, decision gates, and threaded messages. Fits workflows that split work across multiple agents. CX Codex +1 349,800installs

From the same set22

ai-video-generation Generate videos with Google Veo, Seedance, HappyHorse and 40+ models directly in your editor. Supports text-to-video, image animation, lipsync and audio generation. CX Codex +1 872,100installs ai-image-generation Generates and edits images through belt with selectable models. Use it for illustrations, mockups, and changes to existing images. CX Codex +1 870,900installs twitter-automation Automates Twitter and X interactions through the belt command-line interface. It posts content, manages direct messages, tracks profiles, and handles likes. CX Codex +1 870,600installs agent-browser This skill hands your agent a browser: open pages, click elements, fill forms, grab screenshots and record video. Useful for scraping and UI testing. CX Codex +1 162,800installs web-search This skill gives your agent web search and content extraction through Tavily and Exa. Useful for research, fact-checking and RAG pipelines. CX Codex +1 110,000installs python-executor Runs Python 3.10 scripts inside an isolated inference.sh sandbox. Helpful when your agent needs to crunch data, scrape websites, or render graphics without touching your local system. CX Codex +1 109,700installs remotion-render This skill sends a Remotion React component to inference.sh and gets back an MP4. Useful when video should come from code, not from a timeline editor. CX Codex +1 109,700installs landing-page-design Guides landing page work around the hero, CTA and social proof. Use it when shaping a product or marketing page and its visual direction. CX Codex +1 56,100installs

Project sponsors

Companies that keep this analytics open
Gold sponsor
Nutra.Club

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor