Gen Avatar — Development skill for Claude Code
Generate a talking-avatar (lip-sync) video from an image + speech audio.
How to install Gen Avatar
Installs to ~/.claude/skills/sherifbutt-claude-image-tts-gen-gen-avatar/SKILL.md
mkdir -p ~/.claude/skills/sherifbutt-claude-image-tts-gen-gen-avatar && curl -fsSL https://raw.githubusercontent.com/sherifButt/claude-image-tts-gen/HEAD/commands/gen-avatar.md -o ~/.claude/skills/sherifbutt-claude-image-tts-gen-gen-avatar/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Gen Avatar does
description: Generate a talking-avatar (lip-sync) video from an image + speech audio argument-hint: --image face.png --audio voice.mp3 [--tier draft|low|normal|high|ultra] allowed-tools:
- mcp__claude-image-tts-gen__generate_avatar
- mcp__claude-image-tts-gen__generate_image
- mcp__claude-image-tts-gen__generate_speech
- mcp__claude-image-tts-gen__estimate_cost
- mcp__claude-image-tts-gen__regenerate
Generate a talking-avatar (lip-sync) video: $ARGUMENTS
Use the `generate_ava
Alternatives in Development
- Speech — Generate spoken audio from text using OpenAI's API with built-in voices 14.6k ★
- Media — Understand an audio / video / image file — Antigravity (agy/Gemini) transcribes and analyzes it, returning a t 284 ★
- Mesh Avatar Studio — Turn one illustration into an animated 2D mesh avatar with a coding agent and a local editor 112 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Gen Gallery
Build a self-contained HTML gallery of all generated media (image/audio/video)
Kinetic Multicam
Claude Code skill: turn one talking-head take into a kinetic supers + camera whips prompt for Seedance 2.0 Fas
Talking Head Video
Turn a 口播/talking-head video + script into a polished vertical explainer — synced subtitles, animated Remotion
Gen Speech
Generate speech audio (TTS) with sensible voice + tier
Video Lipsync Template
Template — prompt para Kling 3.0 (lip-sync)
05 Master Audio
Apply broadcast-ready audio mastering chain to video files using ffmpeg for clear, warm talking-head sound
Related Agents
Video Factory
Full video production pipeline: trends → script → avatar → b-roll → audio → subtitles → YouTube. One prompt to
Dialogue Naturalness Reviewer
Seventh of book-forge's QA reviewers. Asks whether dialogue sounds like people talking rather than like a mode
Voice Engineer
GAIA voice interaction specialist. Use PROACTIVELY for Whisper ASR, Kokoro TTS, the Talk SDK, speech-to-speech