
Three.Ws Audio
- 89 repo stars
- Updated July 28, 2026
- nirholas/three.ws
Adds text-to-speech, speech-to-text, audio-to-face lipsync, and motion-capture clips so a builder can give a 3D agent a voice and animated face.
About
three.ws Audio is an MCP server that gives a 3D agent voice and animation: text-to-speech, speech-to-text, audio-to-face lipsync, and motion-capture clips, all backed by real upstream model calls. It works anonymously on a public surface, and an optional API key raises rate limits and unlocks your private motion-capture clips. A solo builder reaches for it to voice and animate an avatar without stitching together separate speech and animation providers.
- TTS and STT via real upstream models
- Audio-to-face lipsync
- Motion-capture clips for 3D agents
- Optional key raises rate limits + unlocks private clips
Three.Ws Audio by the numbers
- Data as of Jul 28, 2026 (Skillselion catalog sync)
claude mcp add --env THREE_WS_BASE=YOUR_THREE_WS_BASE --env THREE_WS_API_KEY=YOUR_THREE_WS_API_KEY --env THREE_WS_TIMEOUT_MS=YOUR_THREE_WS_TIMEOUT_MS audio-mcp -- npx -y @three-ws/audio-mcpAdd your badge
Show developers this MCP server is listed on Skillselion. Paste this into your README.
| repo stars | ★ 89 |
|---|---|
| Package | @three-ws/audio-mcp |
| Transport | STDIO |
| Auth | Required |
| Last updated | July 28, 2026 |
| Repository | nirholas/three.ws ↗ |
What it does
Adds text-to-speech, speech-to-text, audio-to-face lipsync, and motion-capture clips so a builder can give a 3D agent a voice and animated face.
Who is it for?
voicing and animating 3D avatars
Skip if: text-only agents
What you get
- synthesized speech
- transcripts
- lipsync + mocap clips