# @three-ws/audio-mcp

> Give 3D AI agents a voice and a face from any MCP client — text-to-speech, speech-to-text, audio-to-face lipsync (ARKit blendshapes), and the motion-capture clip library. Read-only over the live three.ws API; free NVIDIA lanes, no key required.

@three-ws/audio-mcp is a Model Context Protocol server from three.ws. Install: `npx -y @three-ws/audio-mcp`.

## Docs

- [README](https://github.com/nirholas/audio-mcp/blob/main/README.md): install, configuration, full reference
- [Documentation site](https://nirholas.github.io/audio-mcp/): the README as a web page
- [Full text for LLMs](https://nirholas.github.io/audio-mcp/llms-full.txt): README inlined
- [AGENTS.md](https://github.com/nirholas/audio-mcp/blob/main/AGENTS.md): guidance for coding agents

## Project

- [Source](https://github.com/nirholas/audio-mcp)
- [npm](https://www.npmjs.com/package/@three-ws/audio-mcp)
- [three.ws](https://three.ws): the platform this is part of
- [Issues](https://github.com/nirholas/audio-mcp/issues)
- [MCP Registry](https://registry.modelcontextprotocol.io/?q=io.github.nirholas%2Faudio-mcp)