three.ws Audio MCP Server

Give a 3D AI agent a voice and a face - text-to-speech, speech-to-text, audio-to-face lipsync, and the motion-capture clip library, from any MCP client.

People connecting AI & ML tools to Claude, Cursor, VS Code, or another MCP client. The project is written in JavaScript.

One of 37 MCP servers published from nirholas/three.ws. Stars and repository activity are shared across all of them. See all 37 →

VERIFIED ACTIVE

LAST COMMIT 2026-08-24 · VERIFIED 2026-08-25

Apache-2.0 · JavaScript servers · how we verify → /methodology

01 · Install three.ws Audio

before you install - you'll need

The README does not document required environment variables for a basic install.

Claude Code

claude mcp add nirholas-three.ws-packages-audio-mcp -- npx -y @three-ws/audio-mcp

Claude Desktop / Cursor / VS Code - add to config

{
  "mcpServers": {
    "nirholas-three.ws-packages-audio-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@three-ws/audio-mcp"
      ]
    }
  }
}

Same JSON for Cursor. For VS Code, rename the top-level key from `mcpServers` to `servers`.

Using another client? Same JSON, different key

Claude Desktop · mcpServers

Cursor · mcpServers

VS Code · servers

Windsurf · mcpServers

Zed · context_servers

Cline · mcpServers

Roo Code · mcpServers

Continue · mcpServers

LibreChat · mcpServers

Gemini CLI · mcpServers

Codex CLI · mcp_servers

Full setup guides: every client.

02 · Evidence

Security posture

What to check before giving this server access to your agent - from the registry, GitHub, and our own probes. We don't score safety; we show what's verifiable.

runs as local process (stdio) - runs on your machine with your user's permissions

license Apache-2.0 - declared in the repository

npm package @three-ws/audio-mcp - the @three-ws scope differs from the repo owner (nirholas); confirm it's the project's official package

registry namespace io.github.nirholas is GitHub-verified and matches the repo owner

03 · What three.ws Audio can do

Prose above is summarized from the project's README and registry record - no invented capabilities.

Limitations (from the README)

Audio crosses the wire as base64 (TTS returns it, ASR/A2F accept it). Both the synthesis input (text) and the recognition input (audio, ~8 MB cap) are bounded by the platform - keep clips to a spoken utterance rather than long recordings. For lipsync on audio you already have, pass wav/pcm directly; browser-recorded WebM/Opus must be decoded to WAV or PCM first (Riva and Audio2Face do not accept the WebM container).

04 · Who maintains three.ws Audio

three.ws Audio is maintained by nirholas. We track 66 MCP servers from nirholas - 65 actively maintained, 7,658 combined GitHub stars, oldest repo from Feb 2024. Full record: all servers from nirholas.

05 · Facts

repository: github.com/nirholas/three.ws
website: https://three.ws/
category: AI & ML - actively maintained as of 2026-08-25.
registry: io.github.nirholas/audio-mcp (active, first published 2026-06-24 · 3 versions)
packages: npm:@three-ws/audio-mcp

06 · three.ws Audio FAQ

What is three.ws Audio?

Give a 3D AI agent a voice and a face - text-to-speech, speech-to-text, audio-to-face lipsync, and the motion-capture clip library, from any MCP client.

Is three.ws Audio still maintained?

Yes - as of 2026-08-25, its last commit was 2026-08-24. We re-verify nightly.

How do I install three.ws Audio?

Run `npx -y @three-ws/audio-mcp`. The README does not document required environment variables for a basic install. You can also paste the ready-made client config above.

Does three.ws Audio run locally?

Yes - it's a stdio server: it runs on your machine (via npx) with your user's permissions. Your data stays local unless the server itself calls external APIs.

07 · Alternatives to three.ws Audio

Alternatives to three.ws Audio

Maintained AI & ML servers if three.ws Audio isn't the fit.

Pairs well with

Servers that cover what three.ws Audio doesn't - only shown when the pairing reason fits the companion.

More AI & ML MCP servers · three.ws Autopilot · 3D AI Agent Avatar · three.ws Billing · three.ws Brain · three.ws Coin Clash