three.ws Audio

three.ws Audio is a local MCP server: Text-to-speech, speech-to-text, audio-to-face lipsync, and motion-capture clips for 3D agents. Install it from npm as @three-ws/audio-mcp.

Claude CodeCodexAntigravity

commandprompt

Terminal

claude mcp add audio-mcp -e THREE_WS_BASE=... -e THREE_WS_API_KEY=... -e THREE_WS_TIMEOUT_MS=... -- npx -y @three-ws/audio-mcp

Run in your project folder. Add --scope user to use it everywhere.

Add to claude_desktop_config.json or .cursor/mcp.json.

{
  "mcpServers": {
    "audio-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@three-ws/audio-mcp"
      ],
      "env": {
        "THREE_WS_BASE": "...",
        "THREE_WS_API_KEY": "...",
        "THREE_WS_TIMEOUT_MS": "..."
      }
    }
  }
}

Fill in the environment variables with your own credentials.

• Runtime: Node.js 18+ (runs with npx).
• MCP client: Claude Code, Codex, Antigravity, Claude Desktop, Cursor or any other client that speaks MCP over stdio.
• Environment variables: THREE_WS_BASE, THREE_WS_API_KEY, THREE_WS_TIMEOUT_MS