three.ws Audio for VS Code

io.github.nirholas/audio-mcp

Text-to-speech, speech-to-text, audio-to-face lipsync, and motion-capture clips for 3D agents.

client:VS Code transport:stdio runtime:npm

Install three.ws Audio in VS Code

.vscode/mcp.json

{
  "inputs": [
    {
      "type": "promptString",
      "id": "three-ws-base",
      "description": "THREE_WS_BASE",
      "password": true
    },
    {
      "type": "promptString",
      "id": "three-ws-api-key",
      "description": "THREE_WS_API_KEY",
      "password": true
    },
    {
      "type": "promptString",
      "id": "three-ws-timeout-ms",
      "description": "THREE_WS_TIMEOUT_MS",
      "password": true
    }
  ],
  "servers": {
    "audio-mcp": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@three-ws/audio-mcp"
      ],
      "env": {
        "THREE_WS_BASE": "${input:three-ws-base}",
        "THREE_WS_API_KEY": "${input:three-ws-api-key}",
        "THREE_WS_TIMEOUT_MS": "${input:three-ws-timeout-ms}"
      }
    }
  }
}

VS Code prompts for each input the first time the server starts, so no secret is written to the file. VS Code docs

three.ws Audio in other clients

three.ws Audio MCP server