three.ws Audio

local MCP server

Installation

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.

Claude Desktop, Cursor & other clients

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.

Summary

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

Questions

three.ws Audio is a local MCP server distributed as the npm package @three-ws/audio-mcp.

Run: 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: codex mcp add audio-mcp --env THREE_WS_BASE=... --env THREE_WS_API_KEY=... --env THREE_WS_TIMEOUT_MS=... -- npx -y @three-ws/audio-mcp

Similar MCP servers

NameStars

mcp-listenio.github.analyticsinmotion/mcp-listen10
mcp-listenio.github.decibri/mcp-listen10
anymdio.github.SylphxAI/anymd942
elevenlabscom.mcparmory/elevenlabs31
janeeio.github.rsdouglas/janee30
rlhf-feedback-loopio.github.IgorGanapolsky/rlhf-feedback-loop27
cacheoverflowio.github.GetCacheOverflow/cacheoverflow19
mistral-mcpio.github.Swih/mistral-mcp15