CodingButter/simple-voice-mcp

Voice MCP Server

A voice-enabled MCP (Model Context Protocol) server built with Bun, React, and ElevenLabs. This server exposes three tools for LLMs to enable voice interaction: speak, listen, and action.

Features

• 🎤 Speech-to-Text: Web Speech API with three modes:

  • Manual: Click to record, click send button
  • PTT (Push-to-Talk): Hold button while speaking, release to send
  • Auto: Automatically sends after 1.5s of silence

• 🔊 Text-to-Speech: ElevenLabs streaming audio

• 💬 Chat Interface: Facebook Messenger-style UI

• 📊 Action Tracking: Collapsible action logs attached to LLM responses

• 🔌 WebSocket: Real-time audio streaming and status updates

• ⚡ MCP Tools: Three tools exposed via stdio transport

Prerequisites

• Bun v1.0.0 or later
• ElevenLabs API Key
• Modern browser with Web Speech API support (Chrome, Edge recommended)

Quick Start with npx

The easiest way to use this MCP server is via npx:

# Install globally
npm install -g voice-mcp

# Or run directly with npx
npx voice-mcp

Then configure in your MCP client (Claude Desktop, Claude Code, etc.):

{
  "mcpServers": {
    "voice-mcp": {
      "command": "npx",
      "args": ["voice-mcp"],
      "env": {
        "ELEVENLABS_API_KEY": "your_api_key_here",
        "MCP_HTTP_PORT": "53245"
      }
    }
  }
}

Open your browser to http://localhost:53245 to access the voice interface!

Installation from Source

# Clone the repository
git clone https://github.com/codingbutter/simple-voice-mcp.git
cd simple-voice-mcp

# Install dependencies
bun install

# Copy environment example
cp .env.example .env

# Edit .env and add your ElevenLabs API key
# ELEVENLABS_API_KEY=your_api_key_here

Development

Start the development server (HTTP/WebSocket + MCP stdio):

# Set your API key
export ELEVENLABS_API_KEY="your_api_key_here"

# Run in development mode with HMR
bun dev

The server will:

• Start an HTTP server on port 3000 (configurable via MCP_HTTP_PORT)
• Serve the React UI at http://localhost:3000
• Listen for MCP requests via stdio

Production

# Build the frontend
bun run build

# Run in production mode
NODE_ENV=production ELEVENLABS_API_KEY="your_key" bun start

MCP Configuration

Claude Code (Automatic)

This project includes a .mcp.json file that automatically configures the server with Claude Code:

1. Add your ElevenLabs API key to .mcp.json:

   {
     "env": {
       "ELEVENLABS_API_KEY": "your_api_key_here"
     }
   }
   

2. Restart Claude Code - The server will auto-start

3. Open browser to http://localhost:53245

The server is configured with autoStart: true, so it starts automatically when Claude Code launches.

Claude Desktop or Other MCP Clients

To use this as an MCP server with Claude Desktop or another MCP client, add this to your MCP configuration:

{
  "mcpServers": {
    "voice-mcp": {
      "command": "bun",
      "args": ["run", "/absolute/path/to/simple-voice-mcp/src/index.tsx"],
      "env": {
        "ELEVENLABS_API_KEY": "your_api_key_here",
        "MCP_HTTP_PORT": "53245",
        "ELEVEN_VOICE_ID": "21m00Tcm4TlvDq8ikWAM",
        "ELEVEN_MODEL_ID": "eleven_flash_v2_5"
      }
    }
  }
}

MCP Tools

The server exposes three tools:

speak(text, listen?, timeout_ms?, voiceId?, modelId?)

Generate and stream text-to-speech audio to connected clients.

Parameters:

• text (string, required): The text to convert to speech
• listen (boolean, optional): If true, wait for user response after speaking
• timeout_ms (number, optional): Timeout when listen=true (default: 60000ms)
• voiceId (string, optional): ElevenLabs voice ID (default: Rachel)
• modelId (string, optional): ElevenLabs model ID (default: eleven_flash_v2_5)

Returns:

• { ok: true, message, messages? } - If listen=true, includes user's messages

listen(timeout_ms?)

Wait for text input from clients (blocks until user sends text or timeout).

Parameters:

• timeout_ms (number, optional): Timeout in milliseconds (default: 60000)

Returns:

• { messages: string[] } - Array of messages (empty if timeout)

action(text)

Send a status or action update to the client UI. Appears as collapsible section.

Parameters:

• text (string, required): The action/status text to display (e.g., "Reading file X", "Running tests")

Returns:

• { ok: true }

Note: Only send concrete actions being performed, not commentary or explanations.

Testing with MCP Inspector

# Install MCP Inspector globally
npm install -g @modelcontextprotocol/inspector

# Test the server
export ELEVENLABS_API_KEY="your_key"
npx @modelcontextprotocol/inspector bun src/index.tsx

Architecture

┌─────────────────────────────────────────┐
│  MCP Client (Claude Desktop, etc.)     │
└───────────────┬─────────────────────────┘
                │ stdio (JSON-RPC)
                │
┌───────────────▼─────────────────────────┐
│  MCP Server (Bun Process)              │
│  ├─ stdio transport                    │
│  ├─ Three tools: speak/listen/action   │
│  └─ HTTP/WebSocket server               │
└───────────────┬─────────────────────────┘
                │ HTTP + WebSocket
                │
┌───────────────▼─────────────────────────┐
│  Browser UI (React)                     │
│  ├─ Chat interface                     │
│  ├─ Web Speech API (STT)               │
│  ├─ Audio playback (TTS)               │
│  └─ WebSocket client                    │
└─────────────────────────────────────────┘

Environment Variables

Project Structure

src/
├── index.tsx              # Main entry point (MCP + HTTP server)
├── App.tsx                # React root component
├── frontend.tsx           # React DOM setup
├── mcp/
│   └── tools.ts          # MCP tool implementations
├── server/
│   ├── http.ts           # HTTP + WebSocket server
│   ├── websocket.ts      # WebSocket manager
│   └── tts.ts            # ElevenLabs TTS manager
├── hooks/
│   ├── useWebSocket.ts   # WebSocket client hook
│   └── useSpeechRecognition.ts  # Web Speech API hook
└── components/
    ├── chat/
    │   ├── ChatInterface.tsx   # Main chat UI
    │   └── ChatMessage.tsx     # Message bubble component
    └── ui/               # shadcn/ui components

Important Notes

• stdio Constraint: The server uses stdout for MCP JSON-RPC. All logging goes to stderr.
• Browser Compatibility: Web Speech API works best in Chrome/Edge
• Multi-Instance: Each MCP server instance needs a unique port (set via MCP_HTTP_PORT)

Documentation

See for detailed technical specifications. See for a quick setup guide.

License

MIT - See for details.

Built With

• Bun - Runtime & bundler
• React 19 - UI framework
• Tailwind CSS v4 - Styling
• shadcn/ui - UI components
• ElevenLabs - Text-to-speech
• Model Context Protocol - MCP SDK