MCP Voice Interface

Talk to AI assistants using your voice through a web browser. Compatible with Claude Desktop, OpenCode, and other MCP-enabled AI tools.

Features

🎙️ Voice Conversations - Speak naturally with AI assistants
🌍 30+ Languages - Speech recognition in multiple languages
📱 Remote Access - Use from phone/tablet while AI runs on computer
⚙️ Smart Controls - Collapsible settings, always-on mode, custom voices
⏱️ Dynamic Timeouts - Intelligent wait times based on response length

Easy Installation

🚀 One-Command Setup

Claude Desktop:

npx mcp-voice-interface --install-claude-config
# Restart Claude Desktop and you're ready!

OpenCode (in current project):

npx mcp-voice-interface --install-opencode-config --local
npx mcp-voice-interface --install-opencode-plugin --local
# Start OpenCode and use the converse tool

Claude Code CLI:

npx mcp-voice-interface --install-claude-code-config --local
# Start Claude Code CLI and use voice tools

📦 Manual Installation

From NPM:

npm install -g mcp-voice-interface
mcp-voice-interface

From Source:

git clone <repository-url>
cd mcp-voice-interface
npm install && npm run build && npm start

How to Use

1. Start the server - Run mcp-voice-interface
2. Open browser - Visit https://localhost:5114 (opens automatically)
3. Allow microphone - Grant permissions when prompted
4. Start talking - Use the converse tool in your AI assistant

Voice Commands in AI Chat

Use the converse tool to start talking:
- converse("Hello! How can I help you today?", timeout: 35)

Browser Interface

The web interface provides:

• Voice Settings (click ⚙️ to expand)
  • Language selection (30+ options)
  • Voice selection
  • Speech speed control
  • Always-on microphone mode
• Smart Controls
  • Pause during AI speech (prevents echo)
  • Stop AI when user speaks (natural conversation)
• Mobile Friendly - Works on phones and tablets

Remote Access

Access from any device on your network:

1. Find your computer's IP: ifconfig | grep inet (Mac/Linux) or ipconfig (Windows)
2. Visit https://YOUR_IP:5114 on your phone/browser
3. Accept the security warning (self-signed certificate)
4. Grant microphone permissions

Perfect for continuing conversations away from your desk!

Configuration

Environment Variables

export MCP_VOICE_AUTO_OPEN=false  # Disable auto-opening browser
export MCP_VOICE_HTTPS_PORT=5114  # Change HTTPS port

Ports

• HTTPS: 5114 (required for microphone access)
• HTTP: 5113 (local access only)

Requirements

• Node.js 18+
• Modern browser (Chrome/Safari recommended)
• Microphone access

Troubleshooting

Certificate warnings on mobile?

• Tap "Advanced" → "Proceed to site" to accept self-signed certificate

Microphone not working?

• Ensure you're using HTTPS (not HTTP)
• Check browser permissions
• Try refreshing the page

AI not responding to voice?

• Make sure the converse tool is being used (not just speak)
• Check that timeouts are properly calculated

Development

npm install
npm run build
npm run dev     # Watch mode
npm run start   # Run server

License

MIT