Zonos TTS MCP

🚀 Zonos TTS Integration with MCP

This is the Model Context Protocol (MCP) integration implemented for Zonos TTS, which allows Claude to directly generate speech.

🚀 Quick Start

This integration enables Claude to generate speech directly. After configuration, you can use the speak_response tool to convert text into speech.

📦 Installation

Installation via Smithery

To automatically install the Zonos TTS integration via Smithery:

npx -y @smithery/cli install @PhialsBasement/zonos-tts-mcp --client claude

Manual Installation

1. Ensure that the Zonos server is running and has our API implementation (PhialsBasement/zonos-api).
2. Install dependencies:

npm install @modelcontextprotocol/sdk axios

3. Configure PulseAudio access:

# Ensure that your Pulse Audio is correctly configured to support audio playback.
# The MCP server will automatically attempt to connect to your Pulse server.

4. Build the MCP server:

npm run build
# This will create the compiled server files in the dist folder.

5. Add to Claude's configuration file: Edit your Claude configuration file (usually located at ~/.config/claude/config.json) and add the following to the mcpServers section:

"zonos-tts": {
  "command": "node",
  "args": [
    "/path/to/your/zonos-mcp/dist/server.js"
  ]
}

Replace /path/to/your/zonos-mcp with the actual path where you installed the MCP server.

💻 Usage Examples

Basic Usage

After configuration, Claude will automatically know how to use the speak_response tool:

speak_response(
    text="Your text here",
    language="en-us",  # Optional, default is en-us
    emotion="happy"    # Optional: "neutral", "happy", "sad", "angry"
)

✨ Features

• Text-to-speech (TTS) via Claude
• Support for multiple emotions
• Support for multiple languages
• Correct audio playback via PulseAudio

📚 Documentation

Requirements

• Node.js environment
• PulseAudio configuration
• A running Zonos API instance (PhialsBasement/zonos-api)
• A working audio output device

Notes

⚠️ Important Note

Ensure that both the Zonos API server and this MCP server are running. Audio playback requires correct PulseAudio configuration.