Zonos TTS MCP Linux

🚀 Zonos TTS MCP for Linux

An integration of the Model Context Protocol (MCP) designed for Zonos TTS, allowing Claude to directly generate speech on Linux systems.

🚀 Quick Start

This project enables Claude AI to achieve text-to-speech functionality through Zonos TTS. The integration uses the Model Context Protocol (MCP), allowing Claude to generate natural and fluent speech in multiple languages and emotions.

✨ Features

• Text-to-speech via Claude
• Support for multiple emotions (neutral, happy, sad, angry)
• Multi-language support
• Correct audio playback via PulseAudio/PipeWire
• Compatibility with Linux environments

📦 Installation

Installation via Smithery

To automatically install the unmodified original version of the Zonos TTS integration for Claude Desktop, you can run the following command via Smithery:

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

Manual Installation (for Linux with GPU optimization)

1. Ensure that the Zonos API is running and the API implementation version is deployed (PhialsBasement/zonos-api).

2. Clone this repository:

git clone https://github.com/angrysky56/Zonos-TTS-MCP-Linux.git
cd Zonos-TTS-MCP-Linux

3. Install dependencies:

npm install @modelcontextprotocol/sdk axios zod

4. Build the MCP server:

npm run build

5. Add to the Claude configuration file: Edit your Claude configuration file (search for the file containing "mcpServers", usually located in the user's home directory), and add the following to the mcpServers section:

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

Replace /path/to/your/Zonos-TTS-MCP-Linux with the actual path where the project is installed.

📚 Documentation

Troubleshooting

Error messages in the console

If you encounter an error message like this:

Unexpected token 'P', 'Playing au'... is not valid JSON

This project already includes fixes for these common issues:

1. Redirect console output to stdout for easier debugging when issues occur.
2. Fix the problem of non-terminated audio playback.

More troubleshooting information

Please visit GitHub for the full README file and more detailed information.

Usage Instructions

Claude can be invoked via the following command:

await window.zilASA?.api("tts/speak", {
  text: "Hello World",
  modelId: "your-model-id",
});

Parameter setting examples

• Text: The text content for which you want to generate speech.
• Emotion (optional): Set the emotion of the speech, such as happy, sad, angry, or calm.
• Language (optional): Specify the target language, such as en-US or zh-CN.

More detailed information

Please visit GitHub for the full documentation and more examples.

Project Source

• GitHub - Zonos TTS MCP for Linux

📄 License

The use and distribution of this project are subject to its license agreement.