Zonos TTS

MCP server that allows Claude to have a voice.

typescript

14

GitHub Stars

typescript

Language

4 months ago

First Indexed

3 weeks ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

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

You run a dedicated MCP server that enables Zonos TTS to be used by Claude to generate speech directly. This server handles text input, converts it to audio, and plays it back through your system, with support for multiple languages and emotions.

How to use

After you start the Zonos TTS MCP server, Claude can invoke its speak_response tool to turn text into speech. You can call this tool with the text you want spoken, an optional language (defaults to en-us), and an optional emotion (neutral, happy, sad, angry). Use the tool to generate audio that you then hear through your configured audio output.

Practical usage pattern:

Start the MCP server on a host with Node.js and PulseAudio properly configured.
In Claude, use the speak_response tool to synthesize speech for your desired text.
If you want a particular mood, specify emotion like happy or neutral, and choose the language if needed.

How to install

Prerequisites you need before starting:

Node.js installed
PulseAudio configured for audio playback
Running instance of Zonos API (PhialsBasement/zonos-api) if you plan to integrate directly
Access to a terminal with permissions to install packages and run processes

Step 1 Installing via Smithery
```bash
npx -y @smithery/cli install @PhialsBasement/zonos-tts-mcp --client claude

Step 2 Manual installation
1. Make sure you have Zonos running with our API implementation (PhialsBasement/zonos-api)
2. Install dependencies:
```bash
npm install @modelcontextprotocol/sdk axios

Configure PulseAudio access:

# Your pulse audio should be properly configured for audio playback
# The MCP server will automatically try to connect to your pulse server

Build the MCP server:

npm run build
# This will create the dist folder with the compiled server

Add to Claude's config file by editing your Claude config (usually at ~/.config/claude/config.json) and add this 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. "

## Additional setup notes

Notes to keep in mind:
- Ensure both the Zonos API server and this MCP server are running to enable end-to-end speech generation.
- Audio playback depends on a properly configured PulseAudio setup on your system.
- The MCP server is designed to integrate seamlessly with Claude and provide the speak\_response tool for TTS.

## Available tools

### speak\_response

Generates spoken audio from text input, with optional language and emotion controls for TTS within Claude.