📌Overview

Purpose: To integrate a Model Context Protocol for Zonos TTS, enabling Claude to generate speech directly.

Overview: The Zonos MCP Integration is designed to facilitate text-to-speech functionality through Claude by utilizing the Model Context Protocol, allowing for nuanced speech output with multi-language and emotional expression capabilities.

Key Features:

Text-to-Speech Functionality: Enables Claude to convert written text into spoken audio, enhancing its interactivity.
Emotional Expression Support: Allows for the selection of various emotional tones (e.g., happy, sad, angry) to enrich user experience.
Multi-Language Capability: Supports text-to-speech in multiple languages, broadening accessibility for diverse users.
PulseAudio Compatibility: Ensures proper audio playback through PulseAudio, providing reliable sound output.

Zonos MCP Integration

A Model Context Protocol integration for Zonos TTS, allowing Claude to generate speech directly.

Setup

Installing via Smithery

To install Zonos TTS Integration for Claude Desktop automatically via Smithery:

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

Manual Installation

Make sure you have Zonos running with the API implementation (PhialsBasement/zonos-api).
Install dependencies:

npm install @modelcontextprotocol/sdk axios

Configure PulseAudio access:

Ensure your PulseAudio is properly configured for audio playback. The MCP server will automatically try to connect to your PulseAudio server.

Build the MCP server:

npm run build

This will create the dist folder with the compiled server.

Add to Claude's config file:

Edit your Claude config file (usually in ~/.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.

Using with Claude

Once configured, Claude automatically knows how to use the speak_response tool:

speak_response(
    text="Your text here",
    language="en-us",  # optional, defaults to en-us
    emotion="happy"    # optional: "neutral", "happy", "sad", "angry"
)

Features

Text-to-speech through Claude
Multiple emotions support
Multi-language support
Proper audio playback through PulseAudio

Requirements

Node.js
PulseAudio setup
Running instance of Zonos API (PhialsBasement/zonos-api)
Working audio output device

Notes

Make sure both the Zonos API server and this MCP server are running.
Audio playback requires proper PulseAudio configuration.

Zonos-TTS-MCP