Voicevox MCP Server

by srvhat09

AI/Speech Voicevox Text-to-Speech Speech Synthesis JSON-RPC

This project provides an MCP server that uses the Voicevox Engine to perform speech synthesis and play the results. It offers endpoints that can be called from AI tools like Cursor and Cline, enabling text-to-speech functionality.

View on GitHub

Last updated: N/A

What is Voicevox MCP Server?

Voicevox MCP Server is a server that conforms to the Model Context Protocol (MCP) and utilizes the Voicevox Engine for speech synthesis. It provides a JSON-RPC over stdio interface for interacting with MCP clients.

How to use Voicevox MCP Server?

Clone the repository. 2. Install dependencies using uv sync. 3. Start the Voicevox Engine (either locally or remotely). 4. Configure your MCP client (e.g., CLINE, Roo code) with the server's command and arguments. Refer to the README for specific configuration examples and options.

Key features of Voicevox MCP Server

Text to Audio Query conversion
Audio Query to WAV data conversion
Generated audio data playback
MCP protocol compliant JSON-RPC over stdio interface

Use cases of Voicevox MCP Server

Integrating Voicevox speech synthesis into AI tools like Cursor and Cline
Creating applications that require text-to-speech functionality
Developing interactive voice experiences
Automating voice generation tasks

FAQ from Voicevox MCP Server

What is the default host and port for the Voicevox Engine?

The default host is 127.0.0.1 and the default port is 50021.

What is the default speaker ID?

The default speaker ID is 3. Refer to the provided link in the README for a list of speaker IDs.

How do I install the MCP server in Claude Desktop?

Use the command mcp install src/main.py.

What Python version is required?

Python 3.10 or higher is required.

How do I handle English words being pronounced letter by letter?

You can either create a custom dictionary or convert the words to katakana in the input text.