Voicevox MCP Server

Name: Voicevox MCP Server
Author: srvhat09

@srvhat09

Repository

About Voicevox MCP Server

docker版 voicevox engine を利用し受け取るメッセージを音声再生するMCP Server

Basic information

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "voicevox_mcp_light": {
      "command": "uv",
      "args": [
        "sync"
      ]
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is Voicevox MCP Server?

Voicevox MCP Server is a Model Context Protocol (MCP) compliant server that uses the Voicevox Engine for speech synthesis. It converts text into audio and plays the result, providing endpoints callable from AI tools such as Cursor and Cline.

How to use Voicevox MCP Server?

Install dependencies with uv sync, start the Voicevox Engine via Docker, then configure the server in your MCP client (e.g., Cline, Roo code) using the provided JSON settings. The server runs as a stdio-based MCP tool and can be invoked with synthesizeAndPlay(message="..."). Optional arguments include --host, --port, and --speaker (default speaker ID is 3).

Key features of Voicevox MCP Server

Converts text to speech audio queries
Converts audio queries to WAV data
Plays generated audio directly
MCP‑compliant JSON‑RPC over stdio interface
Configurable Voicevox Engine host, port, and speaker ID

Use cases of Voicevox MCP Server

Providing spoken responses from AI coding assistants (Cline, Cursor)
Reading aloud text generated by language models
Integrating text‑to‑speech into MCP‑compatible tools
Prototyping voice feedback in development environments

FAQ from Voicevox MCP Server

What are the prerequisites?

Python 3.10 or higher is required, along with a running Voicevox Engine (local or remote). The recommended way to run the engine is via Docker (CPU or GPU image).

How does it handle English text?

By default, English letters are spoken one character at a time. Workarounds include converting the text to katakana before input or using a custom dictionary (custom dictionary creation is not yet implemented).

Which transport protocol does it use?

It uses JSON‑RPC over stdio, which is the standard MCP transport.

Is Claude Desktop supported?

Claude Desktop has not been tested yet.

What is the default speaker ID?

The default speaker ID is 3. It can be changed with the --speaker option; a list of available speaker IDs is referenced from the Voicevox VVM repository.