Boyomi-chan MCP Server (Node.js version)
This is a server that uses the Model Context Protocol (MCP) to provide text-to-speech functionality using Bokuyomi-chan (a slow voice) to AI assistants. It is implemented in Node.js/TypeScript.
overview
This server is an MCP server that allows AI assistants such as Claude to use Boyomi-chan.
Related MCP server: 棒読みちゃんMCPサーバー (Node.js版)
function
Text to speech
Select voice type (female, male, etc.)
Volume adjustment
Adjustable speech speed
Pitch Adjustment
Prerequisites
Node.js 16 or higher
npm 7 or higher
Boyomi-chan must be installed.
The HTTP link for Boyomi-chan is running on port 50080.
How to install
Clone this repository:
Install the dependencies:
Which compiles:
How to use
Starting the Server
Integration with Claude for Desktop
To work with Claude for Desktop you need to edit the configuration file:
Open the Claude for Desktop configuration file:
MacOS:
~/Library/Application Support/Claude/claude_desktop_config.jsonWindows:
%APPDATA%\Claude\claude_desktop_config.json
Add the following content (replace the paths with the actual file paths):
Restart Claude for Desktop.
Usage Example
Claude for Desktop will read text aloud to you by:
Read out "Hello, World"
A male voice reads out "This is a test."
Speed up and read "I'm in a hurry"
Parameter Description
Parameters | explanation | Default value | Scope |
text | Read text | Required | Any text |
voice | Audio Type | 0 (1 female) | 0: Female 1, 1: Male 1, 2: Female 2, ... |
volume | volume | -1 (default) | -1: default, 0-100: volume level |
speed | speed | -1 (default) | -1: default, 50-200: speed level |
tone | Pitch | -1 (default) | -1: default, 50-200: pitch level |
license
MIT