Rime MCP

A Model Context Protocol (MCP) server that provides text-to-speech capabilities using the Rime API. This server downloads audio and plays it using the system's native audio player.

Features

Exposes a speak tool that converts text to speech and plays it through system audio
Uses Rime's high-quality voice synthesis API

Requirements

Node.js 16.x or higher
A working audio output device
macOS: Uses afplay

There's sample code from Claude for the following that is not tested 🤙✨

Windows: Built-in Media.SoundPlayer (PowerShell)
Linux: mpg123, mplayer, aplay, or ffplay

MCP Configuration

"ref": {
  "command": "npx",
  "args": ["rime-mcp"],
  "env": {
      RIME_API_KEY=your_api_key_here

      # Optional configuration
      RIME_GUIDANCE="<guide how the agent speaks>"
      RIME_WHO_TO_ADDRESS="<your name>"
      RIME_WHEN_TO_SPEAK="<tell the agent when to speak>"
      RIME_VOICE="cove" 
  }
}

All of the optional env vars are part of the tool definition and are prompts to

All voice options are listed here.

You can get your API key from the Rime Dashboard.

The following environment variables can be used to customize the behavior:

RIME_GUIDANCE: The main description of when and how to use the speak tool
RIME_WHO_TO_ADDRESS: Who the speech should address (default: "user")
RIME_WHEN_TO_SPEAK: When the tool should be used (default: "when asked to speak or when finishing a command")
RIME_VOICE: The default voice to use (default: "cove")

Example use cases

Example 1: Coding agent announcements

"RIME_WHEN_TO_SPEAK": "Always conclude your answers by speaking.",
"RIME_GUIDANCE": "Give a brief overview of the answer. If any files were edited, list them."

Example 2: Learn how the kids talk these days

RIME_GUIDANCE="Use phrases and slang common among Gen Alpha."
RIME_WHO_TO_ADDRESS="Matt"
RIME_WHEN_TO_SPEAK="when asked to speak"

Example 3: Different languages based on context

RIME_VOICE="use 'cove' when talking about Typescript and 'antoine' when talking about Python"

Development

Install dependencies:

npm install

Build the server:

npm run build

Run in development mode with hot reload:

npm run dev

License

MIT

Badges

Installing via Smithery

To install Rime Text-to-Speech Server for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install @MatthewDailey/rime-mcp --client claude

MCP Configuration

"ref": { "command": "npx", "args": ["rime-mcp"], "env": { RIME_API_KEY=your_api_key_here # Optional configuration RIME_GUIDANCE="<guide how the agent speaks>" RIME_WHO_TO_ADDRESS="<your name>" RIME_WHEN_TO_SPEAK="<tell the agent when to speak>" RIME_VOICE="cove" } }

All of the optional env vars are part of the tool definition and are prompts to

All voice options are listed here.

You can get your API key from the Rime Dashboard.

The following environment variables can be used to customize the behavior:

RIME_GUIDANCE: The main description of when and how to use the speak tool

RIME_WHO_TO_ADDRESS: Who the speech should address (default: "user")

RIME_WHEN_TO_SPEAK: When the tool should be used (default: "when asked to speak or when finishing a command")

RIME_VOICE: The default voice to use (default: "cove")

Example use cases

Example 1: Coding agent announcements

"RIME_WHEN_TO_SPEAK": "Always conclude your answers by speaking.", "RIME_GUIDANCE": "Give a brief overview of the answer. If any files were edited, list them."

Example 2: Learn how the kids talk these days

RIME_GUIDANCE="Use phrases and slang common among Gen Alpha." RIME_WHO_TO_ADDRESS="Matt" RIME_WHEN_TO_SPEAK="when asked to speak"

Example 3: Different languages based on context

RIME_VOICE="use 'cove' when talking about Typescript and 'antoine' when talking about Python"