Rime MCP

🚀 Rime MCP Context Model Protocol (MCP) Server

The Rime MCP Context Model Protocol (MCP) server uses the Rime API to provide text-to-speech functionality and plays the output through the system's native audio player.

✨ Features

• Exposes a speak utility to convert text to speech and output it via the system's audio device.
• Utilizes Rime's high-quality text-to-speech synthesis API.

📦 Dependencies

• Node.js 16.x or higher
• A working audio output device
• macOS: Use afplay
• Here are sample codes provided by Claude (untested):
  • 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="<Instructions on how to use the speak utility>"
      RIME_WHO_TO_ADDRESS="<Name of the person to address>"
      RIME_WHEN_TO_SPEAK="<Instructions on when the agent should start speaking>"
      RIME_VOICE="cove" 
  }
}

All optional environment variables are part of the tool's definition and are used for prompting.

All voice options can be found here.

You can obtain your API key on the Rime dashboard.

The following environment variables can be used to customize behavior:

• RIME_GUIDANCE: Instructions mainly describing when and where to use the speak utility.
• RIME_WHO_TO_ADDRESS: The person to address (default is "user").
• RIME_WHEN_TO_SPEAK: Indicates when the agent should start speaking (default is "When asked to speak or when a command is completed").
• RIME_VOICE: The default voice to use (default is "cove").

💻 Usage Examples

[基础用法/Basic Usage]

Example 1: Announcement function of the coding agent

"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: Learning how kids speak

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: Switching languages based on context

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

🚧 Development

1. Install dependencies:

npm install

2. Build the server:

npm run build

3. Run in development mode (with hot reloading):

npm run dev

📄 License

MIT