Rime MCP
by MatthewDailey
Rime MCP is a Model Context Protocol server that provides text-to-speech capabilities using the Rime API. It downloads audio and plays it using the system's native audio player.
Last updated: N/A
What is Rime MCP?
Rime MCP is a server that converts text to speech using the Rime API and plays the audio through the system's audio output.
How to use Rime MCP?
Configure the MCP with the provided JSON snippet, including your Rime API key and optional guidance, address, speaking conditions, and voice preferences as environment variables. Use the speak tool to convert text to speech.
Key features of Rime MCP
Exposes a
speaktool for text-to-speech conversionUses Rime's high-quality voice synthesis API
Configurable voice, guidance, and speaking conditions
Supports macOS, Windows, and Linux (with varying audio players)
Use cases of Rime MCP
Coding agent announcements
Simulating different speaking styles (e.g., Gen Alpha slang)
Using different languages based on context
Providing audio feedback for user interactions
FAQ from Rime MCP
Where do I get my Rime API key?
Where do I get my Rime API key?
You can get your API key from the Rime Dashboard: https://rime.ai/dashboard/tokens.
What are the voice options?
What are the voice options?
All voice options are listed here: https://users.rime.ai/data/voices/all-v2.json.
What environment variables can I use to customize the behavior?
What environment variables can I use to customize the behavior?
You can use RIME_GUIDANCE, RIME_WHO_TO_ADDRESS, RIME_WHEN_TO_SPEAK, and RIME_VOICE.
What audio players are used on different operating systems?
What audio players are used on different operating systems?
macOS uses afplay. Windows uses Built-in Media.SoundPlayer (PowerShell). Linux uses mpg123, mplayer, aplay, or ffplay.
How do I run the server in development mode?
How do I run the server in development mode?
Run npm install, npm run build, and then npm run dev.