Rime
CreatedMatthewDailey
Enables text-to-speech capabilities using the Rime API, playing audio through the system's native audio player.
About
This server acts as a Model Context Protocol (MCP) endpoint, providing text-to-speech functionality through the Rime API. It downloads generated audio and plays it using the system's audio output. Customize voice characteristics, dictate when and how the agent speaks, and even specify different languages based on context. Ideal for coding agent announcements or simply adding a voice to your applications.
Key Features
- 4 GitHub stars
- Uses high-quality voice synthesis from Rime
- Plays audio through the system's native audio player
- Allows customization of voice, guidance, and speaking behavior via environment variables
- Converts text to speech using the Rime API
- Supports different languages based on context
Use Cases
- Coding agent announcements
- Adding spoken feedback to applications
- Customizing voice and language for different contexts
