Rime Text-to-Speech
Text-to-speech server that converts text into spoken audio through Rime's API, streaming with optimized buffering for minimal late
A text-to-speech server for the MCP ecosystem that integrates with Rime's API to convert text into spoken audio. This implementation streams audio content with optimized buffering to reduce latency between text generation and speech playback. It provides a 'speak' tool that can be configured through environment variables to control voice selection, speaking style, and playback behavior. Built with TypeScript and Node.js, it supports cross-platform audio playback through various media players and includes features for handling WebSocket connections and managing temporary audio files. Particularly useful for AI assistants that need to communicate verbally with users or for applications requiring audio narration of generated content.
Source
Repository: https://github.com/matthewdailey/rime-mcp
Maintain Rime Text-to-Speech?
Let people know it's listed here — add the badge (live metrics, light/dark aware) or a plain link to your README or docs.
[Rime Text-to-Speech on getagentictools](https://getagentictools.com/mcp/matthewdailey-rime-mcp?ref=badge)