j3k0/speech.sh

@j3k0

This MCP (Model Context Protocol) server provides text-to-speech capabilities through OpenAI's API. It allows AI assistants and other applications to convert text into spoken audio.

text-to-speech

openai

zsh

Speech MCP Server

Provides text-to-speech capabilities via OpenAI's API for AI assistants and applications.

Installation

Install dependencies: zsh, jq, curl, ffmpeg/mplayer, and speech.sh.
Make scripts executable: chmod +x mcp.sh speech.sh launch.
Set OpenAI API key: export OPENAI_API_KEY="your-key".

Usage

Start the server with ./launch or ./mcp.sh. Use JSON-RPC requests to call the speak method with a text parameter.

Configuration

Use environment variables like SPEECH_VOICE, SPEECH_SPEED, SPEECH_MODEL to customize.

Notes

Speech plays immediately through system speakers.
Logs are stored in logs.txt and speech_logs.txt.

Transport:

stdio

streamable

Language:

Updated: 8/3/2025

Homepage:

https://github.com/j3k0/speech.sh/blob/main/MCP_README.md

Recommend MCP Servers 💡

jvm-mcp-server

xzq-xu

This is an implementation project of a JVM-based MCP (Model Context Protocol) server. The project aims to provide a standardized MCP server implementation for the JVM platform, enabling AI models to better interact with the Java ecosystem.

2025-03-10

ffmpeg-mcp

video-creator

Using ffmpeg command line to achieve an mcp server, can be very convenient, through the dialogue to achieve the local video search, tailoring, stitching, playback,clip, overlay, concat and other functions

2025-03-25