Text-to-Speech MCP

Example Use Cases

• 1

  Convert chat or document text into spoken audio for accessibility or voice playback within MCP-compatible clients like Claude Desktop.

• 2

  Programmatically generate and save high-quality speech files (MP3, WAV, OPUS, AAC, FLAC, PCM) for podcasts, notifications, or other automation.

• 3

  A simple local CLI or server to integrate OpenAI TTS voices and settings (voice character, speed, instructions) into workflows or UIs.

Description

tts-mcp provides a Model Context Protocol (MCP) server and command-line tool to generate high-quality text-to-speech audio using OpenAI TTS models. It supports multiple voice characters, configurable speed and formats (MP3, WAV, OPUS, AAC, etc.), and can be integrated into MCP-compatible clients such as Claude Desktop. The project is intended to be easy to run locally (via npx or npm) and configurable via command-line options or environment variables. This enables automated or interactive agents to produce and play speech output or save audio files programmatically.