Speech.sh is a command-line interface (CLI) tool and Model Context Protocol (MCP) server for converting text to speech using the Groq TTS API, which is OpenAI-compatible. It offers multiple voice options, adjustable speech speed, caching for efficient API usage, retry mechanisms, and audio playback via popular media players. The tool is ideal for developers, tinkerers, or AI integrators seeking simple, open-source TTS capabilities from the command line or as an MCP integration for AI assistants such as Claude Desktop or Claude Code.
Visit Speech.sh's official website for product details and getting started.
Comprehensive guide on installing, configuring, and using Speech.sh with examples.
Community forum for troubleshooting, feature requests, and general discussions about Speech.sh.
Showcases various use cases and examples of how to utilize Speech.sh effectively.