MCPs tagged with # audio-processing

Speech.sh provides robust text-to-speech capabilities from the command line by leveraging OpenAI's API and offers Model Context Protocol (MCP) compatibility for integration with AI assistants. Supporting multiple voice options, adjustable speech speed, and both tts-1 and tts-1-hd models, it ensures seamless audio conversion and playback. Flexible API key management, auto-caching, and reliable retry logic make it suitable for diverse environments. Additional features include security-focused processing, dependency validation, and compatibility with both ffmpeg and mplayer audio players.

• ⭐ 5
• MCP
• j3k0/speech.sh