This MCP server implementation provides text-to-speech capabilities using the Kokoro TTS engine. It exposes a single tool for generating speech from text, with options for customizing voice, speed, and output format. The server supports cross-platform audio playback and can save generated audio to files, making it useful for applications requiring high-quality speech synthesis.
No reviews yet. Be the first to review!
Sign in to join the conversation
Highlight AIConvert text to speech. Parameters: text (required), voice (optional, default: 'af_heart'), speed (optional, default: 1.0), save_path (optional), play_audio (optional, default: False)
