{"slug":"drakulavich/kesha-voice-kit","name":"kesha-voice-kit","description":"Local-first voice toolkit: STT (25 langs, ~19x faster than Whisper on Apple Silicon via CoreML, ONNX fallback), TTS (Kokoro + Vosk-TTS + 180 macOS voices, SSML), VAD, language detection (107 langs). Rust engine, OpenClaw skill. No cloud, no API keys.","category":"other","tags":[],"official":false,"stars":38,"transport":"stdio","install":null,"tools":[{"name":"kesha","description":"Transcribe audio files to text with support for multiple formats (plain text, transcript, JSON, TOON), language detection, timestamps, and speaker diarization."},{"name":"kesha say","description":"Convert text to speech and output audio in WAV, OGG/Opus, or FLAC format. Supports English (Kokoro) and Russian (Vosk-TTS) with auto-language routing."},{"name":"kesha install","description":"Download and install engine models, including optional components like VAD, TTS, and diarization models."},{"name":"kesha status","description":"Show installed backend information for the speech-to-text engine."}],"env_vars":[],"auth_type":"none","github":"https://github.com/drakulavich/kesha-voice-kit","homepage":"","server_url":"","status":"active","source":"mcpservers.org","updated_at":"Thu May 28"}