kesha-voice-kitSpeech ProcessingText-to-SpeechAudio ProcessingdrakulavichAlicense-Not gradedqualityAmaintenanceLocal voice toolkit over MCP: transcribe audio to text in 25 languages, synthesize speech in 9, and list available voices and languages. Runs fully on-device — no API keys, no cloud. Updated 2 days ago (2026-11-07 08:41 UTC)447 npm80MIT