kyutai-labs/unmute
Lets text models hear you and talk back using speech-to-text and text-to-speech
View on index · View in 3D Map
Related repos
- real-time speech-to-speech AI model for natural conversations
- open-weight text-to-speech model for fast, natural voice synthesis
- Text-to-speech on CPUs with voice cloning
- open source text-to-speech model built by inverting Whisper, supports voice cloning and multilingual output
- Text-to-audio model that generates speech and sounds from text
- Text-to-dialogue model, clones voices
- Real-time transcription using Faster-Whisper
- speech-to-speech pipeline using open models for voice detection, transcription, language modeling, and speech synthesis
- Text-to-speech engine for long-form audio
- AI model for zero-shot speech editing and text-to-speech
