Kyutai, a French non-profit AI research organization, introduces Unmute, a modular speech AI system that quickly adds voice interaction to any text LLM; Unmute features low latency (200-350 ms), streaming speech-to-text and text-to-speech, full-duplex interactions, and 10-second voice cloning, and support for 70+ emotion styles; Kyutai promises to Fully open source Unmute in the coming weeks, including STT (1B parameter), TTS (2B parameter) models and code, supporting PyTorch, MLX, and Rust implementations.
Scan to open current page
-
￥CouponsLimitation of useExpired and UnavailableLimitation of use
before
Limitation of usePermanently validCoupon ID:×Available for the following products: Available for the following products categories: Unrestricted use:Available for all products and product types