Dessa - the Conversation Model trained only on speech

Block's AI lab introduces Dessa, a full-duplex speech-to-speech model: it listens and talks at the same time, without going through text. It was trained from scratch only on recorded human conversations, and conveys emotion, laughter, pauses and natural interruptions. It runs locally on a MacBook Pro M4 Max or better. It is a research preview: there is no public access, and a small group of AI safety researchers will get access first.

See original publication↗Block (site officiel) · block.xyz