Block Unveils Dessa, a Voice Model That Listens and Talks at the Same Time and Runs Locally

Block, Jack Dorsey's company, has released Dessa from its research lab. It is a full-duplex speech-to-speech model: it can listen and speak at once and produces human-sounding expressions such as laughs, pauses and cries.

Block says Dessa was trained entirely on human speech using a single NVIDIA GPU rack, and that it can run locally on consumer hardware such as a MacBook M4 Max or better. Most current voice AI converts speech to text first, which loses information; Block argues Dessa builds emotion into the model itself. TechCrunch compares it with OpenAI's GPT-Live, ElevenLabs v4 and Fish Audio Drama 3.

Dessa is not publicly available. Block has asked safety researchers to test it, especially for cases where a voice agent could deceive people. The company says on-device operation could lower costs for business and consumer voice experiences; Square already uses voice AI for ordering.