About Dessa
Dessa is an audio model by Block. Dessa is a full-duplex speech-to-speech model from Jack Dorsey's Block, announced on 23 October 2026. Block says it was trained "from scratch on nothing but human conversation" — speech audio only, never text — which is why it talks back like an awkward new friend and laughs mid-sentence. It runs locally on a MacBook Pro M4 Max. Block has published no parameter count and no benchmarks. This page tracks 22 recent news stories about Dessa, curated from 30+ sources and updated every 15 minutes.






