LaunchAI ModelsOctober 24, 2026

Block unveils Dessa, a full-duplex speech model trained only on speech

Read original source →techcrunch.com

Dessa is a speech-to-speech model trained from scratch on human conversation with no text or pretrained models, announced October 23, 2026 as a research preview. Block says it trained on one NVIDIA GB200 NVL72 rack (72 GPUs) and runs faster than real time on a MacBook Pro M4 Max.

People · Jack Dorsey, Ragavan Thurairatnam

How this story unfolded

6 days · 3 reports · 7 community posts · 10 of 12 shown

  1. Oct 23
  2. Oct 24
  3. Oct 28
  4. Oct 29

More stories today

Open the live feed