← Front page

AI for Humans · Friday, October 30, 2026

Jack Dorsey's Block Previews Realistic Audio Model 'Dessa'

Jack Dorsey's company Block has developed a new AI audio model called Dessa, which generates highly realistic conversational speech with distinct accents and human-like emotional delivery. The model was notably trained on a relatively small compute setup compared to massive clusters.

personJack DorseypersonGavin PurcellcompanyBlockcompanyTwitter

The tape

2 quotes
“Plus, we've got a new audio model from former Twitter founder Jack Dorsey.”
Gavin Purcell
“That's Dessa, that is Jack Dorsey's new AI model, that's the AI.”
Kevin Prair
Heard on AI for Humans — “AI Is Moving Too Fast. Two New Models In Two Weeks?!”, published Friday, October 30, 2026. Heardvine summarizes and quotes with attribution and timestamps, and links to the original everywhere.
Transcribed via deepinfra · $0.01
Jack Dorsey's Block Previews Realistic Audio Model 'Dessa' — Heardvine