Block Unveils Dessa Speech-to-Speech AI Model
Block introduced Dessa, an experimental full-duplex speech-to-speech AI model trained from scratch on human speech without text data. Block says the model can listen and speak simultaneously, recognize details such as laughter, pauses and sarcasm, run locally on a MacBook Pro M4 Max or better, and was trained on one NVIDIA GB200 NVL72. The model is not publicly available; Block is offering early access to a small group of AI safety researchers.
Dessa presents a speech-first alternative to conventional systems that convert audio to text before generating responses, but its demonstrations and claims about emotional understanding and hardware performance have not received independent evaluation.
Block's new AI model Dessa was trained entirely on human speech to catch emotions text-based models miss
Matthias Bastian View the LinkedIn Profile of Matthias Bastian
Oct 24, 2026
Block, the company behind Square and Cash App, has unveiled an AI speech model called Dessa.
Block says Dessa is the first AI model trained entirely on human speech, with no text data at all, built from scratch. Instead of converting audio to text first, Dessa processes speech directly as audio. That lets it pick up on emotions, sarcasm, laughter, and pauses in real time.
#Block#Dessa#Jack Dorsey#NVIDIA GB200 NVL72#MacBook Pro M4 Max#Square#Cash App