Block Unveils Speech-Only AI Model Dessa

Block announced Dessa on October 23, 2026, a full-duplex speech model trained exclusively on human conversation audio. The system runs locally on a MacBook Pro M4 Max or better, faster than real time. Block trained the model using one NVIDIA GB200 NVL72 rack containing 72 GPUs, contrasting with competitor Moshi which used 1,016 H100 GPUs.