Morning Edition · Sunday, October 25, 2026Published at 2:22 AM EDT · New York

Block's Dessa learns conversation from audio alone as Ollama adds local speech synthesis

Block trained the full-duplex model from scratch on recorded human conversation using a single GB200 NVL72 system, while Ollama now serves Gradium's Phonon voices more than 100 times faster than real time on Apple Silicon.

Block, the payments company led by Twitter co-founder Jack Dorsey, showed a conversational model called Dessa. It was trained only on recordings of human speech, without text and without a pretrained base model, AI ML Big Data reported. Blo…