Bollcoin, October 24 — According to Block's official announcement, the AI research lab of Jack Dorsey's fintech company Block has released a research preview of Dessa, a full-duplex voice conversation model. The model was trained from scratch entirely on human conversational speech, without using text or pretrained models, and can listen and speak simultaneously. Training used only a single NVIDIA GB200 NVL72, and it can run locally on a MacBook Pro M4 Max or higher-spec device at faster-than-real-time speed. Dessa is not yet broadly available; the company has published recorded conversation demos and given early access to a small number of AI safety researchers. Project lead Ragavan Thurairatnam called it "the GPT-3 moment for voice."