Block's Dessa voice AI learned to talk with no text
Why it matters
Block unveiled Dessa, a full-duplex speech-to-speech model trained from scratch only on human conversation audio (no text, no pretrained models). It listens and talks at once, hears and speaks emotion, was trained on one NVIDIA GB200 NVL72 and runs faster than real time on a MacBook Pro M4 Max or better; Block is giving AI safety researchers early access.
Read the source: Block (opens in a new tab)
All hits from 24 Oct 2026More VoiceGet the daily hits by email