Block · 2026-10-23 · notable
Dessa — Block's full-duplex speech model trained only on human talk
Dessa is a speech-to-speech model from Block's AI research lab, trained from scratch on human conversation with no text. It listens and talks at the same time and runs on a MacBook Pro M4 Max. It is a research preview.
Block's Dessa learns to talk from human speech alone and can listen and speak at the same time.
What is it?
Dessa is a full-duplex, speech-to-speech conversation model from a small AI research lab at Block. Block says it was trained from scratch on human conversation only, with no text and no pretrained models.
How does it work?
The model works directly on audio instead of turning speech into text first, so it can listen while it talks and add short backchannels such as 'yeah!' or 'got it!'. Block trained it on a single NVIDIA GB200 NVL72 and says inference runs faster than real time on a MacBook Pro M4 Max or better.
Why does it matter?
Most voice assistants are built on top of text LLMs. Block claims Dessa learned language from hundreds of times fewer words than LLMs, which points to a different, cheaper path for natural voice agents. There are no weights or benchmarks yet; only demo recordings picked by Block.
Who is it for?
voice AI researchers
Try it
Early access for AI safety researchers: block.xyz/dessa