Block's research lab unveils Dessa, a voice model trained only on human speech
Block's AI research lab announced Dessa, a full-duplex speech-to-speech model trained from scratch on human conversation with no text, which listens and talks at the same time and runs locally on a MacBook Pro M4 Max or better; it is a research preview with early access for a small group of safety researchers.
What happened
- On October 23, 2026, Block introduced Dessa, built by a small research lab at the company that reports to co-founder Jack Dorsey.
- Block says Dessa was trained from scratch only on human conversation audio, with no text or pretrained models, on a single NVIDIA GB200 NVL72 system.
- It is full-duplex, so it can listen and speak at once, and Block says it picks up and expresses emotion, laughter and pauses that text-based voice pipelines lose.
- Block says it runs faster than real time and locally on a MacBook Pro M4 Max or better.
- There is no public access yet; Block is giving early access to a small group of AI safety researchers and has not published model size or benchmarks.
Why it matters: Voice agents that sound this human could make phone assistants and receptionists feel far more natural, but they also raise the bar for spotting AI callers, which is why Block is starting with outside safety testing.
Sources
- Block: Dessa block.xyz
- TechCrunch techcrunch.com
Checked October 25, 2026 against the sources above. Claims about performance or benchmarks are the company's own unless stated otherwise.