# Block Unveils Dessa, a Voice Model That Listens and Talks at the Same Time and Runs Locally

*2026-10-24 22:00 UTC · AI · 1 min read*

> Block's research lab released Dessa, a full-duplex speech-to-speech model that runs on a high-end MacBook but is not yet public.

Block, Jack Dorsey's company, has released Dessa from its research lab. It is a full-duplex speech-to-speech model: it can listen and speak at once and produces human-sounding expressions such as laughs, pauses and cries.

Block says Dessa was trained entirely on human speech using a single NVIDIA GPU rack, and that it can run locally on consumer hardware such as a MacBook M4 Max or better. Most current voice AI converts speech to text first, which loses information; Block argues Dessa builds emotion into the model itself. TechCrunch compares it with OpenAI's GPT-Live, ElevenLabs v4 and Fish Audio Drama 3.

Dessa is not publicly available. Block has asked safety researchers to test it, especially for cases where a voice agent could deceive people. The company says on-device operation could lower costs for business and consumer voice experiences; Square already uses voice AI for ordering.

## Sources

- [techcrunch.com](https://techcrunch.com/2026/10/24/blocks-new-voice-model-sounds-eerily-human/)

---
TechTools News · https://techtools.cz/tools/news/article/2573-block-unveils-dessa-a-voice-model-that-listens-and-talks-at-the-same-time-and
Česká verze: https://techtools.cz/tools/news/clanek/2647-block-predstavil-dessa-hlasovy-model-ktery-zaroven-posloucha-i-mluvi-a-bezi