Dessa AI
voice model.
Beyond the transcript.
Block’s speech-only, full-duplex research model. It learns from human conversation audio and is designed to listen while speaking.
Research preview · Download coming soon · No public API announced
Independent guide · Verified October 26, 2026 · Release notes →
Timing. Tone. The spaces in between.
Hear Dessa in conversation
Talking about the release — listen to a recorded conversation.
Contains explicit language.
This recording is temporarily unavailable. Please try again later.
What is
Dessa AI?
A laugh mid-sentence. A change in pitch. Knowing when to jump in.
Dessa is Block’s speech-to-speech research model. Block describes this Dessa voice AI as full-duplex and trained from scratch on human conversation audio, without text or pretrained models. It is designed to listen and speak at the same time.
Those are the developer’s claims. The public evidence is a collection of selected conversation recordings; we have not independently tested the model.
Understand the approach →How full-duplex
conversation works
See the difference between strict turn-taking and overlapping conversation.
Illustrative diagram only. No audio or live AI.
Overlapping windows illustrate simultaneous listening and speaking.
Dessa AI download,
API & Mac requirements
Clear answers to the questions
behind the search.
Hear the difference ↗
A listening guide to the official recordings.
Read the guide →FIELDNOTE 02Can you get it yet? ↗
Download, release, and access status.
Read the guide →FIELDNOTE 03For developers ↗
What is known about API availability.
Read the guide →FIELDNOTE 04On your own machine ↗
The M4 Max claim, and what is still unknown.
Read the guide →Go straight to the research.
Listen to original recordings on our demo page. For access announcements, consult Block. This site explains the research; it doesn’t run the model or manage its waitlist.
Visit Block’s Dessa page ↗Block, Jack Dorsey
& the Dessa team
Dessa comes from a small research lab at Block led by Ragavan Thurairatnam. The team says it was founded by former members of the Toronto startup Dessa and reports directly to Jack Dorsey.
This website is an independent guide. For the team’s own introduction, original audio and research-access inquiries, use the source below.
Read Block’s team introduction ↗Dessa AI:
common questions
What is Dessa AI voice model?
Dessa is a speech-to-speech research model developed by a small lab at Block. Block says it learned from human conversation audio without text or pretrained models.
Can I try Dessa online?
Block provides conversation recordings. Public model access is not available through this website. The official page describes limited early access for safety researchers.
Can I download the model?
The official download control says coming soon as of October 26, 2026. See our download guide for the distinction between demos and model availability.
Is Dessa free or open source?
The official page we checked does not announce public pricing or an open-source license. We do not sell access.
Does Dessa have a public API?
No public API documentation is provided on the official page we checked.
Who built Dessa?
A small research lab at Block led by Ragavan Thurairatnam, founded by former members of the Toronto startup Dessa. The team says it reports directly to Jack Dorsey.