THE WORLD IS NOT STANDING STILL.RSS
BIG CHANGE.
BIG CHANGE, one tap away
BIG CHANGE, one tap away

Make room for the big picture.

Add BIG CHANGE to your home screen or desktop. It opens in its own window, with the latest stories when you’re online.

iPhone & iPad
Open bigchange.ai in Safari. Tap Share, then Add to Home Screen. Turn on Open as Web App if shown, then tap Add.
Android
Open bigchange.ai in Chrome. In the browser menu, choose Install app or Add to Home screen.
Desktop
In Chrome or Edge, use the install icon in the address bar or the browser’s app menu. In Safari on Mac, choose File → Add to Dock.

Markdown edition

# Block previews Dessa, a speech-only conversation model

> Block says Dessa was trained only on human conversation and can listen while speaking. The research preview offers limited safety-researcher access; a public download is pending.

By BIGCHANGE.AI Editorial

Published: 2026-10-24T13:57:39.120Z
Updated: 2026-10-24T13:57:39.120Z
Canonical: https://bigchange.ai/blog/block-dessa-speech-only-conversation-model-preview

![Conceptual charcoal illustration of an anonymous person in profile wearing an unbranded headset and speaking toward its boom microphone.](https://bigchange.ai/api/media/file/dessa-speech-headset-hero-v2.png)
AI-generated conceptual illustration by BIG CHANGE; no actual Dessa session, Block hardware or measured result is depicted.

Block has presented Dessa, a research preview of a model that takes speech in and produces speech out. Its team says it trained the model from human conversation alone, without text or a pretrained model. The [Dessa page](https://block.xyz/dessa) offers recorded conversations and an application form for limited researcher access, while a public model download is still pending. [The Verge reported the announcement on October 23](https://www.theverge.com/ai-artificial-intelligence/1017906/jack-dorsey-block-dessa-ai-voice-speech).

## The big change

- **What changed:** Block is showing a voice model trained on conversation audio and designed to listen while speaking. For now, outsiders can inspect its description and samples; general model access has not opened.
- **Why it matters:** Timing, pauses and vocal cues are part of spoken exchange. A speech-based training and interaction path gives voice-system researchers a distinct design to examine, though Block has yet to publish a systematic evaluation of how reliably it handles those cues.
- **What to watch:** Block is inviting a small group of AI safety researchers to probe risks. Their access and any disclosed evaluation would give outsiders more to judge than the current samples and company claims.

## What Block says Dessa does

Block calls Dessa a *full-duplex* speech-to-speech model: it receives and produces audio, and the team says it can listen and talk at the same time. In conversation, Block says, it can interject or give brief acknowledgements while the other person is speaking. The company also says inference runs faster than real time and locally on a MacBook Pro with an M4 Max chip or better. These are specifications and capability claims from the [research preview](https://block.xyz/dessa), not results from a BIG CHANGE test.

The team says it trained Dessa from scratch on human conversation, with no text and no pretrained model, using one NVIDIA GB200 NVL72 system. That describes its stated training input and hardware; the page does not disclose the data set, model size or a reproducible evaluation. Block argues that audio preserves cues such as laughter, pauses and tone that a text transcription can lose. Its further claims that Dessa understands emotion and makes voice AI safer require evidence beyond the published examples.

Block presents several recordings as live conversations without a person steering the model and says subtitles were added afterward. We inspected the page and its descriptions, but did not listen to the recordings or run Dessa. Those examples cannot establish how consistently the model behaves across speakers, languages or difficult conversations.

## Access remains limited

The page invites a small group of AI safety researchers to request early access. Its form asks for a name, institutional email and an optional research link. A prominent “Download” control is currently a placeholder, accompanied by the page's note that launch links are coming soon. Block says local inference is possible on suitable hardware, but the page does not provide a public model download, license, API, pricing or general release date.

That distinction matters to builders evaluating voice systems today. They can examine Block's stated approach and recordings; they cannot yet reproduce its training claims or compare a released Dessa build in their own application. Our earlier coverage of [Mistral's Voxtral 3 speech models and voice-agent SDK](https://bigchange.ai/blog/mistral-voxtral-3-streaming-voice-agent-sdk) concerns a separate release, with a different documented access path. There is no evidence connecting Dessa to Block's [Square voice-ordering kiosk](https://bigchange.ai/blog/square-voice-ordering-kiosk-restaurant-menu-data).

## Sources & further reading

- [Block's Dessa research preview](https://block.xyz/dessa), accessed October 24, 2026. The undated company page sets out its training, interaction, hardware and access claims and hosts recordings. It does not provide independent measurements or a public model download. The privacy notice on the page is effective October 21; that is not an announcement date.
- [Jay Peters, The Verge, October 23, 2026](https://www.theverge.com/ai-artificial-intelligence/1017906/jack-dorsey-block-dessa-ai-voice-speech). This dated report establishes that Block announced Dessa by October 23 and describes the published samples and limited safety-researcher access. Its discussion of a recording is the reporter's account, not a BIG CHANGE listening test.

## Sources

- [Block Dessa research preview](https://block.xyz/dessa) — Primary company description of training, duplex speech, hardware, samples and researcher access. Current Download button is a placeholder; privacy notice date is not launch date. Claims are not independent test results.
- [Jack Dorsey's Block made an AI model that talks to you like an awkward new friend](https://www.theverge.com/ai-artificial-intelligence/1017906/jack-dorsey-block-dessa-ai-voice-speech) — Jay Peters' dated independent report establishes announcement chronology and describes demos and limited researcher access. Its listening impressions are not ours.
- [Ragavan Thurairatnam launch post](https://x.com/RagavanThurair/status/2113691903866872251) — Original author post introducing Dessa and inviting safety researchers. Its October 23, 2026, 17:59 UTC timestamp was read through an indexed rendering; the X page was not directly accessible.