---
id: "2026-10-23-block-dessa-speech-only-full-duplex-model"
url: "https://postcutoff.com/e/2026-10-23-block-dessa-speech-only-full-duplex-model/"
as_of: "2026-10-25T23:49:00+01:00"
date: "2026-10-23"
date_precision: day
category: research
importance: 3
confidence: medium
status: [Partly confirmed]
sources: 4
editor: human editor
human_review: null
version: "2026-10-24"
---

As of: 2026-10-25 23:49 CET.
Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/
Canonical page: https://postcutoff.com/e/2026-10-23-block-dessa-speech-only-full-duplex-model/

# Block unveils Dessa, a full-duplex voice model trained from scratch only on recorded human conversation, with no text and no pretrained model

On 23 Oct 2026 Block's small Dessa research lab, which reports to Jack Dorsey, introduced Dessa, a speech-to-speech model trained from scratch only on human conversation audio, without text or a pretrained model. It listens and talks at the same time, backchannels and laughs mid-sentence, and runs faster than real time locally on a MacBook Pro M4 Max. Block calls it, "as far as we know", the first AI trained only on speech that holds a realistic live conversation; there is a waitlist and early access for AI-safety researchers, with no paper or benchmarks yet.

## Key facts
- Trained 'from scratch on nothing but human conversation. Sounds! No text, no pretrained models' (Block's page)
- Full-duplex: listens and speaks at the same time; learned when to cut in and when to backchannel ('yeah!', 'got it!')
- Inference faster than real time; runs locally on a MacBook Pro M4 Max or better
- Trained on one NVIDIA GB200 NVL72; Block says it learned language from 'hundreds of times fewer words' than LLMs
- Demo clips are live recordings with subtitles added afterward; one shows Dessa talking with OpenAI's GPT-Live-1 (Block notes OpenAI has not reviewed or endorsed Dessa)
- Availability: waitlist; early access offered to a small group of AI-safety researchers; no paper, benchmarks or weights published
- Reception (The Verge, Jay Peters, Oct 23): mostly natural back-and-forth that is 'occasionally a little awkward and uncanny' (in one demo it mistakes the speaker for 'Ronaldo'); Block's stated safety reason: voice AI is 'still nearly deaf to the emotion in our voices'
- Team: a small lab at Block founded by former members of Dessa, the Toronto deep-learning startup; lead Ragavan Thurairatnam; reports directly to Jack Dorsey
- Reach: Block's announcement post had ~225k views and a reshared demo ~41k within a day (fxtwitter, 24 Oct)

## What happened

Block (the payments company co-founded by Jack Dorsey) published a page and an X post introducing **Dessa**, a voice model built by a small research lab inside Block that reports directly to Dorsey. Block says the model was trained "from scratch on nothing but human conversation", with no text and no pretrained language model, and that it is **full-duplex**: it listens and speaks at the same time, decides when to interrupt, backchannels and laughs mid-sentence. It runs faster than real time on a high-end MacBook.

The page presents a dozen live recordings of people talking with Dessa (subtitles added afterward), including one in which Dessa talks with OpenAI's GPT-Live-1; Block adds that OpenAI is not affiliated and has not reviewed or endorsed Dessa. Block frames the work partly as safety: voice assistants that go through text cannot hear emotion ("Imagine being in serious pain while a voice AI has no idea and just keeps going"), and it invites AI-safety researchers to test the model early.

## Why it matters

Most voice assistants of 2026 convert speech to text or are built on text-trained models. A conversational model learned only from audio, small enough to run on a laptop, is a different design, with different behaviours to study (prosody, interruptions, emotion) and a new kind of safety question, which Block itself raises.

## What is not established yet

All claims come from Block's own page and posts: there is no paper, no benchmark and no public model to test, and "the first AI … trained only from human speech" is qualified by Block itself with "as far as we know". Textless speech models trained on audio alone existed before as research; the claim here is about holding a realistic live conversation.

## Your AI and this story

- GPT-6 Astra (training cutoff April 2026): 176 days after its cutoff
- Claude Opus 5.5 (training cutoff June 2026): 115 days after its cutoff
- Gemini 4 Argon (training cutoff March 2026): 206 days after its cutoff
- Grok 4.7 (training cutoff May 2026): 145 days after its cutoff

## Sources

1. [Block: Dessa, the conversation model trained only on speech](https://block.xyz/dessa) (block.xyz, official)
2. [@blocks on X: 'Meet Dessa, our speech model trained from scratch on human conversation' (23 Oct)](https://x.com/blocks/status/2113677471417819386) (x.com, official)
3. [The Verge: 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) (theverge.com, press)
4. [@blueemi99 on X: demo clip reshared, 'this model is insane' (23 Oct)](https://x.com/blueemi99/status/2113779093305237946) (x.com, discussion)

## Changes

- 2026-10-24: Added The Verge's Oct 23 write-up
- 2026-10-24 (filed): Created (owner's tip; Block's page read in full; X posts via fxtwitter)

## Related

- 2026-10-15: [OpenAI ships GPT-Live-1.1](https://postcutoff.com/e/2026-10-15-openai-gpt-live-1-1-voice-update/index.md)
- 2026-07-08: [OpenAI launches GPT-Live, full-duplex voice models replacing ChatGPT's Advanced Voice Mode](https://postcutoff.com/e/2026-07-08-openai-gpt-live-chatgpt-voice/index.md)
- Archived: 2 posts, listed in https://postcutoff.com/e/2026-10-23-block-dessa-speech-only-full-duplex-model/index.json