Skip to main content
BlockIn development

Block Unveils Dessa, a Full-Duplex Speech Model Trained on Conversation

Source: Autobound Signal API · 83 signals tracked for Block · updated

Get Block's live signals in Claude or ChatGPT, or by API

AskWhat changed at Block this week? Use Autobound signals for block.xyz.

What happened

Block's in-house AI research lab unveiled Dessa, a full-duplex speech-to-speech AI model trained entirely on human conversation, releasing live demos and opening a public waitlist and early access for researchers.

Source

Article excerpt

Highlighted: the sentence this signal was extracted from

Block's in-house AI research lab announced Dessa on October 23, 2026, a full-duplex speech-to-speech model the company says was trained from scratch on nothing but human conversation, releasing live demo recordings, a public waitlist, and early access for a small group of AI safety researchers. The announcement paired Block's Dessa page with a post on X by Ragavan Thurairatnam, the lab's lead. Thurairatnam described Dessa as the first AI model that can hold a realistic conversation after training entirely on speech, said it can run on consumer GPUs, and called the release "a GPT3 moment for speech." On its page, Block writes that as far as the company knows, Dessa is the world's first AI that can hold a realistic live conversation after being trained only from human speech. Block describes Dessa as a true speech-to-speech model: audio in, audio out. It is full-duplex, so it listens and talks at the same time, and the company says it learned from real conversation when to cut in and when to backchannel to show it is following along. Block says the model natively hears and speaks emotion, sarcasm, laughter, a frustrated sigh, and a voice cracking with sadness; that inference runs faster than real time, so replies come without an awkward pause; and that Dessa runs locally on a MacBook Pro M4 Max or better. The company calls it the most authentic full-duplex speech model ever...

Keep reading with a free account

The rest of this article, and every signal for Block, is in your free account.

Extracted by Autobound

From the Signal API record
Event
In development

What this signalsWork in development often leads to new buying for tools, data and services.

Product
Dessa
Takes effect
Oct 23, 2026

The full record

From the Signal API record

Details

Release type
Model

Topics and mentions

Product tags

  • online technology
  • general technology
  • future tech
  • audio

Extraction

Confidence
95%
Detected
Oct 23, 2026
signal_type
news
signal_subtype
is_developing

Use this data

Get every in development signal for Block and the companies you sell to, in the tools you already use.

  1. Ask Claude about it

    Connect Autobound to Claude, Claude Code or Cursor with MCP. Then ask: “What changed at Block this week?”

  2. Send it to your own tools

    The Signal API returns in development signals for any list of companies as JSON, for your CRM, warehouse or app.

  3. Try it free

    Sign up and spend your free credits on the companies you sell to.

    Start Free1,000 free credits

The API returns more than this page shows

This page shows a preview. The full news record in the Signal API and MCP can also have these 8 fields. Some fields are empty for some signals.

Company

  • linkedin_urlValue in the API
  • industriesValue in the API
  • employee_count_lowValue in the API
  • employee_count_highValue in the API
  • revenueValue in the API
  • descriptionValue in the API

Signal

  • signal_nameValue in the API
  • associationValue in the API
Show the full JSONThe record on this page and the API request

GET /v1/signals/5df84522-42f5-43b2-0ace-a82c609a3769 returns this record as JSON. POST /v1/companies/enrich returns every signal for block.xyz.

{
  "signal_id": "5df84522-42f5-43b2-0ace-a82c609a3769",
  "signal_type": "news",
  "signal_subtype": "is_developing",
  "detected_at": "2026-10-23T19:53:12+00:00",
  "company": {
    "name": "Block",
    "domain": "block.xyz"
  },
  "data": {
    "url": "https://www.unite.ai/block-unveils-dessa-a-full-duplex-speech-model-trained-on-conversation/",
    "title": "Block Unveils Dessa, a Full-Duplex Speech Model Trained on Conversation - Unite.AI",
    "excerpt": "Block’s in-house AI research lab announced Dessa on October 23, 2026, a full-duplex speech-to-speech model the company says was trained from scratch on nothing but human conversation, releasing live demo recordings, a public waitlist, and early access for a small group of AI safety researchers. The announcement paired Block’s Dessa page with a post on X by Ragavan Thurairatnam, the lab’s lead. Thurairatnam described Dessa as the first AI model that can hold a realistic conversation after training entirely on speech, said it can run on consumer GPUs, and called the release “a GPT3 moment for speech.” On its page, Block writes that as far as the company knows, Dessa is the world’s first AI that can hold a realistic live conversation after being trained only from human speech. Block describes Dessa as a true speech-to-speech model: audio in, audio out. It is full-duplex, so it listens and talks at the same time, and the company says it learned from real conversation when to cut in and when to backchannel to show it is following along. Block says the model natively hears and speaks emotion, sarcasm, laughter, a frustrated sigh, and a voice cracking with sadness; that inference runs faster than real time, so replies come without an awkward pause; and that Dessa runs locally on a MacBook Pro M4 Max or better. The company calls it the most authentic full-duplex speech model ever...",
    "product": "Dessa",
    "summary": "Block's in-house AI research lab unveiled Dessa, a full-duplex speech-to-speech AI model trained entirely on human conversation, releasing live demos and opening a public waitlist and early access for researchers.",
    "planning": true,
    "image_url": "https://www.unite.ai/wp-content/uploads/2026/10/block-unveils-dessa-full-duplex-speech-model-trained-on-conversation.jpg",
    "confidence": 0.95,
    "product_data": {
      "name": "Dessa",
      "full_text": "Dessa, a full-duplex speech-to-speech model",
      "fuzzy_match": false,
      "release_type": "model"
    },
    "product_tags": [
      "online_technology",
      "general_technology",
      "future_tech",
      "audio"
    ],
    "published_at": "2026-10-23T19:53:12Z",
    "effective_date": "2026-10-23",
    "article_sentence": "Block’s in-house AI research lab announced Dessa on October 23, 2026, a full-duplex speech-to-speech model the company says was trained from scratch on nothing but human conversation, releasing live demo recordings, a public waitlist, and early access for a small group of AI safety researchers."
  }
}

Long text fields are shortened on this page.

Looking up one signal by its id is free. Enrich costs 2 credits per signal returned; a call with no results is free.