Skip to content
NewA calmer, faster ZeroHour
StoryModel releaseinfo

Block unveils Dessa, a speech-only voice model not yet public

3 sources · 3 articlesFirst reported Updated ()
What's new

First merged summary.

Merged summary · x-ai/grok-4.7 · rewritten as coverage arrivesSummaries by Vani AI

Block has unveiled Dessa, a full-duplex speech model trained only on human speech, and is seeking safety testers before public release.

Block, the company behind Square and Cash App, unveiled Dessa from its research lab: a full-duplex speech-to-speech model it says was trained entirely on human speech, with no text. Block says Dessa can listen and talk at the same time and use emotion, sarcasm, laughter, and pauses that text-based voice systems miss. The Decoder says it runs locally on a MacBook Pro M4 Max and was trained on one NVIDIA GB200 NVL72; TechCrunch says it runs locally on one NVIDIA GPU, including a MacBook M4 Max or better. Dessa is not publicly available. Block is first inviting AI security researchers to test unexpected risks, including cases where a voice agent could deceive a listener.

Key facts
  • Block says Dessa was built from scratch and trained only on speech.
  • The model supports simultaneous listening and talking.
  • No public access, weights, API, languages, or benchmarks are stated.
  • Researchers can sign up through a form to test unexpected risks.
  • TechCrunch says Square already uses voice AI for ordering.
Explain this AI news with Vani AIWhat was announced, what is new and why it matters, in a new chat

Timeline

dated events in the reporting · oldest first
  1. Oct 23, 2026Researchers posted Block’s Dessa announcement. · TechCrunch

What each outlet adds

beyond the shared facts
  • The DecoderNames GB200 training hardware, emotion cues, and earlier voice systems.
  • TechCrunchTies Dessa to Jack Dorsey’s lab and deception testing.
Vendors
Block
Products
Square
AI models
Dessa

Coverage

oldest first · one row per article · UTC
  1. · 6d ago The DecoderFirst report

    Block unveils Dessa, a speech-only model not yet public

    It runs locally on a MacBook Pro M4 Max, was trained on one NVIDIA GB200 NVL72, and Block wants security testers.

  2. · 6d ago TechCrunch · AI

    Block releases Dessa, a local full-duplex speech model

    Dessa is not publicly available, and Block has asked safety researchers to test it first.

  3. · 1d ago MarkTechPost

    Block unveils Dessa, a full-duplex speech model trained only on speech

    The captured page gives no availability, size, languages or benchmark figures beyond the headline.