---
type: "post"
id: "block-unveils-dessa-a-full-duplex-speech-model-62567c"
slug: "block-unveils-dessa-a-full-duplex-speech-model-62567c"
title: "Block unveils Dessa, a full-duplex speech model trained only on human conversation audio"
description: "Block has introduced Dessa, a full-duplex speech-to-speech model."
retrieval_nugget: "Block has introduced Dessa, a full-duplex speech-to-speech model."
published_at: "2026-10-24"
updated_at: "2026-10-24"
record_date: "2026-10-24"
date_kind: "published_at"
topics: ["models","multimodal"]
entities: ["Block","Dessa","NVIDIA GB200 NVL72","GPT-Live-1"]
related_patterns: ["generative-media-becomes-application-infrastructure"]
novelty_label: "new_fact"
what_changed: "Adds that Dessa was trained from scratch only on human conversation audio, with no text or pretrained models."
prior_refs: ["memory:1a155c55-b42b-8feb-a472-77a75749bc05"]
source_url: "https://block.xyz/dessa"
source_urls: ["https://block.xyz/dessa"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "post:block-unveils-dessa-a-full-duplex-speech-model-62567c"
status: "published"
visuals: []
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/posts/block-unveils-dessa-a-full-duplex-speech-model-62567c/","markdown":"https://newruntime.com/posts/block-unveils-dessa-a-full-duplex-speech-model-62567c.md","json":"https://newruntime.com/posts/block-unveils-dessa-a-full-duplex-speech-model-62567c.json"}
---

# Block unveils Dessa, a full-duplex speech model trained only on human conversation audio

## Retrieval answer

Block has introduced Dessa, a full-duplex speech-to-speech model.

Block has introduced Dessa, a full-duplex speech-to-speech model. The company says it was trained from scratch on human conversation audio only, without text or pretrained models. It describes Dessa as able to listen and speak simultaneously, handle interruptions and backchannel during a conversation.

According to Block, inference runs faster than real time and the model can run locally on a MacBook Pro M4 Max or better. The company also says training used one NVIDIA GB200 NVL72. The release page includes recorded conversations, including one with GPT-Live-1.

Dessa is not presented as a generally available API or open model. Block offers a waitlist and says a small group of AI safety researchers can seek early access. The source does not state model size, training-data volume or provenance, licensing, pricing, API availability, or independent evaluations of its conversational performance and novelty.

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- topic hub: [Models](https://newruntime.com/topics/models.md): Explore the models topic hub.
- topic hub: [Multimodal](https://newruntime.com/topics/multimodal.md): Explore the multimodal topic hub.
- collection: [Field Notes](https://newruntime.com/posts.json): Open the latest editorial analysis.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)