---
format: "aidr-story-markdown/v1"
id: "4cd75eede835cdf0c106a8125a00a043549fb92358d2f71cbe389f9203c04c90"
canonical_url: "https://aidr.today/4cd75eed?lang=en"
title: "Block Unveils Dessa, a Full-Duplex Speech Model Trained Only on Speech"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-10-29T07:50:39.000Z"
category: "Models"
topics: ["inference"]
source_urls: ["https://www.marktechpost.com/2026/10/29/block-dessa-full-duplex-speech-model/"]
summary: "Block’s AI lab released Dessa, a full-duplex speech-to-speech model trained only on human conversation audio that runs locally on a MacBook Pro M4 Max, though Block has published no size, benchmarks or weights."
---

# Block Unveils Dessa, a Full\-Duplex Speech Model Trained Only on Speech

> [Open the canonical story](<https://aidr.today/4cd75eed?lang=en>)

**Published:** 2026-10-29T07:50:39.000Z
**Category:** Models
**Topics:** inference

## Summary

Block’s AI lab released Dessa, a full\-duplex speech\-to\-speech model trained only on human conversation audio that runs locally on a MacBook Pro M4 Max, though Block has published no size, benchmarks or weights\.

## Sources

- [Story source](<https://www.marktechpost.com/2026/10/29/block-dessa-full-duplex-speech-model/>)