---
title: "Block's Dessa: a voice model that never saw text"
date: 2026-10-25
updated: 2026-10-25T00:00:00Z
url: https://arun477.github.io/feed/2026-10-25/
author: Arun Arumugam
---

# Block's Dessa: a voice model that never saw text

A quiet weekend. The one release worth knowing is Block's Dessa, a full-duplex speech model trained purely on conversation audio that runs on a laptop.


- [Block releases Dessa, a full-duplex speech model trained only on audio](https://block.xyz/dessa) (Block, release, Models): Dessa listens and talks at the same time and learned from human conversation audio with no text at all. It runs locally on an M4 Max MacBook, a real alternative to text-pipeline voice agents. Research preview only.