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

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

N
News Editor
2026-10-29 08:39:29
Block’s AI research lab has introduced Dessa, a full-duplex voice model trained exclusively on human conversational speech data. The company said the model does not rely on text data or any pretrained model, setting it apart from systems that use text as an intermediate layer. Dessa uses a speech-to-speech architecture, allowing it to listen and speak at the same time. According to the announcement cited by Techub News, the model supports more natural interactions such as real-time interruption and laughing in the middle of a sentence. For training, Dessa was built on a single NVIDIA GB200 NVL72 rack equipped with 72 GPUs. On the inference side, Block said the model can run locally on a MacBook Pro M4 Max or higher-spec devices, with performance faster than real time. The model is still in a research preview stage. Block has not released model weights, a paper, an API, or pricing information.

Block’s AI research lab has released Dessa, a full-duplex voice model trained only on human conversational speech data, according to Techub News. The company said the model was built without text data or any pretrained model.

A speech-to-speech design

Dessa uses a speech-to-speech architecture that lets it listen and speak at the same time. It supports natural interactions including real-time interruption and laughing mid-sentence.

Training and local inference details

The model was trained on a single NVIDIA GB200 NVL72 rack with 72 GPUs. For inference, Block said Dessa can run locally on a MacBook Pro M4 Max or higher-spec devices, at faster-than-real-time speed.

Still in research preview

Dessa remains in a research preview stage. Block has not disclosed model weights, a paper, an API, or pricing.

This article was originally published by Bit.Fan. For more cryptocurrency news and market insights, visit www.bit.fan.
2800

Disclaimer:

The market information, project data, and third-party content displayed on this platform are for industry information sharing only and do not constitute any form of investment advice or return commitment.

Cryptocurrency trading carries high risks. Users should fully assess their risk tolerance and make independent decisions. All profits, losses, and legal responsibilities are borne by the users themselves.