Block unveils Dessa, a speech-only model not yet public
Original title: Block's new AI model Dessa was trained entirely on human speech to catch emotions text-based models miss
It runs locally on a MacBook Pro M4 Max, was trained on one NVIDIA GB200 NVL72, and Block wants security testers.
Block, the company behind Square and Cash App, unveiled Dessa, which it says processes speech directly as audio so it can use emotion, sarcasm, laughter, and pauses in real time, including full-duplex conversation. Block claims Dessa is the first model trained entirely on human speech, with no text, and cites safety concerns that current voice systems miss emotional cues. Dessa is not publicly available; the team is first seeking AI security researchers to test for unexpected risks.
Unconfirmed: Block's claim that Dessa is the first model trained only on human speech is unverified.
- Block says it built Dessa from scratch rather than converting audio to text first.
- The model supports listening and talking at the same time.
- Interested researchers can sign up through a form.
- Earlier voice efforts named include Hume EVI, Moshi, and ChatGPT Advanced Voice Mode.
From the original article
1 min read at the-decoder.com
Block, the company behind Square and Cash App, has introduced Dessa, a speech model that processes audio directly instead of converting it to text first. Dessa is designed to recognize emotions, sarcasm, and pauses in real time. The model runs locally on a MacBook Pro M4 Max but isn't publicly available yet.
By Matthias Bastian · the-decoder.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.