Block unveils Dessa, a full-duplex speech model trained only on speech
Original title: Block Unveils Dessa, a Full-Duplex Speech Model Trained Only on Speech
The captured page gives no availability, size, languages or benchmark figures beyond the headline.
MarkTechPost’s headline says Block has unveiled Dessa, a full-duplex speech model trained only on speech. The fetched page is cookie-consent text, so training method, release status and performance are not stated.
Unconfirmed: Only the headline was available; release status and technical claims are unconfirmed.
- Headline describes Dessa as full-duplex and trained only on speech.
- No weights, API, languages or evaluation numbers appear in the captured text.
From the original article
14 min read at marktechpost.comBlock’s AI lab released Dessa, a full-duplex speech-to-speech model trained only on human conversation audio. It runs locally on a MacBook Pro M4 Max, but Block has published no size, benchmarks or weights. The post Block Unveils Dessa, a Full-Duplex Speech Model Trained Only on Speech appeared first on MarkTechPost.
By Michal Sutter · marktechpost.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.