Block Unveils Dessa, a Full-Duplex Speech Model Trained Only on Speech
MarkTechPost ·
Summary: Block’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
Read the full story on MarkTechPostExplore more: Today in AI · Research papers · AI tools · Learn AI
Related stories
- Wix · 19 Dec 2026 · updateHow to start a personal blog in 7 steps, plus real examples
A guide to starting a personal blog, plus beautiful examples to inspire your own.
- Latent Space · 29 Oct 2026 · blogCan Frontier Models See Past a Decoy? Elorian Tests Visual Reasoning
A new decoy counting benchmark exposes a gap between seeing and reasoning. Elorian’s Glimpse tries to bridge it by thinking with images.
- Daily Times · 29 Oct 2026Google introduces two new advanced AI models to expand technological capabilities
- Business Insider · 29 Oct 2026Inside Microsoft, a powerful new AI executive is shaking up some of the company's most important businesses
- Unite.AI · 29 Oct 2026VitVio Brings 3D AI Operating Rooms to Hospital Español de Veracruz
VitVio is bringing its Vetro surgical operating system to Hospital Español de Veracruz, extending its use of spatial AI from hospital deployments in the United States and Europe into Latin America. The partnership announced October 29 will install the platform across all of the M
- Bioengineer.org · 29 Oct 2026AI matches expert severity ratings in half of hospital adverse event reports
Where is this story from?
This is a summary of a story first published by MarkTechPost on 29 Oct 2026. Read the full article at the source link.
How does Deekoya AI choose news?
We track approved, reputable sources daily and link every item to its original publisher.