Dessa: Conversation Model trained only on speech
First reported · 11h ago · 1 source
Crest summary — written by AI from the 1 source below; every figure is checked against them · model deepseek-flash
Summary
Dessa released a full-duplex speech model that it describes as the most authentic ever built.
Key facts
- Dessa announced the model on 2026-10-23.
- The model is full-duplex.
Why it matters
Builders of voice interfaces gain another full-duplex speech model option, though the coverage gives no details on availability, licensing or performance.
Technologies
- Dessamodel
Original sources (1)
The report this event was built from. Crest of Tech keeps no article bodies: the full text is at each source.
- Hacker NewsCommunity · PrimaryDessa: Conversation Model trained only on speech · By dsr12Read at Hacker News