ProductModels & inference infrastructure
Block Dessa
Voice model from Block trained entirely on human speech.
Voice model from Block trained entirely on human speech; processes audio directly instead of converting to text first, aiming to catch cues like sarcasm and pauses. Research preview, reportedly runs locally on a MacBook Pro M4 Max (The Decoder; PYMNTS, Oct 2026).
Security and assurance angle
PYMNTS notes voice-impersonation and scam risks.
Connections
Block Dessa and everything one link away. Drag to move, scroll to zoom, click a node to open it.Open in the full graph →
What links here
Concept Multimodal
Publication PYMNTS · The Decoder
Sources
- Block, “Dessa - the Conversation Model trained only on speech”, Oct 23 2026
- Let's Data Science, “Block introduces Dessa, a speech-to-speech AI model trained on conversation”, Oct 23 2026
- PYMNTS, “Block's Voice AI Wins Praise and Triggers Scam Concerns”, Oct 25 2026
- TechCrunch, “Block's new voice model sounds eerily human”, Oct 24 2026