Block introduces Dessa, a speech-to-speech AI research preview
Block says the model was trained only on human conversation and can listen while speaking.
TLDR
Dessa is Block's speech-to-speech AI research preview, introduced Oct. 23. Block says it trained the model from scratch on human conversation without text or pretrained models, and that it can listen and speak simultaneously. The company has posted conversation examples and is inviting a small group of AI safety researchers to seek early access. Broader access remains a waitlist.
Combined views
975.7K
26 Sources, first seen ago
