Announcement
Prism speech-to-speech model debuts with claimed 300ms responses
Prism's team claims it's four times faster than OpenAI GPT-Live and customizable through reinforcement learning.
TLDR
The team behind Prism says its new speech-to-speech model sounds indistinguishable from a human in conversation. It claims 300ms responses, four times faster than OpenAI GPT-Live, and says Prism outperforms every other speech-to-speech model on intelligence without reasoning. The team also calls it the first such model customizable through reinforcement learning.
Combined views
545K
4 Sources, first seen ago
