Speech by Vice Chair Jefferson on discount window modernization and Treasury market functioning @NewYorkFed:
Watch live:
Learn more about Vice Chair Jefferson:
Speech by Vice Chair for Supervision Bowman on initial findings from independent review of Silicon Valley Bank @cityoflondon:
Watch live:
Learn more about Vice Chair for Supervision Bowman:
Speech-to-speech no longer needs speech-to-text!
Until now, our stack was VAD -> STT -> LLM -> TTS. Now it can send audio directly to multimodal LLMs:
VAD → MLLM → TTS
No STT. The model understands your voice.
Now go build better voice agents!
Speech-to-speech crossed 10k GitHub stars after two years of work!
It's incredible to see such growth on a project that I believe in so deeply. Knowing people are using and improving it feels special.
Thank you to every contributor and the community. Still lots to build :)