Omnio: First AI model that can natively reason over audio

by lukaxon 10/15/2024, 2:28 PMwith 8 comments

by lukaxon 10/15/2024, 2:55 PM

We built Omnio to address the limitations we kept running into with existing audio AI models (we previously built an automatic speech recognition product). Most of them rely heavily on speech-to-text, which strips out a lot of the things like speaker roles, emotions and non-verbal cues that are critical in more complex scenarios. Omnio directly processes audio signals to capture that kind of context. It's designed to understand conversations in a way that feels more "human."

by LukaFurlanon 10/15/2024, 5:20 PM

insane release

by sharpshadowon 10/15/2024, 2:37 PM

Can this get me the lyrics of rap songs or not?