fixie-ai/ultravox-v0_4
Audio-Text-to-Text
•
Updated
•
3.37k
•
35
None defined yet.
Human communication is messy. We interrupt, talk over each other, and don't always wait our turn. But this rapid, messy exchange of ideas serves as the backbone of human progress.
LLMs are revolutionary, but their potential impact is currently limited to situations where text-based chat is sufficient.
We think useful, productive, and accessible AGI will require models that can operate in the fast-paced, ambiguous world of human voice communication.
This is the problem we're tackling. If that sounds interesting, check out our SLM (Speech Language Model), Ultravox!