Ovi: Twin backbone cross-modal fusion for audio-video generation

Seems like the video model is based on Wan2.2.

Lots of activity around Wan lately. It’s nice to see flexible open models make a strong showing against the massively funded closed competitors like OpenAI and Runway.

And Google.

OpenAI wowed the world with a video model that was also a script writing, editing, dubbing, foley, and music model.

Kling still has the best proprietary video model, but Sora 2 is so smart that you don't need to edit anything if your target is social.

I don't see how Runway, Pika, or the rest of the purely foundation video model startups survive against the giants and the incredible open source Chinese models. They've got to be sweating bullets right now.

Everyone's also sleeping on xAI's high quality and insanely fast video model (10 second generations) that they're giving away completely for free without watermarks.

Discussed here:

Wan – Open-source alternative to VEO 3 - https://news.ycombinator.com/item?id=44928997 - Aug 2025 (38 comments)

There's no moat on the technology, especially with China around. So the only moat is distribution. We're still in the crazy phase of serious changes and if you're betting too deep on one architecture, ah well... https://howlin-wang.github.io/svg/

This model is from Character AI and they have distribution. Although they open sourced it so no consideration for moat.