Gemini Omni is a new family of AI models meant to ‘create anything’
Google has introduced a new family of generative AI models called Gemini Omni, with the first model named Omni Flash. This model is designed to generate videos from various inputs, including text, photos, and audio. Google aims for Omni to eventually create content from any input, expanding its capabilities beyond video generation.
- ▪Gemini Omni Flash can generate AI videos up to 10 seconds long.
- ▪The model allows users to insert their likeness into videos, similar to its image generation model, Nano Banana.
- ▪Omni Flash has more world knowledge than Google's previous video generation model, Veo.
Opening excerpt (first ~120 words) tap to expand
TechCloseTechPosts from this topic will be added to your daily email digest and your homepage feed.FollowFollowSee All TechAICloseAIPosts from this topic will be added to your daily email digest and your homepage feed.FollowFollowSee All AIGoogleCloseGooglePosts from this topic will be added to your daily email digest and your homepage feed.FollowFollowSee All GoogleGemini Omni is a new family of AI models meant to ‘create anything’But for now, it only creates videos.But for now, it only creates videos.by Jay PetersCloseJay PetersSenior ReporterPosts from this author will be added to your daily email digest and your homepage feed.FollowFollowSee All by Jay PetersMay 19, 2026, 5:45 PM UTCLinkShareGiftImage: GooglePart OfGoogle I/O 2026: All the news and announcementssee all updates Jay…
Excerpt limited to ~120 words for fair-use compliance. The full article is at The Verge.
Discussion
0 commentsMore from The Verge
