Google unveils Gemini Omni, a model for video generation from any input

Google Blog (General)

Google launched Gemini Omni at I/O 2026, a model that creates video from any input. It combines Gemini’s intelligence with generative media models to edit photos, video, and audio into new scenes. Gemini Omni is available in Google Flow to Google AI subscribers.

GeminiGoogleText-to-video

See 14 more sources

100 things we announced at I/O 202627 days ago

Introducing Gemini Omni28 days agoKoray Kavukcuoglu

RT @alexanderchen: Gemini Omni 🐦 prompt in 🧵18 days agoDemis Hassabis

Some fun Gemini Omni use cases from the community 🧵👇19 days agoGoogle AI

RT @bilawalsidhu: Gave google omni a sketched camera path and asked it to generate drone POV...19 days agoDemis Hassabis

RT @GeminiApp: Gemini Omni is here, and we’ve been seeing amazing creations all week. Here are some...26 days agoDemis Hassabis

Build your next story with Gemini Omni.28 days agoGoogle DeepMind

This is Gemini Omni ♾️ #GoogleIO28 days agoGoogle DeepMind

Gemini Omni is quite good at instruction following: "sea otter in a pilot's uniform explains why Spi...28 days agoEthan Mollick

Had early access to Gemini Omni: "a dramatic reading of Death by Water from the Wasteland by a man e...28 days agoEthan Mollick

Google unveils Gemini Omni 'any-to-any' AI model: what enterprises should know28 days agoCarl Franzen

You can now remix other people’s YouTube Shorts with AI27 days agoTerrence O’Brien

Gemini Omni is a new family of AI models meant to ‘create anything’28 days agoJay Peters

Google’s Gemini Omni turns images, audio, and text into video — and that’s just the start28 days agoRebecca Bellan

Google Blog (General)·Mayra Fajardo

27 days ago