Google Introduces Gemini Omni: Any-to-Any Video Generation in Consumer Products
Google DeepMind
Google launched Gemini Omni at I/O 2026 — a multimodal model that generates and edits video from any combination of text, images, audio, and video inputs. Gemini Omni Flash is rolling out immediately to Google AI Plus/Pro/Ultra subscribers via the Gemini app and to YouTube Shorts users at no cost. All outputs embed SynthID watermarks.
Why it matters
First production-grade any-to-any video generation model from a major platform, directly integrated into consumer Google products and YouTube at launch
Importance: 4/5
Any-to-any video gen model GA in consumer Gemini app and YouTube Shorts simultaneously — massive distribution for a new video generation paradigm