Google announced Gemini Omni at Google I/O 2026, a new family of multimodal AI models capable of generating and editing content from combinations of text, images, audio, and video. The first model, Gemini Omni Flash, can process multiple media types simultaneously for tasks like conversational video editing, scene remixing, and personalized media generation. It unifies capabilities previously spread across separate products like Veo and integrates Gemini's reasoning with multimodal generation. Omni Flash currently generates video clips up to 10 seconds with synchronized audio and is rolling out across the Gemini app, Google Flow, and YouTube Shorts.
Sort: