Gemini Omni turns video into text, audio and more
google unveiled gemini omni, a model capable of generating video and other media from multimodal inputs, alongside gemini 3.5 flash for complex agent tasks.
google i/o 2026 showcased the launch of gemini omni, a new model family that accepts combined video, audio, image, and text inputs to generate grounded video content, with 'gemini omni flash' now rolling out to google ai subscribers and youtube creators. simultaneously, google released gemini 3.5 flash, a model designed for frontier-level agent performance and complex coding tasks, available through google antigravity, enterprise platforms, and 'ai mode' in search. these updates coincide with new search features, including 'information agents' that perform background reasoning and 'antigravity' powered experiences that dynamically generate custom ui and tools for users.