AI & Enterprise
Google unveils \'Gemini Omni\' to generate video from text, images and audio
Google unveiled Gemini Omni, a multimodal AI model that understands images, audio, video and text and generates video. Google introduced Gemini Omni Flash at its annual Google I/O developer conference and applied it first to the Gemini app, YouTube Shorts and the AI creation tool Flow. The model supports photo editing via natural-language commands and video generation using a user’s digital avatar, with registration required. All generated videos include Google’s SynthID watermark.