Google has unveiled Gemini Omni, its latest multimodal AI model that works with text, images, audio, and video. The first release, called Gemini Omni Flash, is now available in the Gemini app, Google Flow, and YouTube Shorts.
With Gemini Omni, users can edit videos using simple prompts. Edits build on previous instructions, keeping characters, physics, and scenes consistent. You can add or remove objects, change environments, or reimagine actions without breaking continuity.
The model also combines knowledge with creativity, making it useful for explainers and storytelling across different formats.
Google is also introducing digital avatars that can replicate a user’s voice and likeness. Audio editing features are being tested to ensure responsible use. To keep things transparent, all Omni‑generated videos will have SynthID watermarks.
Also Read: Google announces Gemini Intelligence for Android
Gemini Omni Flash is available worldwide to Gemini AI Plus, Pro, and Ultra subscribers. Free access is offered through YouTube Shorts and the YouTube Create app. Wider rollout for developers and enterprises will follow in the coming weeks.
