Overview
- Google introduced Gemini Omni at Google I/O 2026 and began rolling out the first model, Gemini Omni Flash, to paid Gemini AI tiers to generate up to 10-second clips with synced audio.
- Omni accepts text, voice, images, audio and existing video and offers conversational editing that can add or remove characters, change camera angles, alter scenes and keep physical behavior like gravity and fluids coherent.
- All Omni-generated videos will carry Google DeepMind’s SynthID invisible watermark and Google says detection tools will be added to Gemini, Chrome and Search while several partners have agreed to adopt the marker.
- Google is integrating Omni across products, including planned free access in YouTube Shorts and YouTube Create, a CapCut editing plug-in inside Gemini, and staged API and enterprise previews in the coming weeks.
- The launch ties into Google’s commerce and ad push — features like Universal Cart, new Gemini-driven ad formats and the Shopping Graph aim to keep creation, discovery and buying inside Google’s ecosystem and change how marketers serve shoppers.