AI Models & Agents
Google releases Gemini Omni 1.2 Flash for video
The model can generate and edit clips up to 15 seconds; Google says its outputs carry SynthID watermarks.
A video creator reviews a short generated clip on a computer, with a timeline and abstract frames on screen.
Photo: Kronos News
Google Cloud has made Gemini Omni 1.2 Flash generally available for video generation and editing, with access through its cloud tools and API. Google says the model can create and revise clips up to 15 seconds long, follow image and video references, and generate scenes with dialogue and synchronized speech. [1]
Users can refine a clip through conversational instructions rather than starting over, while audio references are restricted to allowlisted users, according to Google. The company says generated videos include an imperceptible SynthID watermark. The announcement comes from Google Cloud; it does not provide an independent evaluation of output quality or performance. [1]
Editorial notes
Transparency note
AI assisted drafting. Human edited and reviewed.
- AI assisted
- Yes
- Human review
- Yes
- Last updated
Risk assessment
The product details are based on Google Cloud’s announcement and have not been independently evaluated; the article attributes capabilities and watermarking claims to Google.
Sources
Related stories
View all
Topics
About the author
Kronos News Desk covers ai models & agents and editorial analysis for Kronos News.