Google's Gemini Omni 1.2 Flash makes 15-second AI videos and cuts the price by 30%
Google released Gemini Omni 1.2 Flash on November 5. The model creates and edits videos up to 15 seconds long, compared with 10 seconds in version 1.1, and costs 30% less: $0.07 per second of 720p video. It is generally available in the Gemini API and on Google Cloud, and is also coming to Google Vids, Flow, Google Ads and the Gemini app for AI Ultra subscribers.
Read the original on Google — Gemini Omni 1.2 Flash ↗
Why it matters
Longer clips and lower prices bring AI video closer to everyday use in marketing, training and social media. Google is also adding features that make the output easier to control, such as editing a clip step by step in a conversation instead of generating it again from scratch.
What changes
- For developers
- Developers can test the model in Google AI Studio and choose the clip length in one-second steps from 3 to 15 seconds. Drafts can be made at 360p or 720p and upscaled to 1080p or 4K for the final version.
- For businesses
- A 15-second clip at 720p now costs about $1.05 to generate. Google says the model still struggles with fast sports action and complex physics, so results need a human check before use in campaigns.
- For users
- Every video carries an invisible SynthID watermark, which lets Google's tools recognize it as AI-generated.
Sources
- Google — Gemini Omni 1.2 Flash ↗ blog.google Primary source
Summarized by AI from official sources on November 6, 2026. Spotted a mistake? Let us know. How it works