Google's new Gemini video model makes 15-second clips
Google DeepMind says Gemini Omni 1.2 Flash makes longer clips, supports follow-up edits and costs 30% less than the previous version, at $0.07 per second.

The facts
- According to Google DeepMind, Gemini Omni 1.2 Flash can generate and edit video up to 15 seconds long, up from 10 seconds with Omni 1.1. Length can be set in one-second steps from 3 to 15 seconds.
- The price is down 30% from Omni 1.1, at $0.07 per second for 720p video. Users can draft at 360p or 720p, then upscale the best clips to 1080p or 4K.
- Multi-turn conversational editing lets users change a product, background, lighting or aspect ratio on the same clip without regenerating it. Reference images, short motion clips and audio cues can guide the output.
- It is generally available in the Gemini API and Gemini for business, and is also rolling out in Google Vids and Flow. Outputs carry an imperceptible SynthID watermark, and Google says fast sports action and complex physics still need work.
Case notes · Danny's take
Why it matters
The headline is the clip length. The real story is the edit loop. Fixing one detail with a follow-up prompt, instead of paying to regenerate the whole clip, is what turns AI video from a demo into a production tool. A 30% price cut pushes the same way, towards ad variants made in bulk. Google also admits where it still struggles, and that is worth reading as closely as the launch claims.
For builders
If you build ad, e-commerce or content tools, the product try-on, catalogue spin and ad-variant use cases are the obvious fit. Do the maths at $0.07 per second before you build: a 15-second 720p clip works out at roughly $1.05. Test the consistency claims on your own product images before promising clients anything.
Not financial advice. Do your own investigation.
This story was summarised with AI from Google DeepMind's reporting and checked against our editorial policy. Danny's take reflects his views. Disclaimer.
