Google makes Gemini Omni 1.2 Flash generally available with 15-second video
The model is cheaper per second and can now edit clips conversationally, which matters most to teams producing video ads and marketing variants.
Google has made Gemini Omni 1.2 Flash generally available across the Gemini API and Gemini for business, bringing native 15-second video generation and editing, up from 10 seconds in Omni 1.1. The model is priced at $0.07 per second for 720p video, a 30% cut from Omni 1.1, and developers can draft at 360p or 720p, make follow-up edits, then upscale to 1080p or 4K. New multi-turn conversational editing lets teams swap products, backgrounds or lighting across a clip without regenerating it, and reference adherence keeps faces, garments and brand colors consistent across angles. Provisioned Throughput is offered for enterprise use, with outputs carrying a SynthID watermark. The same model now powers Google Vids, where anyone with a Google account or Workspace subscription can make up to three 15-second videos a month at no cost.
Why it matters
For developers and businesses, the change is that longer clips and cheaper 720p output make AI video generation practical for more routine production work, while editing a clip through follow-up instructions removes the need to regenerate it each time. For ordinary users, the free tier in Google Vids brings three 15-second videos a month to anyone with a Google account. Together these shift AI video from a costly experiment toward a tool that can be used for everyday content, with the SynthID watermark marking outputs as AI-generated.
Matters or hype?
Does this story matter, or is it hype? Vote before you see what everyone else said.
Sources · 2
- Google Blog ↗ Primary source
- Google Blog ↗ Primary source