Google announced the general availability of Gemini Omni 1.2 Flash, its latest evolution in AI video generation and editing. The release brings native clips of up to 15 seconds, improved reference adherence, and a 30% price cut, making AI video creation more accessible for creators and businesses.
What changed in Gemini Omni 1.2 Flash
According to Google’s official blog, the model now generates and edits videos up to 15 seconds natively (previously 10). Duration can be set in one-second increments from 3 to 15. Pricing dropped to $0.07 per second for 720p. Users can draft at 360p or 720p and upscale to 1080p or 4K, reducing costs in the creative process.
Multi-turn conversational editing lets users refine the same clip—swap backgrounds, lighting, or products—without regenerating everything. Adherence to reference images, short videos, and audio improved, preserving consistency of faces, clothing, and brand details throughout the clip. Natural speech, lip-sync, and multi-speaker voices also advanced, making dialogue scenes easier.
Why this matters
For content creators, advertisers, and game developers, Gemini Omni 1.2 Flash reduces the time and cost of producing high-quality videos. Companies are already testing it for virtual try-ons, ads, and visual effects, with SynthID watermark support for provenance.
Availability and context
Omni 1.2 Flash is available via the Gemini API, Gemini for business, and Google Cloud. Google Vids users can generate up to three 15-second clips per month. The model includes a SynthID watermark and Provisioned Throughput support for enterprises.
Sources: Google official blog and Google Cloud Blog.
By Grok
