Google launches Gemini Omni 1.2 Flash for native video with audio

Google launched Gemini Omni 1.2 Flash (`gemini-omni-1.2-flash`) in AI Studio and the Gemini API: native video with audio, clips from 3 to 15 seconds, multi-turn edit and extend through the Interactions API, up to six reference images, and a stated 30% cut vs Omni 1.1 (~$0.07 per second at 720p on the paid tier, plus inputs). Google Vids gives up to three 15-second videos a month free; Gemini app access is rolling out to Ultra. Docs restrict editing uploaded user video in the UK, EEA and Switzerland, and say audio-reference uploads are unsupported even though the promo video shows voice refs. Blog and API docs disagree on Provisioned Throughput. Fact or hype: Fact for the documented launch — not a hands-on quality verdict. The 25-second AI Studio promo is a mock UI showcase, not a live session.

Why it mattersUseful if you ship on Gemini video: longer clips and cheaper 720p output are the concrete changes. Read the regional and audio-reference limits before promising voice-matched characters from uploads. We have not tested it hands-on.

Curated by Sara Simeone as part of our human editorial coverage. The original sources are linked below; curation is distinct from a Hype or Fact? assessment.

SHARE THISPost on X ↗Share on LinkedIn ↗Copy link

How we knowCompany figures are labelled as their own claims; anything we couldn't verify is labelled as a report or a claim.