Google's Gemini Omni 1.2 Flash makes 15-second AI videos for 30% less
Longer 15-second clips and chat-style edits, at $0.07 per second of 720p video for developers. Where regular users can try it.
The skim
- Google's Gemini Omni 1.2 Flash makes AI video clips up to 15 seconds, up from 10 seconds in Omni 1.1, and costs 30% less.
- For developers it's $0.07 per second of 720p video, so a full 15-second clip is about $1.05 at that rate.
- For everyone else: 15-second clips are rolling out in Google Vids at no extra cost, in Flow, and in the Gemini app for Google AI Ultra subscribers.
What's new
Google said on Nov. 5 that Gemini Omni 1.2 Flash is generally available through the Gemini API and Google Cloud. The company lists these changes from Omni 1.1:
- Longer clips: 3 to 15 seconds, in one-second steps.
- Edit by conversation: fix a detail with a follow-up request instead of generating the whole clip again.
- Better reference following: Google says images, video and audio references are followed more closely, which helps keep products and characters consistent.
- Speech: Google Cloud says scenes can have more natural dialogue and clearer lip-sync.
- Draft cheap, finish sharp: draft at 360p or 720p, then upscale to 1080p or 4K.
Where you can use it
Google says you can direct scenes and multi-turn edits in Flow, generate 15-second clips in Google Vids with a Google account or Workspace subscription at no additional cost, and create 15-second videos in the Gemini app, which is rolling out to Google AI Ultra subscribers. It's also coming to Google Ads. The Google Cloud model page lists support for 16:9 and 9:16 video.
The fine print
- Google says fast sports action, rapid script changes and complex physics still need work.
- Outputs carry an imperceptible SynthID watermark, and the Google Cloud model page lists support for C2PA content credentials.
- The price drop applies to the developer and business API. Consumer plans have their own limits.
Sources: Google blog, Google Cloud blog, Google Cloud docs, MarkTechPost.