Google ships Gemini Omni 1.2 Flash with 15-second video and a 30% price cut

Creators can set duration in one-second steps from 3 to 15 seconds, up from a 10-second ceiling on Omni 1.1[1]. Google pitches a draft-cheap workflow: generate at 360p or 720p, fix a detail in a follow-up edit instead of regenerating the whole clip, then upscale the keepers to 1080p or 4K[1].

Omni 1.2 Flash accepts character, product or style images, short motion clips up to three seconds, and audio cues, and Google says faces, garments, packaging type and brand colours hold across camera angles[1]. Multi-turn conversational editing lets you swap a product or background, change lighting or weather, or switch aspect ratio without starting over, across the full 15-second length[1]. Speech is more natural with clearer lip-sync and distinct multi-speaker conditioning, and continuous camera moves such as FPV flythroughs and orbits are meant to produce fewer jump cuts[1].

Enterprise and developer traffic runs on Google Cloud with Provisioned Throughput; outputs carry an imperceptible SynthID watermark[1]. On the consumer side, Google Vids now runs on Omni 1.2 Flash and gives anyone with a Google account or Workspace subscription up to three free 15-second videos a month[2]. The model is also rolling into Flow, the Gemini app for Google AI Ultra subscribers, and Google Ads campaign tools[1].

Fifteen seconds is long enough for a full social ad or product explainer in one pass, and a 30% price cut plus conversational edits makes iteration cheaper than regenerating every variant. Putting the same model behind the API, Cloud, Vids and Ads also means the creative loop and the production loop finally share one generator[1][2].