Google has made Gemini Omni 1.2 Flash generally available, turning its AI video model into a production-ready tool for developers and businesses. The release, announced on November 5 by Google DeepMind product manager Anish Nangia, stretches native video clips to 15 seconds, adds multi-turn conversational editing, and cuts the price 30% from the previous version.

It is the first time Gemini Omni has reached general availability, backed by Google Cloud infrastructure and enterprise-grade security. The model is available through the Gemini API, Gemini for business, and Google Cloud.

The headline change is length. Gemini Omni 1.2 Flash can generate and edit video natively up to 15 seconds long, up from 10 seconds with Omni 1.1, and creators can specify the duration in one-second increments from 3 to 15 seconds. That is enough room for a complete product explainer or a full social ad spot in a single generation.

Longer clips, cheaper to make

Along with the longer clips comes a lower price. Google has dropped the cost 30% from Gemini Omni 1.1, to $0.07 per second for 720p video. The workflow is designed to keep costs down further: creators can draft quickly at 360p or 720p, fix a detail with a follow-up edit instead of re-generating the whole clip, and then upscale their best work to 1080p or 4K.

The model also holds references together better across a clip. Creators can guide generation with character, product, or style images, short motion clips, and audio cues, and the model keeps faces, garments, and brand colours consistent from the first frame to the last.

Edit in conversation, not from scratch

The other big change is how editing works. Instead of starting over when something is wrong, creators can refine the same clip turn by turn in conversation, swapping a product or background, changing the lighting or weather, or switching the aspect ratio. Multi-turn conversational editing works across full 15-second clips, so one generated scene can be reworked into ad variants for different audiences without a fresh brief.

Speech gets an upgrade too, with more fluid, natural-sounding dialogue, clearer lip-sync, and distinct multi-speaker conditioning in multi-character scenes. Camera work is steadier as well: Google says the model directs complex, continuous movements such as sweeping FPV flythroughs with significantly fewer unwanted jump cuts. Every output carries an imperceptible SynthID watermark, so generated clips remain identifiable as synthetic.

Where you can use it, and what is still missing

Gemini Omni 1.2 Flash is rolling out across Google's products and developer platforms. Developers can prototype in Google AI Studio and build with the Gemini API, businesses can use it in the Google Cloud console, and consumers can direct scenes in Flow, generate 15-second clips at no additional cost in Google Vids, and create 15-second videos in the Gemini app, where the feature is rolling out to Google AI Ultra subscribers. It is also available for scaling video campaigns in Google Ads.

Google is open about the limits. Development continues on fast sports action, rapid script changes, and complex physics, and audio-reference input remains gated behind an allowlist rather than open to everyone. Google's help pages also note that 15-second clips in Flow need a Google AI Plus, Pro, or Ultra plan, with free accounts staying at 10 seconds, and that video editing and avatar creation are unavailable in the EEA, Switzerland, the United Kingdom, and some US states.

Even with those caveats, the release marks a shift in how Google positions AI video: no longer a preview or an experiment, but a priced, supported service that businesses can build production workflows around.

By Hamza Faisal