Summary
Google says Gemini Omni 1.2 Flash can generate and edit videos up to 15 seconds, with conversational revisions and improved handling of visual and audio references. The company says 720p generation now costs $0.07 per second, 30% less than with Omni 1.1.
Google announced Gemini Omni 1.2 Flash on Nov. 5, 2026, adding video generation and editing for clips up to 15 seconds. The company says the model also follows visual and audio references more consistently, supports conversational revisions and costs 30% less than Omni 1.1. Its listed price for 720p video is $0.07 per second.
Longer clips and reference-guided generation
Omni 1.2 Flash can generate or edit videos from 3 to 15 seconds long, with duration selectable in one-second increments. Omni 1.1 supported clips up to 10 seconds, according to Google. The longer duration gives creators more room to make a complete short sequence in one generation rather than dividing it into separate clips.
The model can take character, product or style images, motion clips of up to three seconds, and audio cues as references. Google says it has improved the consistency of details such as faces, clothing, packaging and brand colours across frames, camera angles and transitions. The company also describes better continuity between a clip’s opening and closing frames, with less visual drift as scenes move.
These are capabilities and performance claims from Google, illustrated in the announcement with company-provided examples. The source describes uses including product explainers, virtual try-ons and branded video ads.
Edits can build on an existing clip
A user can revise a generated clip through follow-up prompts—for example, changing a background, product, lighting, weather or aspect ratio—rather than generating the whole video again. Google says multi-turn editing works across clips up to 15 seconds. That makes it possible to create variations from an existing sequence while retaining elements such as character performances and camera framing.
Google presents this iterative workflow as a way to manage generation costs: creators can draft at 360p or 720p, make a targeted edit, then upscale selected results to 1080p or 4K. The company has reduced the model’s price by 30% from Omni 1.1; the stated 720p rate is $0.07 per second.
The announcement also describes more natural-sounding dialogue, clearer lip-sync, support for distinct voices across speakers, and more continuous camera movements. Google says the model is intended for business, developer and creator workflows. It notes that work is continuing on fast sports action, rapid script changes and complex physics.
Availability across Google products
Google says Omni 1.2 Flash is generally available through the Gemini API and Gemini for business. Developers can prototype in Google AI Studio, while businesses can access it through the Google Cloud console. Provisioned Throughput is also available, and Google says generated outputs carry an imperceptible SynthID watermark.
The company is rolling the model into other products as well. Google Vids offers 15-second clips at no additional cost to users with a Google account or Google Workspace subscription. Creation of 15-second videos in the Gemini app is rolling out to Google AI Ultra subscribers. Google also lists Flow and Google Ads among the products where the model’s capabilities are available or rolling out.