Google Launches Gemini Omni 1.2 Flash With 15-Second AI Video Clips and a 30% Price Cut
Google has released Gemini Omni 1.2 Flash, a new version of its AI video generation model that produces clips up to 15 seconds long, adds conversational editing, and costs 30 percent less than the model it replaces. The company announced the release on November 5, 2026, and made the model generally available across the Gemini API and Gemini for business the same day.
For anyone producing short video with AI tools, the update matters because it attacks the two limits that have held AI clips back: length and cost. A 15-second clip is long enough for a complete product explainer or a social ad spot in a single generation, and at $0.07 per second for 720p video, a full-length clip costs about $1.05.
What changed from Omni 1.1
The headline change is duration. Gemini Omni 1.2 Flash can generate and edit videos natively up to 15 seconds long, up from 10 seconds with Omni 1.1. Users can specify the length in one-second increments from 3 to 15 seconds, which gives creators room to match a clip to a specific placement instead of trimming or padding afterward.
The second major change is multi-turn conversational editing. Instead of regenerating an entire clip when something is wrong, users can refine the same clip turn by turn, for example by swapping a product or background, changing the lighting or weather, or switching the aspect ratio. Google says this editing works across the full 15-second length, which makes it practical to produce ad variants for different audiences and placements from one starting clip.
The third change is reference adherence. The model accepts character, product, or style images, short motion clips of up to three seconds, and audio cues as inputs, and Google says it holds onto those details from start to finish. Faces, garments, packaging typography, and brand colors are meant to stay consistent across camera angles.
Consistency, dialogue, and camera control
Google also claims stronger visual consistency across the whole clip, with less visual drift or morphing across motion and camera transitions. That matters for longer shots in particular, since a character or product that changes appearance halfway through a clip is unusable for commercial work.
Dialogue is another area of improvement. The model is designed to produce more fluid, natural-sounding speech with clearer lip-sync and distinct multi-speaker conditioning, so each sampled voice is routed to the right character in a scene with several speakers. Google says this shows up in multi-character dialogue in Flow, video explainers in Gemini for business, and avatar-led videos in Google Vids.
Camera work gets more controllable as well. Users can direct complex, continuous camera movements such as sweeping FPV flythroughs, dramatic zoom-outs, and orbits, with significantly fewer unwanted jump cuts. Google illustrates this with a single continuous FPV drone flight across a piazza, through bronze doors, and up through a domed ceiling, with zero jump cuts.
Pricing and workflow
The pricing change is straightforward: Gemini Omni 1.2 Flash costs $0.07 per second for 720p video, which Google says is 30 percent below Gemini Omni 1.1. The workflow is designed to keep costs down further. Creators can draft fast at 360p or 720p, fix a detail with a follow-up edit instead of regenerating the entire clip, and then upscale only the best creations to 1080p or 4K.
The model is rolling out across Google products and developer platforms. Developers can prototype in Google AI Studio and use the Gemini API, businesses can try it in the Google Cloud console, and consumers can direct scenes and multi-turn edits in Flow, generate 15-second clips in Google Vids with a Google account or Google Workspace subscription, create 15-second videos in the Gemini app as it rolls out to Google AI Ultra subscribers, and scale video campaigns in Google Ads. For business users, Google notes that Provisioned Throughput is available and that outputs carry an imperceptible SynthID watermark identifying them as AI generated.
Why it matters
AI video tools have been converging on the same formula: longer clips, lower prices, and editing that behaves more like a conversation than a slot machine. Gemini Omni 1.2 Flash pushes on all three at once. The 15-second ceiling and the conversational editing workflow are the parts most likely to change how teams actually work, because they reduce the two most expensive habits in AI video production: regenerating whole clips to fix one detail, and stitching short fragments into something that looks like a finished spot.
The release also sharpens competition in a crowded field. Every major AI video model now has to answer the same questions: how long can a clip run, how much does a second cost, and how reliably does a character or product survive from the first frame to the last. Google answer is 15 seconds, $0.07 per second at 720p, and a reference system built to hold details across the whole clip. Google itself notes that development is ongoing on fast sports action, rapid script changes, and complex physics.
For creators and small teams, the practical takeaway is simple: 15-second clips for about a dollar each, with editing that lets you fix a scene instead of starting over. That combination makes AI video a more realistic option for everyday marketing work, not just experiments.
