Gemini Omni 1.2 Flash Launched: 15-Second AI Videos at a 30% Lower Price

Google has just made its newest AI video model available to everyone who builds with its tools, and it is a bigger step than a version number suggests. Unfite brings you the full details of Gemini Omni 1.2 Flash, the model that stretches AI video clips to 15 seconds, lets you edit them by talking to it, and costs 30 percent less than the version it replaces.

Announced on November 5, 2026, Gemini Omni 1.2 Flash is now generally available across the Gemini API and Gemini for business. It is Google’s video generation and editing model, and this is the first time the Omni line has reached general availability with Google Cloud’s enterprise-grade infrastructure behind it.

What Is Gemini Omni 1.2 Flash?

Gemini Omni 1.2 Flash is Google’s model for creating and editing video from text, images and video, with native audio built in. You describe a scene, give it reference images or a short clip, and it returns a finished video with sound. The model ID developers need is gemini-omni-1.2-flash.

The “Flash” name matters. This is the fast, cost-effective member of Google’s video family, aimed at people who need many clips quickly — businesses, developers and creators producing videos at scale — rather than one slow, expensive render.

Longer Clips: 15 Seconds Instead of 10

The headline change is length. You can now generate and edit videos natively up to 15 seconds long, up from 10 seconds with Omni 1.1. You can also pick the exact duration in one-second steps, from 3 to 15 seconds.

That may sound small, but it changes what a single generation can hold. Google says the extra five seconds give you room to tell a complete story, create a product explainer, or produce a full social ad spot in one generation, instead of stitching short clips together. You can also interpolate between a first and last keyframe, and extend a clip to build a longer sequence, with products, characters and settings staying consistent from shot to shot.

A 30 Percent Lower Price

The second headline is cost. Google has dropped the price 30 percent from Gemini Omni 1.1, making 1.2 Flash available at $0.07 per second for 720p video. On the API’s token pricing, video output now costs $12 per 1 million tokens, down from $17.50, with input at $1.50 per 1 million tokens.

The workflow itself is designed to keep costs down too. You can draft fast at 360p or 720p, fix a detail with a follow-up edit instead of re-generating the entire clip, and then upscale only your best creations to 1080p or 4K. For anyone generating video in bulk, that draft-first approach is where the real saving sits.

Edit by Talking: Multi-Turn Conversational Editing

The most useful change for everyday creators may be the editing. You can refine the same clip turn by turn — swapping a product or background, changing the lighting or weather, or switching the aspect ratio — instead of starting over from scratch. Multi-turn conversational editing works across full 15-second clips.

That means one generated clip can become many ad variants for different audiences and placements, without a fresh brief or a fresh render each time. Google gives the example of starting from one clip and swapping the background turn by turn — from a striped pavilion tent to an oak forest, a stable with a white horse, a market fair, and a stone castle — while keeping both characters’ performances, armor reflections and camera framing intact.

Better Reference Adherence and Consistency

Gemini Omni 1.2 Flash also holds onto your references better. You can guide generation by combining character, product or style images, short motion clips of up to three seconds, and audio cues, and the model keeps those details from start to finish. Reports say it supports up to six reference images. Faces, garments, packaging typography and brand colours stay consistent across camera angles.

Google says the model delivers stronger character, object and scene consistency from the first frame to the last, with less visual drift or morphing across motion and camera transitions. In one of its own examples, combining one model photo with front-and-back product shots of three outfits produces a 15-second virtual try-on sequence across 360-degree turns and match cuts, while keeping the model’s identity and each garment’s cut, drape and back details consistent. That is exactly the kind of job — catalog spins, virtual try-ons and branded video ads — that businesses will use it for.

More Natural Speech and a Cinematic Look

Dialogue gets better too. Google says you can generate scenes with more fluid, natural-sounding dialogue, clearer lip-sync and distinct multi-speaker conditioning, whether you are directing multi-character dialogue in Flow, creating video explainers, or making polished videos with avatars, music and narration in Google Vids.

Camera work is more controllable as well. You can direct complex, continuous camera movements — sweeping FPV flythroughs, dramatic zoom-outs and orbits — with significantly fewer unwanted jump cuts, steadier scale and a more polished, cinematic look. In Google’s example, guided by two architectural reference photos, the model directs one continuous FPV drone flight across a piazza, through bronze doors, and up through the Pantheon’s coffered dome to the oculus, with zero jump cuts.

Gemini Omni 1.2 Flash vs Omni 1.1 Flash

FeatureOmni 1.1 FlashOmni 1.2 Flash
Maximum clip length10 seconds15 seconds
Duration choicesFixed steps3 to 15 seconds, in 1-second steps
Price (720p)About $0.10 per second$0.07 per second (30% lower)
Video output pricing$17.50 per 1M tokens$12 per 1M tokens
Conversational editingLimitedMulti-turn, across full 15-second clips
Reference followingBasicEnhanced, up to 6 reference images (per reports)
AvailabilityPreview / limitedGenerally available

Where You Can Use It Today

Google is rolling Gemini Omni 1.2 Flash out across its products and developer platforms:

  • Developers: prototype in Google AI Studio, use the Gemini API, and build with Vertex AI on Google Cloud.
  • Businesses: try it in the Google Cloud console, with Provisioned Throughput available for scale.
  • Everyone: direct scenes and make multi-turn edits in Flow, generate 15-second clips at no additional cost in Google Vids with a Google account or Google Workspace subscription, create 15-second videos in the Gemini app (rolling out to Google AI Ultra subscribers), and scale video campaigns in Google Ads.

Outputs carry an imperceptible SynthID watermark, so AI-generated video can be identified later. That matters as these tools reach more creators and more feeds.

What Changes on December 3 and December 5

Two dates are worth noting if you already use Google’s video tools. From December 3, 2026, requests to gemini-omni-1.1-flash will automatically route to 1.2 Flash and be billed at the lower 1.2 rates, so old code keeps working at the new price. And in Flow, the older Veo 3.1 Fast, Veo 3.1 Quality and Omni Flash 1.1 models retire on December 5, 2026, while Veo Extend was already retired on November 5. If you have saved prompts or workflows on the older models, this is the moment to move them over. See Google’s official launch post for the full announcement.

Pros and Cons

Pros: longer 15-second clips with native audio; 30 percent lower price; edit by conversation instead of re-rendering; stronger consistency for faces, products and brands; available across the Gemini app, Flow, Vids and the API; SynthID watermarking built in.

Cons: the API itself has no free tier, so testing at scale costs money; 15-second clips still need human review for continuity, audio, rights and factual accuracy; Google has published no benchmarks for its quality claims, so treat the consistency and lip-sync improvements as claims to test; fast sports action, rapid script changes and complex physics are still being improved, by Google’s own admission.

What This Means for Indian Creators

For Indian creators and small businesses, the practical story is cost and access. Short product videos, reels and ad spots are the daily work of thousands of sellers and creators, and a model that makes a 15-second clip for about a dollar at 720p, then lets you re-cut it by chatting, lowers the barrier to professional-looking video. The Gemini app and Google Vids routes matter most here, since they need no API key or code — though the Gemini app’s 15-second generation is rolling out first to Google AI Ultra subscribers, and Vids access depends on your Google account or Workspace plan. Unfite will keep an eye on when the wider Gemini app rollout reaches more users in India.

It is also worth keeping the AI race in view. OpenAI’s ChatGPT Images 2.6 update, covered earlier on Unfite, brought GIF creation and saved reference images to still images — Google is now answering on the video side, with longer clips and cheaper generation. The two tools do different jobs, but together they show where AI creation is heading: faster, cheaper, and edited in plain language.

Frequently Asked Questions

What is Gemini Omni 1.2 Flash?

Gemini Omni 1.2 Flash is Google’s generally available AI video generation and editing model, released on November 5, 2026. It creates and edits video clips with native audio from text, images and video, with the model ID gemini-omni-1.2-flash.

How long can Gemini Omni 1.2 Flash videos be?

Clips can be 3 to 15 seconds long, with the exact duration selectable in one-second steps. That is up from a 10-second maximum in Omni 1.1 Flash. You can also interpolate between first and last frames and extend a clip to build a longer sequence.

How much does Gemini Omni 1.2 Flash cost?

Google lists $0.07 per second for 720p video, which is 30 percent cheaper than Omni 1.1. On API token pricing, video output is $12 per 1 million tokens, down from $17.50. The API itself is on the paid tier only, with no free tier.

Where can I use Gemini Omni 1.2 Flash?

In the Gemini API and Google AI Studio for developers, in Vertex AI and the Google Cloud console for businesses, and in Flow, Google Vids, the Gemini app (rolling out to Google AI Ultra subscribers) and Google Ads for everyone else.

What happens to Gemini Omni 1.1 Flash?

From December 3, 2026, requests to gemini-omni-1.1-flash are automatically routed to 1.2 Flash at the new, lower rates. In Flow, Omni 1.1 and the Veo 3.1 models retire on December 5, 2026.

Google has not published benchmarks for the new model’s quality claims, and it says work continues on fast sports action, rapid script changes and complex physics. Even so, a longer clip, a lower price and editing by conversation make Gemini Omni 1.2 Flash the most practical AI video upgrade Google has shipped this year — and for creators watching costs, that combination is hard to ignore.

Image Credit: Google — Official Gemini Omni 1.2 Flash image via the Google Blog

Leave a Comment