Gemini Omni 1.2 Flash: Make 15-Second AI Videos Free
Last updated: November 6, 2026
Short answer: 3 free 15-second videos every month: Google's Gemini Omni 1.2 Flash creates 15-second AI video clips in Google Vids at no extra cost with any Google account. The model also edits clips through conversation, costs $0.07 per second on the Gemini API, and brings 15-second videos to Gemini app Ultra subscribers.
Google's new video model makes longer AI clips and cuts the price — but the free route is not where most people look. Gemini Omni 1.2 Flash, announced on November 5, 2026, generates and edits video clips up to 15 seconds long, and anyone with a Google account can make three of them a month free in Google Vids. This guide shows what's new, which route to use, and the exact steps for the free route.
What's New in Gemini Omni 1.2 Flash
Google announced Gemini Omni 1.2 Flash on November 5, 2026, and made it generally available across the Gemini API and Gemini for business. It is the first version of Gemini Omni to reach general availability, backed by Google Cloud's enterprise infrastructure.
The headline change is length. Gemini Omni 1.2 Flash generates and edits video clips natively up to 15 seconds long, up from 10 seconds in Omni 1.1. You can pick any duration from 3 to 15 seconds in one-second steps, so a full scene, product demo or short ad fits in a single generation instead of being stitched together.
The second change is editing. You can now refine the same clip turn by turn — swap a product or background, change the lighting or weather, or switch the aspect ratio — instead of starting over from scratch. Multi-turn conversational editing works across full 15-second clips.
The third change is consistency. The model holds onto character, product and style references from the first frame to the last: faces, garments, packaging typography and brand colours stay consistent across camera angles. You can guide a clip with character, product or style images, short motion clips up to three seconds, and audio cues.
Speech is more natural too, with clearer lip-sync and distinct voices when several characters talk. Camera moves are steadier — continuous FPV flythroughs, zoom-outs and orbits with fewer unwanted jump cuts.
Gemini Omni 1.1 vs 1.2 Flash
| Gemini Omni 1.1 Flash | Gemini Omni 1.2 Flash | |
|---|---|---|
| Max clip length | 10 seconds | 15 seconds |
| Duration choices | 4, 6, 8, 10 seconds | 3 to 15 seconds, 1-second steps |
| Conversational editing | Yes | Yes, across full 15-second clips |
| Price (720p, API) | About $0.10 per second | $0.07 per second |
| Status | Retired in Flow Dec 5, 2026; API requests auto-route to 1.2 from Dec 3, 2026 | Generally available |
If you already read our Google Omni guide, this is the update to it: same model family, longer clips, cheaper price, and a free route that actually works for 15-second videos.
Which Route Should You Use?
Gemini Omni 1.2 Flash is rolling out across several Google products, and the price and limits are different on each one. Pick the route before you start, because the same 15-second clip can be free on one route and paid on another.
| Route | Who can use it | 15-second clips | Cost |
|---|---|---|---|
| Google Vids | Anyone with a Google account or Workspace subscription | Yes — up to 3 free 15-second videos a month | No additional cost |
| Google Flow | Anyone with a Google account; 15 seconds needs Plus, Pro or Ultra | Paid plans only | Credits (50 free credits a day; free accounts stay at 10 seconds) |
| Gemini app | Rolling out to Google AI Ultra subscribers | Ultra only | Included in Ultra |
| Gemini API / AI Studio | Developers, paid tier only | Yes | $0.07 per second (720p) |
| Google Ads | Advertisers | Yes | Campaign pricing |
For most readers, Google Vids is the right start: it is free, needs no subscription, and makes the full 15-second clip. Use Flow when you want multi-turn editing, Extend and upscaling. Use the API only if you are building an app. AI tools are shipping this fast everywhere — OpenAI's Dots agent brings similar AI help inside ChatGPT, and our OpenAI Dots guide shows how to set it up on phone or desktop.
How to Make a 15-Second Video Free in Google Vids
This is the free route. Google says anyone with a Google account or a Google Workspace subscription can generate up to three 15-second videos per month with Omni 1.2 Flash in Google Vids at no additional cost. The rollout takes 1 to 3 days from November 5, so if the 15-second option is not in your account yet, check again in a day or two.
- Open Google Vids on your computer (vids.new) and sign in with your Google account.
- From the start menu, select Create AI videos — or AI video in an existing video.
- In the side panel, select Create.
- Enter your text prompt with subject, location, action, camera, lighting, dialogue, sounds and tone.
- Optional: select Ingredients and upload up to 7 reference images, or select Avatar.
- Click the Omni pill and set Landscape or Portrait, then move the duration slider to 15 seconds.
- Click Generate, then Insert to add the clip to your video.
Two tips from Google's own help page: insert the clip before you close the Vids tab, because the session history disappears when the tab closes. And if a clip has no sound, check your speakers first, then check that the generated clip's track is not muted in the Vids timeline before you regenerate.
A good prompt for 15 seconds describes a short sequence, not one frozen moment. Google's Vids guidance recommends including the subject, location, action, camera, lighting, dialogue, sounds and tone. For example: "A ceramic coffee mug on a sunlit kitchen counter. Shot 1: slow push-in as coffee is poured, steam rising. Shot 2: a hand picks up the mug and the camera follows it to a window. Shot 3: wide shot of a quiet street at sunrise. Warm, soft morning light, gentle acoustic music, sound of pouring coffee."
How to Use Gemini Omni 1.2 Flash in Google Flow
Flow is where the editing tools are deepest. Open flow.google.com and sign in, open a project, then open the generation settings at the bottom of the prompt box. Choose Video, then select Omni Flash 1.2 as the model. Set orientation, number of outputs (choose 1 while experimenting, because credits are charged per video generated) and generation length.
On a free account, Flow stays at 10 seconds — 15-second generation, Extend and upscaling need a Google AI Plus, Pro or Ultra plan. Every account gets 50 Flow credits a day free. Before you generate, Google recommends checking the active model, resolution and live credit cost in the prompt-box Settings, because limits can change.
To edit a clip, select the video and describe the change in plain words — "change the lighting to a cinematic sunset", for example. Flow keeps every version in the History panel, so you never lose the original. To make a clip longer, use Extend (Plus, Pro or Ultra only): it adds 3 to 10 seconds, guided by up to 3 images.
How to Use It in the Gemini App
In the Gemini app, 15-second videos are rolling out to Google AI Ultra subscribers. Google has not published separate step-by-step instructions for the app yet, so if you are on Ultra, look for the video option in the app over the coming days. If you are on Plus or Pro and want 15-second clips today, Google Vids is the free route and Flow is the paid route.
How Much Does Gemini Omni 1.2 Flash Cost?
It depends on the route. In Google Vids, three 15-second videos a month cost nothing extra. In the Gemini app, 15-second videos are part of the Ultra plan. On the Gemini API, the model is paid tier only — the free tier is not available — at $0.07 per second for 720p video, 30% less than Omni 1.1.
Google's own pricing page bills by output tokens: $12 per million video-output tokens, at 5,792 tokens per second of 720p. That works out to about $0.70 for a 10-second clip and about $1.04 for a 15-second clip. Drafting at 360p costs about $0.023 per second, 1080p with upsampling about $0.104 per second, and 4K with upsampling about $0.209 per second. Note that 1080p and 4K are upsampled, not natively generated.
The cheapest workflow is the one Google describes in the launch post: draft at 360p or 720p, fix details with a follow-up edit instead of regenerating the whole clip, then upscale only your best take to 1080p or 4K.
What Still Doesn't Work
Google is open about the limits. Fast sports action, rapid script changes and complex physics are still works in progress — plan around those instead of spending credits on them. Google published no benchmark scores for 1.2, only side-by-side examples against 1.1, so treat the quality claims as a reason to test, not as results.
Audio references are gated behind allowlisting on Google Cloud, and the ability to change people's speech in a video is currently restricted. Every output carries an imperceptible SynthID watermark, so generated video can be identified as AI-made.
Two dates to plan around. From December 3, 2026, all API requests to gemini-omni-1.1-flash automatically route to gemini-omni-1.2-flash and are billed at 1.2 rates. On December 5, 2026, Veo 3.1 Fast, Veo 3.1 Quality and Omni Flash 1.1 are retired in Flow — finish or re-create any project on those models before then.
For still images rather than video, Google's Mixboard turns prompts into images — our Google Mixboard guide walks through it.
FAQ
Is Gemini Omni 1.2 Flash free?
On the Gemini API, no — the model is paid tier only and the free tier is not available. In Google Vids, yes — anyone with a Google account or Workspace subscription can generate up to three 15-second videos a month at no additional cost. In Flow, every account gets 50 free credits a day, but free accounts stay at 10 seconds.
How long can a Gemini Omni 1.2 Flash video be?
From 3 to 15 seconds, in one-second steps. Gemini Omni 1.1 stopped at 10 seconds.
Why can't I see the 15-second option?
The rollout takes 1 to 3 days from November 5, 2026, so check again if it has not reached your account yet. In Flow, 15-second generation needs a Google AI Plus, Pro or Ultra plan, and you must have Omni Flash 1.2 selected — not 1.1 or Veo.
What happens to Gemini Omni 1.1 on December 3, 2026?
All API requests to gemini-omni-1.1-flash automatically route to gemini-omni-1.2-flash from December 3, 2026, and are billed at 1.2 rates.
Can I edit a video I already have?
Yes. In Flow you can upload a video up to 60 seconds and 1 GB and edit it with follow-up prompts, and in Vids you can edit a clip from the side panel. Audio references need allowlisting on Google Cloud, and in Vids users in the EEA, UK, Switzerland, Illinois and Texas cannot upload and edit videos.
Do Gemini Omni videos have a watermark?
Yes. Every output carries an imperceptible SynthID watermark, so generated video can be identified as AI-made.
Sources
- Google — "Gemini Omni 1.2 Flash: 15-second video and lower pricing", November 5, 2026
- Google Cloud — "Gemini Omni 1.2 Flash now GA: cost-effective video", November 6, 2026
- Google AI Studio — Gemini Developer API pricing (Gemini Omni 1.2 Flash)
- Google Workspace — "Introducing Omni 1.2 Flash in Google Vids", November 5, 2026
- Google Flow Help — "Learn about Google Flow models & supported features"
- Google Flow Help — "Manage your Google Flow credits"
- Google Docs Editors Help — "Use AI to generate video clips in Google Vids"
Top comments (0)