Google’s Gemini Omni 1.2 Flash makes 15-second AI videos

Google has released Gemini Omni 1.2 Flash, an updated version of its video generation and editing model from Google DeepMind. The headline changes are longer clips, a lower price and editing by conversation: it generates and edits videos up to 15 seconds with synchronized audio, and Google says the price is 30% lower than Omni 1.1.

Google announced it on November 5 and says the model is now generally available in the Gemini API and on Google Cloud.

Google’s launch video

Google posted the announcement with a launch video on its official X account:

Meet Gemini Omni 1.2 Flash, our updated video generation model from @GoogleDeepMind 🎬

Get stronger consistency, more creative control, and faster, more cost-effective video creation at scale:

⚡ Fast & 30% lower cost: Draft at 360p or 720p ($0.07/s) and upscale to 1080p or 4K

⏱️ Longer clips: Generate and edit videos up to 15s, or pick any exact length from 3s to 15s

💬 Edit in conversation: Swap backgrounds, subjects, or lighting turn by turn without starting over from scratch

🗣️ More natural speech: Create fluid, multi-speaker dialogue with clearer lip-sync

🎬 More controllable shots: Direct continuous camera moves with fewer jump cuts

— Google (@Google) November 5, 2026

We did not find a launch video on Google’s or Google DeepMind’s YouTube channels when we checked on November 6. Google’s blog post includes demo clips that it says were made with the model. Two of them are below.

In this one, Google says Omni 1.2 Flash used two reference photos of the Pantheon in Rome to direct one continuous drone-style flight across the square, through the bronze doors and up to the dome’s opening, with no jump cuts:

And in this one, Google says it combined one model photo with front-and-back shots of three outfits to make a 15-second virtual try-on sequence, keeping the model’s identity and each garment’s details consistent:

These are Google’s own showcase examples, not tests we ran.

What is new

Google lists these changes over Omni 1.1:

• Longer clips. Videos can now run up to 15 seconds, up from 10, and you can choose any length from 3 to 15 seconds in one-second steps.
• Lower price. Google says it cut the price by 30%, to $0.07 per second of 720p video.
• Editing in conversation. You can change the same clip turn by turn, such as swapping a product or background, changing the lighting or weather, or switching the aspect ratio, without generating it again from scratch. Google says this works across full 15-second clips.
• Better reference following. You can steer a video with character, product or style images, short motion clips of up to three seconds, and audio cues. Google says faces, clothing, packaging text and brand colors now stay consistent across camera angles.
• More consistency. Google says characters, objects and scenes drift and morph less from the first frame to the last, including when extending a clip or joining a first and last frame.
• More natural speech. Google cites more fluid dialogue, clearer lip-sync and better handling of several speakers.
• Steadier camera moves. Long, continuous moves such as drone-style fly-throughs, zoom-outs and orbits come with fewer unwanted jump cuts, according to Google.

Google also names what it is still working on: fast sports action, rapid script changes and complex physics.

The specifications

From Google Cloud’s model card for gemini-omni-1.2-flash:

Price

The Gemini API bills the model by output tokens: $12 per million for video, with input at $1.50 per million. Google’s pricing page converts that into a per-second price:

Google gives the 720p figures directly. The other 10-second prices are our arithmetic from its per-second rates. A full 15-second clip at 720p costs about $1.04, according to Google. The model is not on the API’s free tier. Google’s suggested workflow keeps costs down: draft at 360p or 720p, fix details with follow-up edits instead of starting again, then upscale only the clips you keep.

Developers on the older model should note one change: from December 3, 2026, API requests to gemini-omni-1.1-flash will be routed to Omni 1.2 Flash and billed at its rates.

Where you can use it

According to Google’s announcement:

• Developers: the Gemini API, with prototyping in Google AI Studio.
• Businesses: Google Cloud, with the option of reserved capacity (Provisioned Throughput).
• Google Vids: 15-second clips at no additional cost with a Google account or a Google Workspace subscription.
• Flow: Google’s filmmaking tool, for directing scenes and multi-turn edits.
• Gemini app: 15-second videos, rolling out to Google AI Ultra subscribers.
• Google Ads: for video campaigns.

What it means for working professionals

• Marketers and small businesses: 15 seconds is enough for a short social ad or product clip in one generation, and conversational edits make it cheaper to produce versions for different audiences. Google Vids’ no-extra-cost clips are the easiest place to try it.
• E-commerce and fashion: the virtual try-on and product-spin examples are aimed squarely at catalogue work. Check every frame for accuracy before publishing, since a garment detail that drifts is a product description that is wrong.
• Teachers and trainers: short explainers with narration are now within reach, but treat any on-screen text and figures as a draft to check.
• Anyone publishing the results: Google says outputs carry a SynthID watermark and support Content Credentials. That helps platforms identify AI video, but it does not replace telling your audience.

We have not tested Omni 1.2 Flash ourselves. Everything above comes from Google’s announcement, model card and pricing page. For a hands-on look at a rival tool for short animated clips, see our review of ChatGPT Images 2.6, and for Google’s latest frontier model, our report on Gemini 4 Carbon.