Google Launches Gemini Omni 1.2 Flash With 15-Second AI Video Generation And 30% Lower Pricing

Google has introduced Gemini Omni 1.2 Flash, an updated generative AI video model that supports clips up to 15 seconds long, improved visual consistency, and more advanced editing capabilities. The company has also reduced pricing by 30% compared with Gemini Omni 1.1, bringing the cost of generating 720p video to $0.07 per second.

Announced on November 5, 2026, Gemini Omni 1.2 Flash is generally available through the Gemini API and Gemini for business, with availability expanding across Google’s broader product ecosystem.

The release is designed to make AI-powered video production more affordable and accessible for businesses, developers, advertisers, and content creators.

One of the most significant improvements is the extension of native video generation from 10 seconds to 15 seconds.

Users can specify video durations in one-second increments ranging from three to 15 seconds, providing greater flexibility for creating advertisements, product demonstrations, educational content, and short-form videos.

Google has also introduced a more cost-effective production workflow that allows users to generate initial drafts at 360p or 720p before upscaling selected outputs to 1080p or 4K.

Rather than regenerating an entire video when changes are needed, users can refine existing clips through conversational editing.

The feature supports adjustments to backgrounds, products, lighting, weather conditions, and aspect ratios while maintaining the underlying video sequence.

This capability is intended to simplify the development of multiple advertising variations and reduce the computing costs associated with repeated generations.

Gemini Omni 1.2 Flash also delivers improvements in reference adherence, allowing users to guide generation using character images, product photography, stylistic references, short motion clips, and audio cues.

The model supports motion references up to three seconds long and is designed to maintain consistency in facial features, clothing, packaging, typography, and brand colors throughout generated videos.

These improvements could benefit businesses producing virtual product demonstrations, clothing try-on videos, branded advertising, and e-commerce content.

Google highlighted the model’s ability to create a 15-second virtual try-on sequence using a model photograph and product images of several outfits.

The system can also maintain greater consistency across different camera angles and transitions, reducing unwanted changes in characters, objects, and environments.

Another enhancement involves speech generation.

Gemini Omni 1.2 Flash supports more natural dialogue, improved synchronization between speech and facial movements, and more distinct voices for multiple speakers.

These capabilities are intended to support AI-generated explainers, marketing videos, character dialogue, and professional productions involving virtual presenters.

The model also provides greater control over cinematic camera movements.

Users can generate complex continuous sequences, including first-person flythroughs, dramatic zoom-outs, and orbiting camera movements, with fewer unwanted cuts and more consistent visual scale.

Google demonstrated the technology through examples involving architectural environments, animated sequences, and motion transfer between different subjects.

Businesses and creative organizations are already experimenting with Gemini Omni 1.2 Flash in production workflows.

Google identified Adobe, Monks, Havaianas, and Whering among organizations working with the technology.

Adobe plans to incorporate the updated model into Firefly, providing users with longer video outputs and improved consistency when using reference images.

Creative production company Monks has been testing the model for visual effects and controllable video generation.

Whering, a fashion technology company, has evaluated the model’s capabilities for accurately representing clothing and fabrics in virtual styling applications.

Google is also supporting enterprise adoption through Google Cloud infrastructure, including Provisioned Throughput for organizations requiring predictable computing capacity.

Generated outputs carry an imperceptible SynthID watermark intended to identify AI-generated content.

Gemini Omni 1.2 Flash is available for developers through Google AI Studio and the Gemini API, while businesses can access it through Google Cloud.

The technology is also being integrated into Flow, Google Vids, the Gemini app, and Google Ads.

Google Vids users can generate 15-second clips at no additional cost with a Google account or Google Workspace subscription, while access through the Gemini app is rolling out to Google AI Ultra subscribers.

Google acknowledged that further development is needed to improve performance in areas including fast-moving sports footage, rapid changes in scripted scenes, and complex physical interactions.

With longer clips, lower pricing, and improved editing capabilities, Gemini Omni 1.2 Flash represents Google’s latest effort to expand the commercial use of generative video technology across advertising, entertainment, e-commerce, and enterprise content creation.