Gemini Omni 1.2 Flash Release
Google has launched Gemini Omni 1.2 Flash, introducing native 15-second video generation and a 30 percent price reduction for developers and enterprise customers.
The model is now available through the Gemini API and Google AI Studio. Enterprise customers can access it via the Google Cloud console.
Pricing and Resolution Details
Generating video at 360p or 720p resolution now costs $0.07 per second. A full 15-second generation at this rate amounts to $1.05.
introducing gemini omni 1.2 flash, now available in ai studio and the gemini api what's new: – fast & 30% lower cost – longer clips – edit in conversation – more natural speech – more controllable shots pic.twitter.com/ipHJr5hYnN
Users can draft content at lower resolutions before upscaling finished outputs to 1080p or 4K. This workflow keeps operating costs down by avoiding full regenerations for minor fixes.
Conversational Editing and References
The updated model supports multi-turn conversational editing across full 15-second clips. Users can swap products or backgrounds, adjust lighting, and change aspect ratios without starting from scratch.
“The first generation is a starting point. Professional teams need precision to get from there to a finished shot,” said Omar Pera, CPO at Magnific.
Creators can guide generation by combining character, product, or style images with short motion clips of up to three seconds and audio cues. The system maintains consistent faces, garments, packaging typography, and brand colors across different camera angles.
“In Figma Weave, teams can direct an entire video sequence from a single generation, then refine it with references and branching versions on the canvas,” said Itay Schiff, Creative Director of Figma Weave.
Platform Integrations and Audio Updates
Google Vids now incorporates the model, giving eligible users with a Google account or Workspace subscription an allowance of three free 15-second videos per month. The model also integrates with Flow.
Audio generation features clearer lip-sync, more natural-sounding dialogue, and distinct multi-speaker conditioning.
Current limitations in physics and scale
Google acknowledges that developers are still working on fast sports action, rapid script changes, and complex physics.
The model is expanding to the Gemini app for Google AI Ultra subscribers.
What users ask about Gemini Omni 1.2 Flash
What is the maximum video length for Gemini Omni 1.2 Flash?
The model supports continuous video clips of up to 15 seconds, an increase from the 10-second limit in Gemini Omni 1.1. Users can select durations in one-second increments between three and 15 seconds.
Meet Gemini Omni 1.2 Flash ⚡️ We’ve made the model more cost-effective, bumped the video generation and editing limit up to 15 seconds, and made updates to how scenes hold together over time. We've also given character speech an upgrade, reduced visual glitches like jump cuts,… pic.twitter.com/jjhjFmIs5p
How much does 720p video generation cost?
Google priced 720p video generation at $0.07 per second, representing a 30 percent reduction compared to the previous model version.
Where can developers prototype with the new model?
Developers can prototype using Google AI Studio and access the model through the Gemini API, while business users can utilize the Google Cloud console.
https://t.co/lDZweITrTn