Google has released Gemini Omni 1.2 Flash, making it generally available across the Gemini API and Gemini for Business. The update introduces native 15-second video creation, up from 10 seconds in the previous version, along with multi-turn conversational editing and enhanced reference following.
Pricing has dropped 30% compared to Gemini Omni 1.1, now set at $0.07 per second for 720p video. According to Google, the cost-efficiency extends to workflow design: users can draft videos at lower resolutions (360p or 720p), make targeted edits rather than regenerating entire clips, and upscale final versions to 1080p or 4K.
The model supports video duration specifications in one-second increments from 3 to 15 seconds, enabling creators to produce complete stories, product explainers, and social media advertisements in single generations. Users can guide video generation by combining character, product, or style images, short motion clips up to three seconds, and audio cues. The system maintains consistency for details like faces, garments, packaging typography, and brand colors across camera angles and transitions.
Gemini Omni 1.2 Flash demonstrates improved consistency across longer sequences, reducing visual drift and morphing during motion and camera transitions. According to Google, this applies to interpolation between keyframes and clip extensions. The model also generates more natural speech with clearer lip-sync and distinct multi-speaker conditioning.
Users can now refine the same video clip through multiple conversational turns—swapping products, backgrounds, lighting, weather, or aspect ratios—without restarting from scratch. This capability works across full 15-second clips, enabling production of advertisement variants for different audiences and placements.
The model supports more controllable camera movements, including sweeping first-person-view flythroughs and dramatic zoom-outs with fewer jump cuts and steadier scaling. Google notes ongoing development for improvements including fast sports action, rapid script changes, and complex physics simulations.
Gemini Omni 1.2 Flash is now available to developers through the Gemini API with Google AI Studio prototyping and starter apps. Business users can access it via the Google Cloud console. General users can generate clips in Google Vids at no additional cost with a Google account or Google Workspace subscription, create videos in the Gemini app for Google AI Ultra subscribers, and scale campaigns through Google Ads. Outputs include an imperceptible SynthID watermark.
Key facts
- Gemini Omni 1.2 Flash supports native 15-second video generation, up from 10 seconds
- Pricing dropped 30% to $0.07 per second for 720p video
- Model offers multi-turn conversational editing for iterative refinement without full regeneration
- Users can specify video duration in one-second increments from 3 to 15 seconds
- Enhanced reference adherence maintains character, object, and scene consistency across longer clips
- More natural speech generation with improved lip-sync and multi-speaker conditioning
- Available through Gemini API, Google Cloud, Google Vids, Gemini app, and Google Ads