Google has announced the release of Gemini Omni 1.2 Flash, an update to its multimodal video-generation and conversational-editing platform, now available through the Gemini API and Google Cloud. The new version introduces native 15-second video creation, multi-turn conversational editing, and improved reference adherence, while reducing costs by 30% compared to its predecessor, Gemini Omni 1.1 Flash.
Key Features and Improvements
Gemini Omni 1.2 Flash enables users to generate and edit videos up to 15 seconds long, a 50% increase from the previous 10-second limit. Users can specify durations in one-second increments from 3 to 15 seconds, allowing for more flexibility in storytelling, product explainers, and social media advertisements. The pricing for 720p video output is set at $0.07 per second, making a 15-second clip cost $1.05 before additional charges.
The platform also enhances reference adherence, maintaining consistency in faces, garments, typography, and brand colors across camera angles. For example, Google demonstrated the generation of a 15-second virtual try-on sequence that preserved a model’s identity and garment details across 360-degree turns and match cuts.
Multi-turn conversational editing allows users to refine clips iteratively without starting from scratch. This feature supports adjustments such as swapping backgrounds, changing lighting, or altering aspect ratios, making it easier to produce ad variants for different audiences and platforms. In one demonstration, Google showcased how a single clip could be modified turn by turn to feature different settings while maintaining character and scene consistency.
Enhanced Cinematic and Dialogue Capabilities
Gemini Omni 1.2 Flash introduces more fluid, natural-sounding dialogue, improved lip-sync, and distinct multi-speaker conditioning. In one example, the platform used voice and character references to generate a 15-second animated scene with expressive lip-sync and comedic timing. Additionally, the update supports complex camera movements, such as continuous FPV flythroughs and cinematic zoom-outs, with fewer jump cuts and steadier transitions.
Google highlighted the platform’s ability to maintain consistency across longer clips and transitions. For instance, a single 15-second macro science explainer was created with motion-tracked callouts and consistent text and camera movements.
Applications and Enterprise Features
Businesses and developers are already integrating Gemini Omni 1.2 Flash into their workflows. The platform is backed by Google Cloud’s enterprise-grade infrastructure, offering features like Provisioned Throughput and imperceptible SynthID watermarks. QuickFrame AI’s Chief Technology Officer, Richard Girges, noted that the ability to generate complete 15-second connected-TV advertisements in a single pass is a significant advancement for advertising workflows.
Developers can access Gemini Omni 1.2 Flash through the Gemini API, with resources available in Google AI Studio and the Google Cloud console. The platform is designed for scalable video production, making it suitable for businesses, startups, and creators alike.
