Google launches Gemini Omni 1.2 Flash for 15-second video generation

Google has released Gemini Omni 1.2 Flash, a multimodal model for generating and editing video. It accepts text, images, short video clips and audio, and produces video with audio. The model is generally available through the Gemini API and Google Cloud; its weights are closed and it cannot be deployed locally.

The system can create or modify clips up to 15 seconds long, compared with 10 seconds in Omni 1.1 Flash. Users can choose durations from three to 15 seconds in one-second increments. Google also reports improved reference adherence, more consistent faces, clothing, packaging text and brand colors, as well as better dialogue, lip-sync and camera movements. Conversational editing can continue across a full 15-second clip without uploading the previous video again.

Pricing for 720p output is $0.07 per second, or about $1.05 for 15 seconds, representing a 30% reduction from the earlier model. Developers can draft at 360p or 720p, edit selected details and upscale results to 1080p or 4K. Google has not released benchmark scores for version 1.2. The company says fast sports action, rapid script changes and complex physics remain challenging. Outputs include a SynthID watermark.