Google debuts Gemini Omni 1.2 Flash with 15-second AI video clips and conversational editing

Google has launched Gemini Omni 1.2 Flash, an updated video generation model that natively produces video clips up to 15 seconds long, up from 10 seconds in the previous version. The model is generally available through the Gemini API and Google Cloud, with developer pricing reduced by 30% from Omni 1.1 to $0.07 per second for 720p video. Consumers with a Google AI Ultra subscription can access the model via the Gemini app, while free users can test select capabilities through Flow and Google Vids. [1][3]

The update lets users specify video lengths in one-second increments between 3 and 15 seconds. Google says the model improves visual consistency and reference adherence, allowing creators to anchor generations using style images, audio cues, and short motion clips of up to three seconds. Omni 1.2 Flash also introduces multi-turn conversational editing, enabling users to swap backgrounds, alter lighting, or adjust aspect ratios across subsequent prompts rather than regenerating clips from scratch. [1][3]