Gemini omni 1.2 flash launches with enhanced video capabilities and cost reductions

Google has released Gemini Omni 1.2 Flash, making it generally available across the Gemini API and Gemini for business. This new iteration introduces native support for 15-second video generation, multi-turn conversational editing, and improved adherence to reference materials. The update also brings a 30% cost reduction from the previous Gemini Omni 1.1 model, pricing 720p video at $0.07 per second. Key enhancements include the ability to generate videos up to 15 seconds long, allowing for detailed storytelling or ad spots in a single generation. Users can guide creation using combinations of character, product, or style images, short motion clips (up to three seconds), and audio cues, ensuring consistency across frames, camera angles, and garments. Furthermore, the model supports complex tasks like continuous FPV drone flights with zero jump cuts and multi-turn editing to swap backgrounds while maintaining character performance. Beyond video features, the platform allows for iterative refinement, enabling users to make edits like changing lighting or aspect ratio turn by turn rather than restarting. The service is backed by Google Cloud’s enterprise-grade infrastructure, and outputs include an imperceptible SynthID watermark. The capabilities are accessible across the Gemini API, Google Vids, and Gemini for business.