Google is rolling out Gemini Omni 1.2 Flash, a video-generation model that creates and edits clips up to 15 seconds long. The previous version supported up to 10 seconds. Users can select durations from three to 15 seconds in one-second increments, covering formats such as product explainers and social advertisements.
The model adds multi-turn conversational editing, allowing users to modify an existing clip rather than regenerate it from the beginning. Follow-up instructions can change a product, background, lighting, weather, or aspect ratio while retaining other elements. Google also says the release improves character, object, scene, and camera consistency across longer shots and transitions.
Reference controls can combine character, product, or style images with short motion clips and audio cues. According to Google, the model better preserves details such as faces, garments, packaging typography, and brand colors across camera angles. It also targets clearer lip-sync, distinct voices in multi-speaker scenes, and smoother continuous camera movements with fewer unwanted cuts.
Google reduced the price by 30% from Gemini Omni 1.1 to $0.07 per second for 720p video. Creators can draft at 360p or 720p and upscale selected results to 1080p or 4K. Gemini Omni 1.2 Flash is generally available through the Gemini API and Google Cloud, with access also rolling out across Flow, Google Vids, the Gemini app, Gemini for business, and Google Ads. Outputs include an imperceptible SynthID watermark.