Google announced Gemini Omni 1.2 Flash on Nov. 5, extending its video-generation model with clips up to 15 seconds. The prior Omni 1.1 version supported 10-second clips; the new version lets users set a duration in one-second steps from three to 15 seconds.
The update also supports editing a generated clip through follow-up prompts instead of starting over. Google says it improved consistency for references such as a person, product, garment or visual style, and that revisions can change backgrounds, lighting or aspect ratio while keeping other scene elements more stable.
Google says the API price is now $0.07 per second for 720p video, 30% below Gemini Omni 1.1. Developers and businesses can use the model through the Gemini API and Google Cloud; Google also lists Flow, Google Vids, the Gemini app and Google Ads among the rollout surfaces, with access varying by product and subscription.
The model card describes text, image, audio and video inputs, with video and audio outputs. It also notes a safety-sensitive editing capability: Omni can change a person’s speech, and Google says it is restricting that function while it studies how to make it safe to offer.
Google says work remains on fast sports action, rapid script changes and complex physics. Its demonstrations and performance claims are company-reported, so the release establishes the product’s stated feature set and pricing, not independent evidence that the model performs consistently across real production workloads.