Google DeepMind is making its Gemini Omni 1.2 Flash video generation model generally available. According to the source, the update allows clips up to 15 seconds long, supports conversational editing, and costs 30 percent less than its predecessor.
The model is rolling out through the Gemini API, Google AI Studio, the Google Cloud Console, Flow, Google Vids, the Gemini app for Google AI Ultra subscribers, and Google Ads. Google says every generated video carries an imperceptible SynthID watermark to indicate its origin.
Clips can now run from three to 15 seconds, up from a previous maximum of 10 seconds. Pricing drops 30 percent to $0.07 per second for 720p video.
Google describes "Conversational Editing" as a way to adjust a generated clip step by step. Users can change the background, lighting, or aspect ratio without regenerating the whole clip. Google says this works across the full 15-second length. Google also describes a tiered workflow in which drafts are created at 360p or 720p, details are corrected with follow-up edits, and only the final result is upscaled to 1080p or 4K. The source states that this is meant to reduce costs.
Google says the model improves reference adherence.