Google DeepMind said on 5 November that Gemini Omni 1.2 Flash, its video model, is now generally available. It runs through the Gemini API and Gemini for business. Clips can now last up to 15 seconds, up from 10 seconds in version 1.1. Users can pick any length from 3 to 15 seconds. Google cut the price 30% to $0.07 per second for 720p video. Users can also change a clip with follow-up prompts instead of making it again.
Google said the model keeps faces, clothing, text and brand colors steadier within a clip. These are Google's own claims, backed by its demo examples. The post shows no outside tests and no comparison with rival models. Google said it is still improving fast sports action, rapid script changes and complex physics. It said every output carries an invisible SynthID watermark. Google Vids users get 15-second clips at no extra cost. The Gemini app version is rolling out to Google AI Ultra subscribers.
For teams that build or buy video tools, Google now lists a lower per-second price and longer single clips. Its suggested workflow is to draft at 360p or 720p, fix details with follow-up edits, then upscale to 1080p or 4K. Whether this saves money in practice depends on how many edits each clip needs.