Google launches Gemini Omni 1.2 Flash video model with conversational editing

The model is available across Gemini API, Google AI Studio, and other platforms. Video duration can be set from 3 to 15 seconds, with 720p pricing reduced to $0.07 per second. Users can iteratively refine videos without full regeneration, using a tiered workflow to lower costs. The model improves consistency in facial features, clothing, and branding across shots, and reduces visual distortion during motion or scene transitions.

Summarised from the original article by an open-source model, then checked automatically: every number and English name must appear in the source. The original article is authoritative.