Google Rolls Out Gemini Omni 1.2 Flash with 15-Second Videos and 30% Lower Price

What Happened

Google is rolling out Gemini Omni 1.2 Flash, its video generation and editing model, and making it generally available across the Gemini API and Gemini for business, according to the Google AI Blog [1]. The update allows native video creation of up to 15 seconds, up from 10 seconds in Omni 1.1 [1]. The Verge reported the same 15-second limit and said users can set a clip length from three to 15 seconds [2].

According to Google, the main points of the update are:

• Clip length: Users can set the duration in one-second steps from 3 to 15 seconds [1][2].
• Price: The price has dropped 30% from Omni 1.1, to $0.07 per second for 720p video [1].
• Drafting and upscaling: Users can draft at 360p or 720p, then upscale their best creations to 1080p or 4K [1]. Google did not give prices for 1080p or 4K in the source material.
• Editing: A detail can be fixed with a follow-up edit instead of regenerating the whole clip. Multi-turn conversational editing works across full 15-second clips, for example to swap a background or change the lighting [1][2].
• Camera movement and dialogue: Google says the model handles continuous camera moves, such as FPV flythroughs and zoom-outs, with fewer unwanted jump cuts. It also says the model produces more natural-sounding dialogue and clearer lip-sync [1][2].
• Reference inputs: The model can be guided by character, product or style images, motion clips of up to three seconds, and audio cues. Google says faces, garments, packaging typography and brand colors stay consistent across camera angles [1].
• Availability: Google says the capabilities can be used across the Gemini API, Google Vids and Gemini for business [1].

Google’s examples include a 15-second virtual try-on sequence and a 15-second animated scene with multiple speakers. These are demonstrations in the company’s own announcement, and the source material does not give independent test results [1].

The Verge article was written by Emma Roth and posted on November 5, 2026 at 5:56 PM UTC [2]. The Google AI Blog post is dated November 5, 2026 at 17:00 UTC [1].

Who Is Affected

According to Google, businesses, startups and creatives are already using Gemini Omni 1.2 Flash in their workflows [1]. Google names Gemini for business, Google Vids and Flow as places where the dialogue and avatar features appear [1]. The company says the model is meant to help users produce high-quality video content at scale, including product explainers, social ad spots and virtual try-on clips [1].