Google Launches Gemini Omni 1.2 Flash With 15-Second Video Clips and $0.07-Per-Second Pricing

Google announced Gemini Omni 1.2 Flash on November 5, a new version of its video generation and editing model. The maximum clip length rises from 10 to 15 seconds, and for the first time in the Gemini Omni family the model is generally available, through the Gemini API and Gemini for business in Google Cloud.

What changed

Omni 1.2 Flash natively generates and edits video from 3 to 15 seconds long. Google says it improved reference adherence, frame consistency, speech and camera control compared with version 1.1. The company's blog post was written by Anish Nangia, a product manager at Google DeepMind.

The model accepts references: images of a character, product or style, motion clips of up to three seconds, and audio cues. According to Google, faces, garments, packaging typography and brand colors are meant to stay consistent across camera angles. The company points to uses such as virtual try-on, catalog spins and branded video ads.

There is also supposed to be less visual drift between the first and last frame when interpolating keyframes and extending clips. In comparison material for versions 1.1 and 1.2, Google points to subtle differences in detail, for example a soup ladle turning into chopsticks. The comparison comes from the vendor.

Editing, voice and camera

According to Google, multi-turn editing works on full 15-second clips. Users can swap a product or background, or change the lighting, weather or aspect ratio, without regenerating from scratch. Dialogue has also been improved: it is meant to sound more natural, with clearer lip-sync and distinct handling of multiple speakers.

For camera control, Google promises smooth movements such as FPV flythroughs, zoom-outs and orbits, with fewer unwanted jump cuts. The company notes that it is still working on fast sports action, rapid script changes and complex physics.

Pricing and availability

Google charges $0.07 per second for 720p video, 30% less than for Omni 1.1. By simple arithmetic, a 15-second clip at that resolution comes to about $1.05. The company advises drafting at 360p or 720p, fixing details with follow-up edits instead of regenerating, and only then upscaling to 1080p or 4K.

Developers can try the model in Google AI Studio, and businesses in the Google Cloud console or through the API. Provisioned Throughput is also available. In Google's own apps the model is coming to Flow, Google Vids and Google Ads, while 15-second video in the Gemini app is rolling out to Google AI Ultra subscribers.

Watermark and business impact

Generated videos carry an imperceptible SynthID watermark. For Polish agencies, e-commerce companies and marketing teams, the main points are the lower cost per second and a longer clip that fits a typical social media ad without stitching shots together.

Real-world quality still needs to be tested on your own material, because the examples cited come from the vendor.