Google Gemini Omni 1.2 Flash brings 15-second video and 30% price cut
Google DeepMind has released Gemini Omni 1.2 Flash, its video generation and editing model. The model is generally available through the Gemini API and Gemini for business. It creates clips up to 15 seconds natively, up from 10 seconds in Omni 1.1. It also introduces multi-turn conversational editing and drops the price by 30 percent to $0.07 per second for 720p video.
For someone running client delivery or producing marketing assets, the main shift is not just longer clips. It is that you can draft at low resolution, edit a detail in conversation, and upscale only the final take. That changes how you spend on iterations.
In one line: Google released Gemini Omni 1.2 Flash, a video generation model with native 15-second clips, multi-turn conversational editing, and 30 percent lower pricing at $0.07 per second of 720p video.
What changed from Omni 1.1 Flash
Google lists six upgrades in the launch note. The most visible ones are:
- Longer clips: generation and editing now reach 15 seconds, up from 10 seconds.
- Duration control: you can set length in one-second steps from 3 to 15 seconds.
- Reference adherence: you can combine character, product or style images with motion clips up to three seconds and audio cues.
- Consistency: faces, garments, packaging text and brand colors hold across camera angles with less morphing.
- Speech: dialogue sounds more natural, with clearer lip-sync and distinct multi-speaker conditioning.
- Camera control: FPV flythroughs, zoom-outs and orbits show fewer unwanted jump cuts.
This is a meaningful change for anyone who has spent time re-rolling video generations because a product label warped or a background drifted. Omni 1.2 Flash is designed to hold those details better. Google shows a virtual try-on example where one model photo and product shots of three outfits stay consistent across 360-degree turns.
A cheaper workflow, not just a cheaper price
The price cut is straightforward: $0.07 per second of 720p video, down from about $0.10 per second for Omni 1.1. A full 15-second 720p clip costs about $1.05. But Google frames cost control as a workflow. You draft fast at 360p or 720p, fix a detail with a follow-up edit instead of regenerating the whole clip, and then upscale only the best results to 1080p or 4K.
Multi-turn conversational editing now works across the full 15-second length. In practice, you can swap a product, background, lighting or aspect ratio turn by turn. The developer docs show this through a previous interaction ID, so the prior video is not re-uploaded. That matters for teams that produce ad variants for different placements. Instead of re-briefing, you keep the same clip and adjust one element.
For teams already evaluating AI video tools, the video and animation tools directory on kalpakkale.com lists 15 tools in this category. Google Vids users can also generate 15-second clips at no additional cost, with a Google account or Workspace subscription.
Better reference adherence and less drift
Reference adherence is the part that matters for branded content. Google says you can guide generation with character, product or style images, short motion clips up to three seconds, and audio cues. The model is supposed to keep faces, garments, packaging typography and brand colors consistent from the first frame to the last.
There is also less visual drift across motion and camera transitions. Google compares Omni 1.1 and 1.2 on a static exhibition poster prompt. The 1.2 model assembles the poster layer by layer and locks material, shadow and typographic detail through the final frame. That kind of consistency is useful for catalog spins, product explainers and branded video ads.
If you spend time preparing product photography or character references, the image generation tools directory points to related still-image options that can feed such workflows.
What it does not yet do
Google is clear that development is ongoing for fast sports action, rapid script changes and complex physics. No benchmark scores for 1.2 are published. The claims rest on side-by-side demos and partner feedback. MarkTechPost notes that audio references remain allowlist-gated on Google Cloud. That means some features are not fully open to every developer today.
For a client delivery team, the practical question is when to use this. It is a good fit for product explainers, social ad spots, virtual try-ons and branded shorts where reference consistency matters more than fast motion or complex physics. If you need an eight-second dream sequence inside a long-form video, you still need to review the output carefully.
Quick answers
What is Gemini Omni 1.2 Flash?
Gemini Omni 1.2 Flash is Google DeepMind's video generation and editing model. It creates and edits clips up to 15 seconds long, supports multi-turn conversational editing, and costs $0.07 per second of 720p video.
How much does Gemini Omni 1.2 Flash cost compared with Omni 1.1?
Google prices Gemini Omni 1.2 Flash at $0.07 per second of 720p video, a 30 percent cut from Omni 1.1's roughly $0.10 per second. A full 15-second 720p clip costs about $1.05.
What are the known limitations of Gemini Omni 1.2 Flash?
Google says fast sports action, rapid script changes and complex physics still need work. No 1.2 benchmark scores have been published yet.
Sources
- Google DeepMind: Gemini Omni 1.2 Flash: Fast and cost-effective with longer clips
- MarkTechPost: Google Releases Gemini Omni 1.2 Flash: 15-Second AI Video at $0.07 per Second
- The Decoder: Google's Gemini Omni 1.2 Flash stretches AI video clips to 15 seconds and cuts pricing by 30 percent
- Google AI: Gemini Omni 1.2 Flash: Fast and cost-effective with longer clips