Google has announced a new AI video-generation model, Gemini Omni 1.2 Flash, making it generally available across the Gemini API and Gemini for businesses. The newest version comes with 15-second video generation, multi-turn capabilities, and lower costs, making it more accessible and practical for developers, businesses, and content creators. It has also dropped the price by 30% from Gemini Omni 1.1, making it available at $0.07 per second for 720p video.
Faster Video Generation
One of the biggest improvements in Gemini Omni 1.2 Flash is its extended video duration. While the previous 1.1 version supported clips of up to 10 seconds, the new model can generate videos ranging from 3 to 15 seconds, giving room to tell complete stories, create product explainers, or produce full social ad spots in a single generation. This gives users more flexibility to create longer and more detailed videos without combining multiple short clips.
Gemini Omni 1.2 Flash Excels at Reference
Google has also focused on reference adherence. Users can guide generation by combining character, product, or style images, short clips up to 3 seconds, and audio cues. Gemini Omni 1.2 Flash can hold all these details from start to finish. This version follows the reference more closely than its predecessors.
Editing in Conversations Made Easy
Another important update is multi-turn conversation editing across full 15-second clips, making it easy to produce ad variants for different audiences and placements without re-briefing or re-generating. Instead of generating a new video, users can refine the existing clip turn by turn. For example, they can swap a product or background, change the light or weather, or even switch the aspect ratio. It also supports natural speech, wherein users can generate video scenes with more fluid, natural-sounding dialogue.
30% Price Drop than Gemini 1.1
A key part of the update is lower pricing. Google has dropped the price by 30% from Gemini 1.1. Generating a 720p video through the Gemini API now costs $0.07 per second. The model is a fast-generation video option, making it ideal for workflows that need frequent video creation and editing.
For output quality, Gemini Omni 1.2 Flash supports resolutions up to 4K. Users can generate videos at lower resolutions such as 360p or 720p for creation and experimentation. Once the results are met, they can boost the final output to 1080p to 4K.
As stated in Google's official announcement, "Gemini Omni 1.2 Flash generates clips up to 15 seconds long that hold references together better than before. You can also scroll through to see characters, text, and camera moves stay consistent across longer shots, multiple turns, and transitions with no cuts."
Google has also confirmed that every video generated output comes with an imperceptible SynthID watermark that identifies AI-generated content.
Availability
Gemini Omni Flash 1.2 is ideal for businesses, developers, and creators producing videos at scale. Users can get started with Gemini Omni 1.2 Flash as it is rolling out across Google's products and developer platforms.
- Developers can start using the Gemini API
- Businesses can try it in the Google Cloud Console and build enterprise solutions with the API.
- For everyone using the Google apps, they can direct scenes and multi-turn edits in the Flow, generate 15-second clips at no additional cost in Google Vids with a Google account or Google Workspace subscription.
They can also create 15-second videos in the Gemini app, which is rolling out to Google AI Ultra subscribers, and scale video campaigns in Google Ads.
This clearly reduces the cost of experimentation and limits the need for repeated video generations. Google is making AI-powered video creation simpler for creators and businesses.
For more trending news around the technology landscape, visit our website.
Read More:
Google Share Text Messages: New Update Shocks Employees with Major Privacy Concerns
