Google Releases Gemini Omni 1.2 Flash with 15-Second Video Generation
Google has released Gemini Omni 1.2 Flash, a video generation model that is now generally available across the Gemini API and Gemini for business.
Google has released Gemini Omni 1.2 Flash, a video AI model that generates clips up to 15 seconds long and lowers pricing by 30 percent to $0.07 per second for 720p video.
By Hermes-Vector AI Desk

Google has released Gemini Omni 1.2 Flash, a video generation model that is now generally available across the Gemini API and Gemini for business.
The model introduces native 15-second video creation, an increase from the 10-second limit of Gemini Omni 1.1. Users can specify duration in one-second increments from 3 to 15 seconds.
Pricing has dropped 30 percent from Gemini Omni 1.1, making it available at $0.07 per second for 720p video. The workflow allows users to draft at 360p or 720p, make follow-up edits, and upscale to 1080p or 4K.
The model offers better reference adherence by combining character, product, or style images, short motion clips up to three seconds, and audio cues. It maintains consistency for faces, garments, packaging typography, and brand colors across camera angles.
Multi-turn conversational editing allows users to refine the same clip turn by turn, such as swapping a product or background, changing lighting or weather, or switching the aspect ratio.
The model also includes more natural speech with clearer lip-sync and distinct multi-speaker conditioning, as well as more controllable, cinematic camera movements with fewer unwanted jump cuts.
Gemini Omni 1.2 Flash is generally available, backed by Google Cloud’s enterprise-grade infrastructure and security. Provisioned Throughput is available, and outputs carry an imperceptible SynthID watermark.
Developers can prototype in Google AI Studio. Businesses can try it in the Google Cloud console. Users of Google apps can direct scenes in Flow, generate 15-second clips at no additional cost in Google Vids with a Google account or Google Workspace subscription, create 15-second videos in the Gemini app (rolling out to Google AI Ultra subscribers), and scale video campaigns in Google Ads.
The release extends native video generation to 15 seconds while reducing cost, positioning the model for businesses and creators producing videos at scale.
Sources
This article was drafted with AI assistance and checked against the sources above. Company claims are reported as claims. Cover image is AI-generated.
The day's checked news, by email
One short email a day with the top stories. Free, and you can unsubscribe in one click.
Or follow for the latest news:
No comments yet. Start the discussion.
OpenAI has launched GPT-6 Cyber, a model for finding and validating exploitable vulnerabilities, reporting gains on cybersecurity benchmarks and alignment evaluations.
OpenAI says GPT-5.6 Cyber is now available to approved customers in AWS GovCloud (US-East) through Daybreak Red, with inference data not used to train models.