Google releases Gemini Omni 1.2 Flash for video generation
Google has launched Gemini Omni 1.2 Flash, a video generation model featuring native 15-second clips, conversational editing, and a 30 percent price reduction.
2 min read, Friday, 6 November

Google DeepMind has introduced Gemini Omni 1.2 Flash, a major update to its video generation technology. The new model brings native 15-second video creation, improved reference adherence, and multi-turn conversational editing capabilities.
Key facts
- Partner
- Model
- Gemini Omni Flash

Key capabilities and updates
Gemini Omni 1.2 Flash introduces several structural improvements over the previous version:
- Longer clips: Users can now generate and edit videos natively up to 15 seconds long, compared to 10 seconds in the previous version, with duration selectable in one-second increments from 3 to 15 seconds.
- Better reference adherence: The model can combine character, product, or style images, short motion clips up to three seconds, and audio cues, keeping details consistent throughout the video.
- Conversational editing: Users can refine clips turn by turn — such as swapping a background or changing lighting — rather than restarting the generation process from scratch.
- Natural speech and camera control: The model supports clearer lip-sync, multi-speaker conditioning, and continuous camera movements like sweeping flythroughs with fewer jump cuts.
Pricing and availability
The update lowers costs by 30 percent compared to the previous iteration, with pricing set at $0.07 per second for 720p video. Gemini Omni 1.2 Flash is generally available across the Gemini API, Google Cloud, Google Vids, the Gemini app, and Google Ads. Outputs generated by the model include an imperceptible SynthID watermark.
Source: Original announcement
Worth a read?



Comments