Google rolls out Gemini Omni 1.2 Flash with 15-second clips
Original title: Gemini Omni 1.2 Flash: Fast and cost-effective with longer clips
The video model is generally available on the Gemini API at $0.07 per second of 720p, 30% below Omni 1.1.
Google DeepMind made Gemini Omni 1.2 Flash generally available on the Gemini API and Gemini for business. Native clip length rises from 10 seconds to 15, with duration set in one-second steps from 3 to 15 seconds, plus multi-turn conversational editing. The 720p price is $0.07 per second, 30% below Omni 1.1, and outputs carry a SynthID watermark. Google says fast sports, rapid script changes, and complex physics still need work.
Unconfirmed: Consistency, lip-sync, and camera-control gains are Google’s own descriptions, not independent measurements.
- Users can draft at 360p or 720p, then upscale chosen clips to 1080p or 4K.
- References can combine images, motion clips up to three seconds, and audio cues.
- Provisioned Throughput is offered on Google Cloud enterprise infrastructure.
- Speech updates include clearer lip-sync and distinct multi-speaker conditioning.
- Vendors
- Products
- Gemini APIGemini for business
- Organizations
- Google DeepMindGoogle Cloud
- AI models
- Gemini Omni 1.2 Flash
From the original article
4 min read at deepmind.google
Gemini Omni 1. 2 Flash brings 15-second clips, stronger consistency, and faster, more cost-effective generation. This content is generated by Google AI.
deepmind.google
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.