Skip to content
AIBRAINWORX / THE INDEPENDENT AI LABRESEARCH · HARDWARE · OPEN INTELLIGENCE
AI News / Model Watch

Google brings 15-second generation to Gemini Omni 1.2 Flash

The hosted video model adds conversational edits and longer clips, with API pricing stated per second.

Publisher: Google · Model / component: Gemini Omni 1.2 Flash
Availability: Hosted through the Gemini API and Gemini for business; pricing applies.

Concept illustration of a video editing workstation
AI-generated editorial concept illustration. Not an official product image, screenshot, or photograph of a real event.
Event / context: Google announcement: November 5, 2026. Source check: Nov 7, 2026.

Google announced Gemini Omni 1.2 Flash with native 15-second video creation, conversational follow-up edits and improved reference following. The company says it is generally available through the Gemini API and Gemini for business. Read the original announcement and project details.

Why it matters

Google lists 720p API generation at $0.07 per second and describes drafting at lower resolutions before upscaling. At that published rate, a 15-second output would be $1.05 before any other applicable charges; check current provider pricing and terms.

What to know

The release is a hosted service, not an open local model. Google’s claims about speed and consistency need independent testing for a particular creative workflow.

Reported from linked primary sources. No model or product was independently tested.

Follow your curiosity.

Pass the signal.