Gemini Omni
Create anything from any input – starting with video
A multimodal generative-model family that combines text, image, audio, and video inputs to generate and conversationally edit video; its first released model is Gemini Omni Flash.

Model Intelligence
Benchmarkable
No
Model level
family
Recent stories
2 linked stories
releasePRIMARY2026-11-05
Google releases Gemini Omni 1.2 Flash with 15-second video clips
Google released Gemini Omni 1.2 Flash with conversational video editing and clips up to 15 seconds. Drafts at 360p or 720p cost $0.07 per second, which Google says is 30% below its predecessor.
releaseSECONDARY2026-10-27
Google previews Genie 4 with native audio for interactive worlds
Google's Genie 4 generates interactive worlds with native audio, live scene edits and Gemini-driven world-state reasoning. Trusted-tester access has begun; API and Google AI Ultra access are planned.