Google has officially unveiled Gemini Omni Flash, a multimodal AI video generation model, making it available in the Gemini app, Google Flow and YouTube Shorts. Users can generate a video with audio simply by uploading an image as the first frame and adding a prompt. The model is the first in the Gemini Omni family developed by Google DeepMind, and according to its official announcement it began rolling out around Google I/O in May 2026. It is positioned to replace the earlier Veo 3 / 3.1 generation series.
Continue reading
The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.
Already purchased? Sign in✓ Signed in — this article isn’t included in your current plan.