Skip to content
Google DeepMind

Google DeepMind releases Gemini Omni Flash video model

Introducing Gemini Omni

Google DeepMind released Gemini Omni Flash, the first model in the Gemini Omni family. It combines image, audio, video and text inputs to generate high-quality video, and supports multi-turn editing in natural language.

Why it matters: One model now handles image, audio, video and text input plus multi-turn editing, and it ships inside Gemini, Flow and Shorts.

Read the original ↗Export Markdown