Google DeepMind· GeminiModel update

Omni experts share what excites them most about the model.

Google DeepMind announced Gemini Omni, a multimodal model, with its first release Gemini Omni Flash focused on video generation and editing via conversational interaction.

From the source

We recently introduced Gemini Omni, a new model that lets you create anything from any input. The model’s first release, Gemini Omni Flash, makes generating and editing videos as easy as having a conversation.

blog.google

Announced

13 Aug 2026 13:30 UTC