Article:Google AI for Developers
Video Generation and Editing with Gemini Omni Flash
Google has documented the integration of Gemini Omni Flash (gemini-omni-1.1-flash) into the Gemini API. The multimodal model processes text, image, audio, and video simultaneously, enabling text-to-video and image-to-video generation with integrated sound.
From Video: Weekly AI Updates: Local Models, GPT-6 Astra, and Agent Architectures