Google made Gemini Omni Flash available through the API. The model supports full video generation with conversational editing. Users can relight scenes or swap characters using plain language. It accepts multimodal inputs and pairs native audio with each video output. On-screen text synchronizes with movements. This makes video creation more interactive. Enterprises can build end-to-end experiences where they describe changes and the model handles updates. It builds on earlier image and video work like Nano Banana models. The release helps teams produce professional videos faster without traditional editing skills. Small businesses gain accessible tools for marketing and internal content. Availability through the API opens customization options.
Google made Gemini Omni Flash available through the API. The model supports full video generation with conversational editing. Users can relight scenes or swap characters using plain language. It accepts multimodal inputs and pairs native audio with each video output. On-screen text synchronizes with movements. This makes video creation more interactive. Enterprises can build end-to-end experiences where they describe changes and the model handles updates. It builds on earlier image and video work like Nano Banana models. The release helps teams produce professional videos faster without traditional editing skills. Small businesses gain accessible tools for marketing and internal content. Availability through the API opens customization options.