Google on Wednesday released Gemini Omni Flash to general availability, making its fast, conversational video generation and editing model ready for production use. The GA release introduces significant new capabilities that position it as a serious tool for AI-powered video creation.
The new features include video extension, which allows developers to seamlessly continue existing videos by generating extensions at the end of a clip; frame interpolation, which generates smooth transitions between two images; and resolution control supporting outputs from 360p up to 4K (with 1080p and 4K produced via upscaling).
Previously available only in public preview as gemini-omni-flash-preview since late June, the model has been renamed gemini-omni-1.1-flash for its GA release. The original preview endpoint will be deprecated on September 30, 2026.
The launch comes during an active period for Google's Gemini platform. In the past week alone, Google also released Gemini 3.5 Transcribe to general availability — featuring high-accuracy speech-to-text across 85+ languages with speaker diarization — and Gemini 3.7 Flash GA, described as the company's most intelligent workhorse model for coding and agentic workflows.
The rapid release cadence reflects the fierce competition in the AI video generation space, where Google is competing against OpenAI's Veo models and emerging Chinese competitors.
