Google has officially introduced Gemini Omni, a multimodal AI model that integrates reasoning abilities with creative generation across video, image, audio, and text inputs. The launch begins with Gemini Omni Flash, which is immediately available to all Google AI Plus, Pro, and Ultra subscribers globally through the Gemini app and Google Flow. Additionally, users of YouTube Shorts and YouTube Create App can access it at no cost, and developer and enterprise access via API is expected within weeks.
Meet Gemini Omni, our new model that can create anything from any input, starting with video.
— Google Gemini (@GeminiApp) May 19, 2026
With Gemini Omni, you can combine images, videos and text as inputs and generate high-quality videos grounded in Gemini's real-world knowledge. #GoogleIO
Gemini Omni stands out for its capacity to generate high-quality, context-aware videos based on natural language instructions or reference media. Users can perform conversational video edits, maintaining scene continuity and character consistency over multiple editing steps. The model's improved grasp of physics allows for more realistic visual effects and scene changes, supporting both creative storytelling and technical explainers. Gemini Omni also embeds a SynthID digital watermark in all outputs for verification and transparency.
Gemini Omni doesn't just build scenes that look real, it reasons about what should happen next. It combines an intuitive understanding of physics with Gemini's knowledge of history, science, and cultural context.
— Sundar Pichai (@sundarpichai) May 19, 2026
Rolling out today starting with video outputs to Google AI Plus,… pic.twitter.com/EkLjv5O0dN
This launch marks a major expansion of Google's multimodal AI services, targeting a broad audience including content creators, educators, and enterprise users seeking advanced video and media generation tools. By offering Gemini Omni Flash across its AI subscription tiers and popular creator platforms, Google aims to compete directly with other AI generation tools on the market, leveraging its existing user base and expertise in responsible AI development.
