Google unveils Gemini Omni, pushing AI beyond chatbots and into full-fledged video production

Google is introducing Gemini Omni, a new family of multimodal AI models aimed at transforming the way users create and edit video content, marking the company’s latest effort to extend artificial intelligence beyond text-based assistants and into full-fledged creative production workflows.

The first model in the lineup, Gemini Omni Flash, is designed to generate cinematic videos using a combination of text, images, audio, and video prompts. Unlike traditional AI video tools that rely heavily on isolated prompts, Google says Omni can reason on multiple forms of input simultaneously to produce more consistent and context-aware output.

The announcement comes as competition in generative AI rapidly intensifies, with companies racing to build platforms that can handle increasingly complex creative and enterprise tasks. AI-generated video has emerged as one of the fastest-growing segments within the broader AI ecosystem, attracting interest from creators, marketers, studios, and enterprises seeking faster and more scalable production pipelines.

A key feature that Google is highlighting is Omni’s conversational editing capabilities. Users can modify videos through natural language commands such as changing the environment, adjusting camera movement, adding visual effects, and transforming artistic style while maintaining continuity between scenes. The system also supports interactive editing, allowing users to adjust output across multiple prompts without restarting the workflow.

Google says the model demonstrates stronger “world understanding” and enables more realistic renderings of movement, lighting, and environmental interactions. The company claims the system better interprets domain concepts that have traditionally been challenging for generative video models, such as gravity, motion, and spatial coherence.

Gemini Omni also builds on the momentum generated by Google’s widely talked-about AI image model Nano Banana, officially known as Gemini Flash Image. The tool gained attention for its conversational image editing capabilities, allowing users to generate and modify visuals using natural language prompts while maintaining textual consistency and realism. Industry observers see Gemini Omni as Google’s attempt to extend the same intuitive creative workflow from still images to professional video generation and editing.

The platform also supports reference-based generation, allowing users to upload sketches, images, existing footage, or audio clips and turn them into stylized or photorealistic videos. To address concerns about synthetic media and deepfakes, all AI-generated videos created through Gemini Omni will include Google’s SynthID watermarking technology. Gemini Omni Flash will initially be rolled out to Gemini apps, Google Flow, YouTube Shorts, and YouTube Create, with developer and enterprise API access to follow.

Gemini Omni signals Google’s ambition to become a major player in AI-powered media creation, as the AI ​​race increasingly moves beyond chatbots and search into creative production. With conversational video editing, multimodal generation, and tight integration between YouTube and Gemini products, the company is positioning AI not just as an assistant but as a full-fledged creative engine for the next phase of digital content creation.

Nominated for ET AI Award