Google Launches Gemini Omni 1.2 Flash with Enhanced Video Features

On November 5, 2026, Google DeepMind announced the release of Gemini Omni 1.2 Flash, making it generally available through the Gemini API and Gemini for business. This update introduces native 15-second video creation, enhanced multi-turn conversational editing, and improved adherence to reference details, all while reducing the price by 30% to $0.07 per second for 720p video.

One of the key features of Gemini Omni 1.2 Flash is its ability to generate longer clips, now allowing users to create and edit videos up to 15 seconds in length, an increase from the previous limit of 10 seconds. Users can specify clip durations in one-second increments from 3 to 15 seconds, enabling the production of complete stories, product explainers, or social media ads in a single generation.

The update also enhances reference adherence, allowing users to guide video generation by combining images, short motion clips, and audio cues. This ensures that details such as faces, garments, and brand colors remain consistent throughout the video, facilitating the creation of virtual try-on clips and branded ads.

Gemini Omni 1.2 Flash improves consistency across frames, reducing visual drift during motion and camera transitions. This means that characters, objects, and scenes maintain their integrity from the first to the last frame, even when extending clips or interpolating between keyframes.

Editing has become more intuitive with multi-turn conversational editing, which allows users to refine clips by making incremental changes, such as swapping backgrounds or adjusting lighting, without starting over. This feature is particularly useful for creating ad variants tailored to different audiences.

The update also focuses on generating more natural dialogue, with clearer lip-sync and multi-speaker conditioning. This enhancement is beneficial for projects involving multi-character dialogue or video explainers.

Additionally, Gemini Omni 1.2 Flash allows for more controlled camera movements, resulting in smoother transitions and a more cinematic look. Users can direct complex camera movements with fewer unwanted cuts, enhancing the overall quality of the generated videos.

Businesses, startups, and creatives are already integrating Gemini Omni 1.2 Flash into their workflows. The service is now backed by Google Cloud’s enterprise-grade infrastructure and security, with features like Provisioned Throughput and outputs that include an imperceptible SynthID watermark.

For developers, Gemini Omni 1.2 Flash is accessible through Google AI Studio, where they can prototype and explore interactive starter apps. Businesses can try it in the Google Cloud console, while general users can create 15-second clips in Google Vids and scale video campaigns in Google Ads.

As development continues, Google aims to enhance capabilities for fast sports action, rapid script changes, and complex physics, making Gemini Omni 1.2 Flash a robust tool for video production at scale.

Source: Google DeepMind