Gemini Omni 1.2 Flash Introduces 15-Second Video Generation at Reduced Costs

On November 5, 2026, Google DeepMind announced the rollout of Gemini Omni 1.2 Flash, making it generally available across the Gemini API and Gemini for business. This update introduces native 15-second video creation, enhanced multi-turn conversational editing, and improved reference adherence, all at a 30% lower price than its predecessor, now available at $0.07 per second for 720p video.

One of the key features of Gemini Omni 1.2 Flash is its ability to generate and edit videos up to 15 seconds long, an increase from the previous limit of 10 seconds. Users can specify durations in one-second increments from 3 to 15 seconds, allowing for more comprehensive storytelling and the creation of product explainers or full social media advertisements in a single generation.

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

Another significant improvement is the consistency of results. Gemini Omni 1.2 Flash maintains stronger character, object, and scene consistency throughout the video, minimizing visual drift or morphing during motion and camera transitions. This is particularly evident when generating complex scenes, where products, characters, and environments remain consistent from shot to shot.

Editing has also become easier with the introduction of multi-turn conversational editing. Users can refine clips turn by turn, such as changing backgrounds or lighting, without needing to start from scratch. This feature allows for the efficient production of ad variants tailored for different audiences.

The update also enhances the naturalness of generated speech, providing more fluid dialogue, clearer lip-sync, and distinct multi-speaker conditioning. This improvement is beneficial for various applications, including multi-character dialogue and video explainers.

Additionally, Gemini Omni 1.2 Flash allows for more controlled and cinematic camera movements, reducing unwanted jump cuts and achieving a polished look. Users can direct complex camera movements with greater precision, resulting in smoother transitions.

Businesses and creatives are already leveraging Gemini Omni 1.2 Flash in their workflows. The model is now generally available, supported by Google Cloud’s enterprise-grade infrastructure and security. Outputs from the model carry an imperceptible SynthID watermark, ensuring authenticity.

For those interested in utilizing Gemini Omni 1.2 Flash, it is accessible across various Google products and developer platforms. Developers can prototype in Google AI Studio, while businesses can explore it in the Google Cloud console. Additionally, users of Google apps can generate 15-second clips at no extra cost in Google Vids and create videos in the Gemini app.

Source: Google AI Blog