15-Second AI Videos and Prompt-Based Editing; What Has Google Changed?

Google has released Gemini Omni 1.2 Flash, an updated version of its AI video-generation model that allows users to create longer clips, maintain greater visual consistency and edit existing videos through conversational instructions. Announced on Thursday, November 5, the new model can generate videos of up to 15 seconds, compared with the previous 10-second limit. It also introduces multi-turn conversational editing, allowing users to modify an existing video by providing additional instructions instead of generating an entirely new clip. Google has made Gemini Omni 1.2 Flash generally available through the Gemini API and Google Cloud for business users, with access also rolling out across its other products and services. The company has reduced the cost of 720p video generation by 30% compared with Gemini Omni 1.1 Flash, bringing the price to $0.07 per second.

AI Videos Up to 15 Seconds

One of the biggest changes in Gemini Omni 1.2 Flash is its ability to generate longer videos in a single generation. Users can now create clips ranging from three to 15 seconds, with durations adjustable in one-second increments. The previous version supported videos of up to 10 seconds. The longer duration gives creators more room to produce short advertisements, product demonstrations and social media videos without having to combine multiple shorter clips.

Google has also improved visual consistency, allowing the model to retain details such as characters, clothing, products and backgrounds throughout a video. This is particularly relevant for creators and businesses that need to maintain a consistent visual identity across different scenes and camera angles.

Users Can Edit Videos Through Conversations

Another significant addition is multi-turn conversational editing. With this feature, users can take an existing video and provide further instructions to modify it. For instance, they can ask the model to change the background, adjust lighting, alter weather conditions or switch the video's aspect ratio. Rather than generating an entirely new clip whenever a change is required, users can refine the existing video through successive prompts.

The feature could make the video-production process more efficient, particularly when creators need to make small adjustments or produce multiple versions of the same advertisement.

Google Reduces Video Generation Costs

Google has also lowered the cost of using Gemini Omni 1.2 Flash. The model is priced at $0.07 per second for 720p video generation, representing a 30% reduction compared with Gemini Omni 1.1 Flash. Users can initially generate lower-resolution drafts at 360p or 720p before upscaling selected videos to 1080p or 4K. This allows creators and businesses to experiment with different ideas and refine their preferred versions before investing in higher-resolution outputs.

The lower pricing, combined with conversational editing, is aimed at making AI video generation more cost-effective for businesses and developers producing content at scale.

Better Audio, Characters and Camera Movement

Gemini Omni 1.2 Flash also brings improvements to generated speech, lip-syncing and camera movement. According to Google, the model can produce more natural-sounding dialogue, improved lip-syncing and more distinct voices when multiple characters appear in the same scene. It also offers greater control over camera movements, including continuous zooms, sweeping shots and other cinematic movements. Google says these improvements help reduce unwanted jump cuts and maintain visual continuity across scenes.

The model can also use reference images, short video clips of up to three seconds and audio cues to guide video generation. This helps it retain details such as character appearances, product designs and visual styles throughout the output.

Where Can Users Access Gemini Omni 1.2 Flash?

Google is making the updated model available across its developer, business and creative platforms. Developers can access it through the Gemini API and Google AI Studio, while businesses can use it through Google Cloud. The model is also rolling out across Google's products, including Flow, Google Vids, Google Ads and the Gemini app. Availability and access conditions vary across these platforms, with the Gemini app rollout initially extending to Google AI Ultra subscribers.

However, Google acknowledges that the model still has limitations when handling fast-moving sports sequences, rapid script changes and complex physical movements. With longer video generation, conversational editing, improved visual consistency and lower costs, Gemini Omni 1.2 Flash represents Google's latest effort to make AI-powered video production more accessible to creators, developers and businesses.