Google adds AI video generation to Gemini app and Whisk experiment

Google is rolling out new AI-powered video generation features in its Gemini app and the experimental tool Whisk.

Both are based on Veo 2, a video model that, according to Google, is capable of producing realistic motion and detailed visuals. The new functionality is available exclusively to subscribers of the Google One AI Premium plan.

In Gemini Advanced, users can now convert text prompts into short video clips. Output is limited to eight seconds in length, with a resolution of 720p in MP4 format. The clips are delivered in 16:9 landscape format and, according to Google, are intended for use on short-form platforms such as TikTok and YouTube Shorts. A monthly video generation limit applies, and users are notified when they approach their quota.

The system supports a variety of prompts, ranging from realistic nature scenes to stylized or surreal sequences. Google notes that more detailed input generally yields better results.

Whisk Animate enables image-to-video animation

The Whisk tool, part of Google Labs, now includes a feature called “Whisk Animate.” This function transforms uploaded images into animated video clips, also using the Veo 2 model. As with Gemini, the output is restricted to eight seconds and is only accessible to Premium subscribers.

To mark AI-generated content, Google uses its proprietary SynthID technology, which embeds an invisible watermark into each video frame. The company also applies red-teaming and additional review processes to prevent the creation of material that violates its content policies.

The new features are being released gradually on a global scale and support all languages currently available in Gemini. Standard Gemini users do not have access to the video generation tools.