Google Gemini Now Introduces AI Video Making Capability

JAKARTA - Google Gemini, the long-developed AI platform, is now getting stronger with new capabilities to generate videos using Google's latest AI model technology, Veo 2.

This feature will be available to Gemini Advanced customers. In addition, an experimental tool called Whisk is now accessible to more users worldwide, allowing them to create animations from images.

Gemini, which is designed to compete with leading AI platforms, has now received a major update. Starting today, Gemini users can generate videos using text prompts. However, this feature requires a paid subscription. In addition, the Whisk tool is also expanding its reach.

Veo 2-Based Video

Google announced two major developments related to its generative AI tool. First, Gemini's integration with Veo 2, the company's latest text-to-video model. Gemini Advanced customers can start generating video clips up to eight seconds long at 720p resolution using simple natural language prompts. Google states that the more detailed the prompts are, the better the results. The output will be an MP4 file with a 16:9 landscape aspect ratio.

Google is very proud of the results achieved by Veo 2. The company states that the model is “designed to produce high-resolution videos with cinematic realism.” “By better understanding real-world physics and human movement, the model produces smooth character movements, lifelike scenes, and sharper visual details across a variety of subjects and styles,” the blog post reads.

Gemini Advanced users can find Veo 2 in the Gemini model dropdown menu. After each video creation, there is a “Share” button that allows users to upload it to platforms like TikTok and YouTube Shorts. This AI-based video creation will be available on the Gemini app and website.

Google is also expanding the availability of Whisk, an experiment from its Labs. Originally announced in December 2024, Whisk allows users to create videos from images.

Users can also use text prompts, but Whisk’s main focus is on images. This feature allows users to create animations from their favorite images, for example. This feature’s capabilities are also supported by Google’s latest AI video model, Veo 2.