Google Unveils Veo 2 AI Video Generator: Step-by-step guide to creating cinematic clips with Gemini

Google Unveils Veo 2 AI Video Generator: Google has officially launched its next-generation AI video generation tool, Veo 2, integrated into the Gemini platform which marks a significant leap for Google’s generative AI capabilities, allowing users to create short, high-resolution video clips from text prompts.

What is Veo 2?

Veo 2 is the successor to Google’s earlier video generation model, designed to produce eight-second-long videos in 720p resolution using descriptive text prompts. The videos are rendered in MP4 format with a 16:9 landscape aspect ratio, and Google says they are infused with cinematic realism, fluid character motion, and detailed visuals.

According to the company, Veo 2 achieves this level of realism by better understanding real-world physics, human movement, and environmental cues. The feature has begun rolling out globally to Gemini Advanced users on both web and mobile, as well as Google One AI Premium subscribers in all languages supported by Gemini.

How to Access and Use Veo 2 in Gemini: A step-by-step guide

Here’s how users can start creating videos with Veo 2:

• Access Gemini on desktop or mobile and ensure you’re subscribed to Gemini Advanced or Google One AI Premium.
• Select Veo 2 from the model dropdown menu.
• Enter a detailed prompt describing the video you want to generate. Be as specific as possible — including elements like mood, visuals, movement, lighting, and style — to get optimal results.
• Generate the video. Once created, you can preview and share directly to platforms like YouTube Shorts and TikTok.
• Google notes that there is a monthly limit on the number of videos users can create, though the exact cap hasn’t been disclosed. Users will be notified as they approach their limit.

Integration with whisk for mixed prompts

Alongside Gemini, Google Labs is also offering access to Veo 2 through Whisk, which allows users to generate videos using a combination of text and image inputs — enabling richer and more precise outputs.

Sample prompts used by Google

To showcase Veo 2’s capabilities, Google shared a few example prompts and their resulting videos:

• Prompt 1: “Time-lapse of a voxel-style ice cream melting under a clear blue sky…”
• Prompt 2: “An animated shot of a tiny mouse with oversized glasses, reading a book by the light of a glowing mushroom in a cozy forest den.”
• Prompt 3: “A slow-panning shot of an enormous glacial cavern, illuminated by pale cyan light and dotted with frozen candy figures…”
• Prompt 4: “Aerial shot of a grassy cliff leading to a sandy beach, where waves crash and golden light bathes a prominent sea stack.”

Google vs OpenAI

Google’s release comes just months after rival OpenAI launched Sora Turbo in December 2024 — an advanced video generation model available to ChatGPT Plus and Pro users. With both tech giants now pushing into AI video, the competition is heating up in the generative media space.

As AI-generated content becomes more sophisticated, tools like Veo 2 and Sora Turbo are paving the way for creators, marketers, and storytellers to bring their ideas to life with unprecedented ease.