During I/O 2025, Google took a peek at VEO 3, the advanced video generation model of the future. Google highlighted that this new AI model is more advanced than VEO 2 and allows you to create production-ready animations with cinematic content, immersive experiences, and single prompts. Now, the company has opened Gates to access developers in VEO 3. You can access this model via paid preview via Gemini API and Vertex AI.
“People around the world have already used VEO 3 to generate tens of millions of high quality videos. This is the first video model to incorporate high fidelity video output and native audio, first using text to video and then immediately from image to image,” Google wrote in its official blog post.
What VEO 3 offers
So, what exactly is VEO 3? Well, Google describes it as the company's first video model that can incorporate it and incorporate audio such as sound effects, dialogs, ambient noise and more, and generate very realistic videos that all together.
Currently, this model can turn text prompts into videos, but users can also prompt with images immediately. Users can use VEO 3 to create animated shorts, movie scenes, storyboards, or game cinematics.
Some of the core features that make VEO 3 stand out from the current video generation AI model:
Synchronized Sound: VEO 3 can natively generate audio, including dialogue, music, sound effects. All of this is visually accurately timed.
Movie quality: The model also supports high-resolution video output with rich textures, lighting effects and creative details.
Realistic Physics: VEO 3 simulates real physics and sims them with incredible animations, allowing users to create videos that contain elements like flowing water, casting shadows, and natural character movements.
Open for VEO 3 developers
Google has revealed that animation studios like Cartheel and Volley are already using VEO 3 to boost their creative work. Cartwheel uses VEO 3 to convert 2D human motion video into fully equipped 3D animations. Meanwhile, Valley is using VEO 3 to quickly repeat high fidelity story-driven sequences to generate game cutscenes for upcoming RPGs titled Wit's End.
VEO 3 Price
The Veo 3 looks cutting edge and impressive, but using it costs money. Google is currently priced at VEO 3 at $0.75 per second for videos with synced audio output. In Indian, it is about Rs 64.50 per Rs 64.50.
Meanwhile, Google has announced a faster, more affordable version called Veo 3 Fast. Google says the model will arrive soon. This budget-friendly model is for users who need powerful yet cost-effective AI tools for rapid video creation.
How to Use VEO 3
To get started, developers can use Google AI Studio, which includes Starter apps, SDK templates and integration with Gemini APIs.
To maintain transparency, Google emphasizes that VEO 3 embeds digital synthed watermarks in all outputs to ensure responsible AI use.
– end
