Google Unveils Veo, a Stellar Model to Transform Text into Videos

Many artificial intelligence enthusiasts think of "Sora" when generating videos from text descriptions. OpenAI is indeed gearing up to release this impressive model, but a new competitor has emerged: Google's Veo.

The Google I/O 2024 conference was a real treat for fans of AI-based tools and broader technology. Among the highlights was Project Astra, poised as an answer to OpenAI's GPT-4. Similarly, Google Veo aims to offer an alternative to the Sora model.

How does Google Veo operate, and what makes it stand out? The process is straightforward: you input a prompt and await the outcome. However, this time, the result isn't just an image but a realistic video. Google Veo can generate a one-minute video based on the inputted words. How does this translate in real life? Precisely as described:

Google assures that the tool will deliver high-quality videos (1080p) and won't be confined to merely producing videos; Google Veo will also facilitate their editing.

Veo is set to enhance the workflow of professional creators while being accessible for novices in the art scene. Introducing such advanced tools typically occurs in phases; this instance is no exception.

In the upcoming weeks, Google plans to roll out some of these features to select creators through VideoFX, a new experimental platform available on labs.google. Registration for the waiting list is already open.