Google recently officially announced that the second version of its Veo video creation model now supports the Arabic language.
Veo 2 relies on a precise understanding of both human movement and the details of the surrounding environment. This enables it to produce high-fidelity videos with rich visual details.
The model translates Arabic text prompts into eight-second scenes at 720p resolution, delivered in MP4 format with a 16:9 aspect ratio. Additionally, it can transform still images into animated scenes.
As part of its commitment to transparency, the company embeds a digital watermark called SynthID into every frame of the generated videos. This indicates that these scenes were created using artificial intelligence.
Where Can Google Veo 2 Be Used?
The service is now available in the Middle East and North Africa (MENA), alongside other countries worldwide.
Currently, users of Gemini Advanced can create videos directly using Veo 2, accessible via both the mobile app and web browser.
According to Google, this feature is still rolling out and will gradually become available to more users over the coming weeks.
You can start trying out the tool via the official Gemini website (gemini.google.com) or through the Google Gemini app, available on mobile app stores.
Furthermore, Google is currently offering Veo 2 for free trials via its AI Studio platform. This platform also enables developers to integrate the advanced model into their own applications using the API.
