KARACHI: Google has expanded access to its advanced video generation model, Veo 3, allowing users in Pakistan and over 150 other countries to create eight-second videos from photos with sound, the company said in a statement released Friday.
The move comes amid a global surge in interest in creative AI tools, with content creators using different platforms to generate video stories and bring still images to life. With Pakistan’s growing pool of digital creators, the rollout is expected to spur local innovation in short-form content.
“This new capability allows users to transform their favorite photos into vivid eight-second video clips with sound through a powerful photo-to-video feature built on Veo 3,” Google said.
To use the feature, users select “Videos” from the tool menu, upload a photo, and describe the scene and audio. The system then generates a video that can be downloaded or shared.
The tool is accessible through Gemini, Google’s AI-powered assistant that combines search, image generation and content creation features into a single interface.
These capabilities are also integrated into Flow, Google’s AI tool for filmmakers, which now supports speech, background audio, and sound effects.
Google also underscored its commitment to responsible AI development.
“All videos generated with Gemini include a visible watermark and an invisible SynthID digital marker to indicate they are AI-created,” it said.
