At the Google I/O 2024 event, Google unveiled its artificial intelligence capable of generating video from text. Called Google Veo, this AI can produce high-quality 1080p resolution videos from text, images, and video prompts.
Google Veo emerges as a competitor to OpenAI’s Sora, which also generates videos from text. At the I/O ’24 event, Google introduced Veo as its latest generative AI video model, capable of producing high-quality 1080p resolution videos in various visual and cinematic styles, lasting longer than a minute.
Google Veo boasts advanced natural language understanding, enabling it to comprehend cinematic terms like time-lapse or aerial shots. Users can obtain their desired videos by using text, image, or video-based commands. Google claims its AI model renders more realistic movements for humans, animals, and objects. Additionally, Veo is expected to introduce features allowing it to generate story outlines and longer scenes.
Currently undergoing testing by filmmakers and content creators, certain Veo features will be available for preview in VideoFX with selected content creators in the coming weeks. Google also plans to incorporate some of Veo’s capabilities into YouTube Shorts in the future.
