The Make-a-Video tool is a state-of-the-art AI system that uses text to generate videos. It is based on recent progress made in text-to-image and text-to-video generation technology. The system uses image description and unlabelled video data to learn how the world looks and moves. It allows users to bring their imaginations to life by generating one-of-a-kind videos based on a single line of text. The tool also enables users to add extra creative touches and variations to their videos based on input images. The developers are committed to ensuring the safe and responsible use of this technology through ongoing research and development.