Magisto is an AI (artificial intelligence) based video creation and editing platform.
When you upload videos and pictures to Magisto, our artificial intelligence engine begins analyzing your footage. The algorithm examines the footage on three levels—visual analysis, audio analysis, and storytelling.
The visual analysis component means our algorithm checks your footage for in-frame action, camera motion, object detection, tracking, and more. This helps the engine understand which parts of your video are the most visually interesting, and also determine whether your footage needs stabilization, color correction, or other edits.
Next, the audio analysis detects speech, classifies the different types of audio within your uploaded footage, and determines how each of these elements will best fit together to create your video.
Then, once your footage has undergone visual and audio analysis, our AI begins to construct a script of sorts for the final cut of your video—the story. We then pair this information with the video style and template (if applicable) that you select, and edit your video seamlessly together.
It’s important to note that we don’t save any of the analytic information on our servers; the information is stored temporarily while we examine your footage in order to better understand what you’re looking to create, and then deleted.
Here's a great video demonstrating what Magisto is all about - link