How clips of different sizes are joined
Phone clips are often vertical, camera clips are wide, and screen recordings can be any size. ToolGPT makes the merged video as wide as the widest clip and as tall as the tallest one. Each clip is scaled to fit inside that frame, and any space around it is filled with black, so nothing is stretched or cropped.
The frame rate is the highest one among your clips, up to 60 frames per second. Clips can also be in different formats, for example an MOV from a phone and an MP4 from a camera.