It's basically a video editing app connected with ChatGPT, like InVideo. It may feel amazing to generate a smooth video from text descriptions, but the problem is the video is composed of things stiched together from the stock library, the result is incoherent figures, scenes, etc, for example, the main characters can be very different from one second to the next, even your text says otherwise. So maybe you can use those apps to generate videos as a start, then put your editing skills to make them usable, and don't expect to really cut down the time to produce a useble video to a fraction of the time it supposed to take.