Python video creation script

I want a python script to automate the video creation process. I have 4 different parts of the video separately.
- Audio files (multiple audio mp3 files to be added in a sequence)
- Background video(s), maybe multiple, to be added in sequence
- Center aligned overlay image (png) file
- Center aligned (exactly below the image) overlay text (in English)

Please find attached a sample input.json file with image, text and audio files. The background video(s) shall be cut to be of exact same length as the total length of audio file(s). The background videos may run in the loop if the audio files exceed the length of the background videos.

Please note, each text and image file will actually be a translation of each audio file. So in the final video, these 3 things should match each other. Make sure to add a translucent overlay behind the translation (image and text) to ensure the text colour is visible and readable.

The python script should take all these things as input, may as a JSON file and output an mp4 video file.

It is a humble request only people who are willing to do this project and have little experience with python video creation shall bid.