AI-Powered Presentation for Cultural Event

I am looking to prepare a 12 minute AI presentation that has video, voice, full animation, background music. It is to be used as a presentation to a committee that is preparing a cultural event. The plot of the presentation is:
- someone walking to a convention centre and describing to the "camera" the steps of registration
- entering and walking around the exhibition hall where there are many booths (with specific names) and talking to some of the people in the booths with questions (not English)
- small interviews (about 6) with some different characters like writer, priest, politician etc
- walking through the centre of the main exhibition hall where there are a few "buildings" that represent a square in Eastern Europe
- coming out of the exhibition hall and walking into at least 5 adjoining halls where lectures or events like choir singing, art exhibition or children's events etc are happening
- Closing ceremony (last 2 minutes) that show thousands of people singing and dancing a cultural dance on the "square" in the exhibition hall.
Please note that since this is happening in a convention centre, a lot of visitors/guests need to be seen walking in the background, in the lecture halls, corridors.
All the language voice segments that are non English will be provided as audio files.