YouTube Detailed Transcription Software

I am seeking a talented and skilled individual or team to develop a software that generates text in a movie script format. This software will describe every scene and action + transcribe dialogue. The transcriptions should be formatted in a structured manner, providing timestamps for every line of dialogue. Same with events in the video.
I have generated good results using existing online AI tools, but no software was prepared to provide de level of detail that I expect (online apps are more like summarizers)

Im expecting the software will leverage the existing AI platforms for this project.

This text will be an input for another software that we will create afterwards if this project succeeds.

Ideal Skills and Experience:
- Experience with software development and programming languages, AI models like ChatGPT and Gemini
- Familiarity with APIs (YouTube API is a plus)
- Experience in similar projects of audio/video + AI

What I expect from this project:
- An innovative software that can write movie scripts from YouTube any video in English or Spanish.
- The script should be organized with corresponding timestamps.
- The software should be user-friendly and intuitive for ease of use (web or script)