How does youtube transcribe video to text?

Question

YouTube

I want to make a startup and make money on my BMW X6 in 1 year (if I connect the English of the country) or 2 years (if only the Russian Federation)
PAIN : On freelance exchanges, there are a lot of part-time jobs for transcribing audio / video to text
ANALYSIS OF COMPETITORS: There are free ones, but the devil will break his leg there,
there are paid ones, but they are expensive and you won’t earn money for yourself
TASK: Create a service that will help in this
QUESTION: How does youtube do video transcription into text?
I would be grateful for any hints, any programming language is welcome (after all, this is just a tool)

Answer 1

https://cloud.google.com/speech-to-text/
https://medium.com/activewizards-machine-learning-...
If you have a godlike math level and a couple of the same bigheads, then you have a chance to file a neuron better than Google's After
all, the Poles made Ivona

Answer 2

Most likely Google Cloud Speech-to-Text is used
https://cloud.google.com/speech-to-text/
https://cloud.yandex.ru/docs/speechkit/
https://github.com/watson- developer-cloud/speech-t...
PS There are other online services and ready libraries on GitHub