Voice record to text

Hello everyone, I am working on a project in which I need to transcript into a text what I hear from a voice message(from a call recorded). I was investigating and I see that there are few examples related to the package Speech, which would help to convert in text a recording,but in the examples I see it is a recording that you are doing on the moment, live recording. My call messages are downloaded from somewhere. What can I do to take them and transcript like a text their message using UiPath So I can use it in my project?

Also I was reading something related to voice understanding Mining but not sure if I should go deeper and this may be part of the solution.
Thank you