... That's a lot of trust to place in google. Do all this work to gather data, then throw it away and analyze what google did to the data instead.
I don't think the goal of using Google speech-to-text was to solely use the transcriptions for the rest of the project, but you've gotta find some way to sift through those recordings and pull out the interesting bits. I think that was the right choice providing additional context and picking out the good stuff. Imagine having to listen to ~28 hours of recordings (60 sec * 1724 answered calls) when there's a service that can easily turn those recordings into a more easily consumable format, and then you can go back and listen to the neat stuff.
Furthermore, it feels like cheating, dammit. We dialed half of an area code in a full a week back when, and didn't even have the luxury of recording equipment.