Getting intelligible transcripts from AWS

Question

I'm trying to create a transcript of a Skype/phone conversation I had by converting the video to an audio file, uploading the file to Amazon Web Services, getting a transcript made there through the Transcription services there, and downloading the transcript.

When I follow this process I get a JSON file. When I open the file in Excel, the file contains the text of the transcript (with some misrecognized words, which is to be expected) and a bunch of numbers, letters, and timestamps in brackets. The text and the other information are separated from each other, so that if I copy and paste the contents of the file into Word or Notepad, I get the textual transcript at the beginning of the file (in this example, ~3 pages of text) and all of the bracketed information in the bottom of the file (in this example, ~90? pages of text).

How can I get the information from the downloaded JSON file into a document so that the bracketed information (numbers, letters, and timestamps) somehow corresponds with the text? I'd like each timestamp to be near the piece of text to which it's referring.

Thanks.