A simple python script to take a AWS transcribe json file with speaker labels and print a plain text transcript

extract_transcript_with_speaker_labels.py

#!/usr/bin/env python3

# Take a AWS transcribe json file with speaker labels from stdin and
# print out a plain text transcript with the speaker_label items at the
# start of line with a colon

# Copyright Mark Jenkins <mark@markjenkins.ca>
#
# Copying and distribution of this file, with or without modification,
# are permitted in any medium without royalty provided the copyright
# notice and this notice are preserved.  This file is offered as-is,
# without any warranty.

from sys import stdin
from json import load as json_load

transcript_json = json_load(stdin)

for seg in transcript_json['results']['audio_segments']:
    print( seg['speaker_label'] + ":", seg['transcript'] )