Speech to Text script, only for small videos, using google speech recognition.

speechToText.py

#!/usr/bin/env python3
import speech_recognition as sr 
import moviepy.editor as mp
import sys

clip = mp.VideoFileClip(sys.argv[1])
clip.audio.write_audiofile(r"/tmp/converted.wav")
audio = sr.AudioFile("/tmp/converted.wav")
r = sr.Recognizer()

with audio as source:
  audio_file = r.record(source)
#   result = r.recognize_google(audio_file)
  result = r.recognize_google(audio_file, language = "pt-BR")

# exporting the result 
with open('recognized.txt',mode ='w') as file: 
   file.write("Recognized Speech:") 
   file.write("\n") 
   file.write(result) 
   print("ready!")