Audio processing using Pydub and Google Speech Recognition API in Python

In this tutorial, we are going to work with the audio files. We will breakdown the audio into chunks to recognize the content in it. We will store the content of the audio files in text files as well. Install the following modules using the below commands.

pip install pydub

If you run the above command, you will get the following successful message

Collecting pydub
Installing collected packages: pydub
Successfully installed pydub-0.23.1
pip install audioread

If you run the above command, you will get the following successful message.

Collecting audioread
Building wheels for collected packages: audioread
Building wheel for audioread ( started
Building wheel for audioread ( finished with status 'done'
Created wheel for audioread: filename=audioread-2.1.8-cp37-none-any.whl size=2309
8 sha256=92b6f46d6b4726e7a13233dc9d84744ba74e23187123e67f663650f24390dc9d
Stored in directory: C:\Users\hafeezulkareem\AppData\Local\pip\Cache\wheels\b9\64
Successfully built audioread
Installing collected packages: audioread
Successfully installed audioread-2.1.8
pip install SpeechRecognition

If you run the above command, you will get the following successful message.

Collecting SpeechRecognition
Installing collected packages: SpeechRecognition
Successfully installed SpeechRecognition-3.8.1

We have two steps in the process.

  • Breaking the audio into chunks.

  • We have to extract the content using SpeechRecognition.

Take one audio file from your library. Let's start the code.


# importing the module
import pydub
import speech_recognition
# getting the audio file
audio = pydub.AudioSegment.from_wav('audio.wav')
# length of the audio in milliseconds
audio_length = len(audio)
print(f'Audio Length: {audio_length}')
# chunk counter
chunk_counter = 1
audio_text = open('audio_text.txt', 'w+')
# setting where to slice the audio
point = 60000
# overlap - remaining audio after slicing
rem = 8000
# initialising variables to track chunks and ending
flag = 0
start = 0
end = 0
# iterating through the audio with incrementing of rem
for i in range(0, 2 * audio_length, point):
   # in first iteration end = rem
   if i == 0:
      start = 0
      end = point
      # other iterations
      start = end - rem
      end = start + point
   # if end is greater than audio_length
   if end >= audio_length:
      end = audio_length
      # to indicate stop
      flag = 1
   # getting a chunk from the audio
   chunk = audio[start:end]
   # chunk name
   chunk_name = f'chunk_{chunk_counter}'
   # storing the chunk to local storage
   chunk.export(chunk_name, format = 'wav')
   # printing the chunk
   print(f'{chunk_name} start: {start} end: {end}')
   # incrementing chunk counter
   chunk_counter += 1
   # recognising text from the audio
   # initialising the recognizer
   recognizer = speech_recognition.Recognizer()
   # creating a listened audio
   with speech_recognition.AudioFile(chunk_name) as chunk_audio:
      chunk_listened = recognizer.listen(chunk_audio)
   # recognizing content from the audio
      # getting content from the chunk
      content = recognizer.recognize_google(chunk_listened)
      # writing to the file
      audio_text.write(content + '\n')
   # if not recognized
   except speech_recognition.UnknownValueError:
      print('Audio is not recognized')
   # internet error
   except speech_recognition.RequestError as Error:
      print('Can\'t connect to the internet')
   # checking the flag
   if flag == 1:


If you run the above code, you will get the following results.

Audio Length: 480052
chunk_1 start: 0 end: 60000
chunk_2 start: 52000 end: 112000
chunk_3 start: 104000 end: 164000
chunk_4 start: 156000 end: 216000
chunk_5 start: 208000 end: 268000
chunk_6 start: 260000 end: 320000
chunk_7 start: 312000 end: 372000
chunk_8 start: 364000 end: 424000
chunk_9 start: 416000 end: 476000
chunk_10 start: 468000 end: 480052

Checking the file content.

# opening the file in read mode
with open('audio_text.txt', 'r') as file:

If you run the above code, you will get the following result.

English and I am here in San Francisco I am back in San Francisco last week we were
in Texas at a teaching country and The Reader of the teaching conference was a plan
e Re
improve teaching as a result you are
house backup file with bad it had some
English is coming soon one day only time
12 o1 a.m.
everything about her English now or powering on my email list
sports in your city check your email email
Harjeet girlfriend
next Tuesday
checking the year enjoying office English keep listening keep smiling keep enjoying
your English learning


If you have any doubts regarding the tutorial, mention them in the comment section.

Updated on: 01-Nov-2019


Kickstart Your Career

Get certified by completing the course

Get Started