Converting and saving audio files with PyDub

Spoken Language Processing in Python

Daniel Bourke

Machine Learning Engineer/YouTube Creator

Exporting audio files

from pydub import AudioSegment

# Import audio file
wav_file = AudioSegment.from_file("wav_file.wav")

# Increase by 10 decibels
louder_wav_file = wav_file + 10

# Export louder audio file
louder_wav_file.export(out_f="louder_wav_file.wav", format="wav")

<_io.BufferedRandom name='louder_wav_file.wav'>

Reformatting and exporting multiple audio files

def make_wav(wrong_folder_path, right_folder_path):

    # Loop through wrongly formatted files
    for file in os.scandir(wrong_folder_path):

    # Only work with files with audio extensions we're fixing
    if file.path.endswith(".mp3") or file.path.endswith(".flac"):

        # Create the new .wav filename
        out_file = right_folder_path + os.path.splitext(os.path.basename(file.path))[0] + ".wav"

    # Read in the audio file and export it in wav format
    AudioSegment.from_file(file.path).export(out_file,
                                             format="wav")

    print(f"Creating {out_file}")

Reformatting and exporting multiple audio files

# Call our new function
make_wav("data/wrong_formats/", "data/right_format/")

Creating data/right_types/wav_file.wav
Creating data/right_types/flac_file.wav
Creating data/right_types/mp3_file.wav

Manipulating and exporting

def make_no_static_louder(static_quiet, louder_no_static):
    # Loop through files with static and quiet (already in wav format)
    for file in os.scandir(static_quiet_folder_path):

        # Create new file path
        out_file = louder_no_static + os.path.splitext(os.path.basename(file.path))[0] + ".wav"

        # Read the audio file
        audio_file = AudioSegment.from_file(file.path)

        # Remove first three seconds and add 10 decibels and export
        audio_file = (audio_file[3100:] + 10).export(out_file, format="wav")

        print(f"Creating {out_file}")

Manipulating and exporting

# Remove static and make louder
make_no_static_louder("data/static_quiet/", "data/louder_no_static/")

Creating data/louder_no_static/speech-recognition-services.wav
Creating data/louder_no_static/order-issue.wav
Creating data/louder_no_static/help-with-acount.wav

Your turn!

Spoken Language Processing in Python