2_remove_silence.py

def remove_sil(file_path: str, file: str, dest_path: str, format="wav"):
    sound = AudioSegment.from_file(os.path.join(file_path, file), format=format)
    non_sil_times = detect_nonsilent(sound, min_silence_len=50, silence_thresh=sound.dBFS * 1.5)
    if len(non_sil_times) == 0:
        return None
    elif len(non_sil_times) > 0:
        non_sil_times_concat = [non_sil_times[0]]
        if len(non_sil_times) > 1:
            for t in non_sil_times[1:]:
                if t[0] - non_sil_times_concat[-1][-1] < 200:
                    non_sil_times_concat[-1][-1] = t[1]
                else:
                    non_sil_times_concat.append(t)
        non_sil_times = [t for t in non_sil_times_concat if t[1] - t[0] > 350]
        sound[non_sil_times[0][0]: non_sil_times[-1][1]].export(os.path.join(dest_path, file), format='wav')
        
#  via https://github.com/tikhonova/what_would_alan_watts_say/blob/master/speech_synthesis/2_remove_silence.py