If you do get to the real silk data, you can decode it with the original Skype Silk SDK. There is probably no python port for this, but you can invoke external libs from python. Once decoded, use ffmpeg/Audacity raw import/other to convert to WAV/mp3 and test the audio. Then in python, using the wave library or wavio api should work. So to convert this audio file in MP4 file format to an actual MP3 file, we are using this line of code: # this splits the audio file, the base and the extension base, ext = os.path.splitext(output) # this converts the audio file to mp3 file new_file = base + '.mp3' # this renames the mp3 file os.rename(output, new_file) In this tutorial, we are going to see how to convert Mp4 to Mp3 files using Python. This task can be easily done using the moviepy library from Python. First, install the moviepy library. pip install moviepy. Now import the required functions from the library. from moviepy.editor import VideoFileClip,AudioFileClip. My gut feeling is that audio data does have the frames information but I can't get it to convert properly. I tried using io.BytesIO and the python wave module and neither seem to have worked for me, although I am very new to working with audio and could have made a mistake. Show activity on this post. I'm working on the BOT industry for Dyscord and I need to play a voice clip in a kinetic knowledge I have a 32-bit computer. import discord from discord.ext import commands import os client = commands.Bot (command_prefix="!") @client.command () async def play (ctx, url : str): print ('We have logged in as {0.user Slice audio # pydub does things in miliseconds ten_seconds = 10 * 1000 first_10_seconds = song [: 10000 ] last_5_seconds = song [ -5000 :] Make the beginning louder and the end quieter I want to convert webm files to wav files with Python to analyze. Is there any simple way to do the conversion from webm to wav in Python? I looked through all questions here and on google. I know there are some possibilities, but i can't convert the files locally with ffmpeg or convert them with the API from cloudconverter website. Steps to convert audio file to text. Step 1: Import speech_recognition as speechRecognition. #import library. Step 2: speechRecognition.Recognizer () # Initializing recognizer class in order to recognize the speech. We are using google speech recognition. Step 3: recogniser.recognize_google (audio_text) # Converting audio transcripts into text. ID1Oi.