Have you ever created a perfect video or audio and realised afterwards that the audio sounds crappy? Or do you have a library of 100s of audio files that have different quality levels on their audio?
If you use Drupal, this is a solution to your problem. Introducing the Auphonic module that uses the Auphonic service to normalize your audio levels using AI.
This uses AI Interpolator and takes an MP3 file and produces an MP3 file.
Auphonic module: https://www.drupal.org/project/auphonic https://auphonic.com/ https://workflows-of-ai.com/ https://podcast.workflows-of-ai.com/
This video is from before the AI Interpolator module became AI Automators, part of the AI module . Module and menu names have changed since, and some steps look different today.
YouTube's automatic captions, lightly corrected. Click a line to jump to that moment in the video.
0:00
hey there Marcus here today we're going to talk about how we can automate audio levels and make them better well actually let's restart hey there Marcus here today
0:14
we're going to talk about how we can automate audio levels and make them better so I think you got the idea what it is we're trying to do here by listening to this but if you didn't
0:28
Auphonic is basically your your AI sound engineer and I have created a module for this so Auphonic is a service that takes audio files and normalizes it it can do a lot more but that's the integration
0:42
that is built into Drupal currently uh and this is of course very important if you for instance have many files with different uh audio levels so this is something I'm very bad at uh I'm using a
0:56
very hobby is microphone right so so you might not get the best quality from from when I'm talking hopefully you can understand me at least uh so if you have multiple files that has different audio
1:11
levels and you want to normalize and get better quality this is a solution for this it's also you know if you're interviewing someone and you might only have one microphone and you might point
1:21
it at that person's face then the questions you're trying to ask might not be the best quality this of course happens a lot if you watch Drupal presentations it might be that someone
1:33
from the audience is asking a question and because the microphone is far away you only hear this very faintly so this is also something that you can try to fix with a
1:43
Auphonic um and we're going to automize this so Auphonic is uh a module I built for the AI Interpolator uh that basically takes a input file and uh generates output file
1:58
that's normalized and that's it so it's very simple uh that's what we're going to set up now before I start with that I would just want to uh uh to remind people about workflows of AI so if you
2:11
don't subscribe to the YouTube channel you can go to workflows of AI and there you can search and filter by different modules where I show different workflows AI workflows connected to
2:24
troo um if you don't know Drupal Dro is open source free software all the modules I show here are open source and free of course they're using um services that cost money so in this case it's the
2:38
Auphonic service however I will mention this you actually get two hours uh free every month which means that if you're if you're only doing some simple podcasting or something like that that's
2:52
not too long you can actually use this the other thing uh that I want to show as well is uh uh this so this is another reason why I did this or this is actually the
3:07
main reason so there is a completely 100% automated um podcast called the Drupal Weekly News on podcast. workflow of- a.com or uh in most most podcast software you can just search for drup of
3:24
Weekly News Spotify not included but almost everything else and the problem with this it's using audio from ElevenLabs then uh that might come at different levels and also when I uh concatenate
3:38
this using ffmpeg there might be uh level differences which was pretty um annoying uh so the idea now is to implement this into the workflow of podcasts uh Drupal Weekly News podcast
3:54
so there's uh normalized good quality so it sounds as professional as a real podcast in terms of Audio Level as well so uh I'm just going to give example how you use this it's actually
4:09
very very easy so uh we're just going to start by downloading uh uh the files we need need in this case we only need two we need the Auphonic uh so I'm running DD so I have to
4:25
set ddev in front and then we just need the AI Interpolator module as well as well and the reason for this is that the Auphonic is just a core service module and then it has the interpolated module and
4:37
the idea is there that maybe there comes uh other Integrations that doesn't have anything to do with uh the interor so I wanted to make sure to split this then we just log into our website after we
4:52
got these two modules click extend and we're just going to search for the Auphonic AI Interpolator Auphonic this will install the Auphonic core it will install AI Interpolator uh that's the first step
5:06
then we just need to set it up so it's under configuration web services Auphonic config and I am just going to get my username because I don't really know what it is here uh so it's not your your
5:23
uh mail it's uh another username so this is my user username uh and then my password so it doesn't work with API key it works with username password right so after I
5:39
have set up this I'm just going to go to content types and add a content type called normalize audio uh in this case it's just helping a lot so I'm just a helper functions I'm
5:54
just going to uh turn off all the stuff there right uh uh for a typical publishing workflow I remove the body field and I'm just going to create two field file now so I'm going to start
6:07
with input file which is a file that takes MP3s we're just going to upload one in this case but in theory you could upload multiple and uh basically allow uh multiple
6:21
outputs then so we have an input file and the thing we're going to uh the thing we're going to automate is the output file so we just take uh file in this case uh
6:34
MP3 and then we enable the AI Interpolator so this is where we're going to find our Rule and we have in this case Auphonic normaliz audio and we're run base mode and we connect it to the
6:46
input file so this is basically telling it take the input file normalize that and put it in the output file if you're going to work with large files this can take some time so make
6:57
sure you're using the cron process work then so you don't use the direct or or batch because they unless you have a long server time out they will basically time out before they're finished but in
7:09
this case I'm just going to use the intro file that I used before uh to generate this so we're just going to add our content now then normalize audio test just going to add a file that's the
7:25
intro. MP3 I'm just going to play it here so you hear the quality of it hey there Marcus here today we're gonna talk about how we can automate audio levels and yeah you get the idea I
7:39
click save okay I did not put in my password correct let's try this again uh let's try another password if this is the correct one we save H now it seems to be working that seems
8:03
to work better uh yeah so the problem with using password is there is no API key that I can click on that has um that has the API key so I have to remember the password uh so now we have output file
8:21
we'll listen to this hey there Marcus here today we're going to talk about how we can automate audio levels and make them better well actually that's so you here it took up
8:35
the volume a little bit um and yeah that's basically it very very simple workflow today um it's not more complex than this this but of course if you work a lot with audio video and you need to
8:51
reset uh the levels or you're working with automated podcasts uh automated um audio files for for blind people for instance then you can get a nice normalization using this service
9:08
and it's as I said you get two hours for free so it doesn't hurt to test it even if you might not want to pay uh for it so that's it thank you for watching
