Transcripts
1. Introduction: Hey, everyone. Welcome to audio editing using AI and Text. I'm Ricky Lahiri,
decision scientist by profession and a hobbyist
content creator. In this course, I teach my own real world audio
editing workflow. The exact system I use to
clean audio, remove errors, tighten pacing, and
improve clarity using AI and text
based editing tools. Instead of working with
complex waveforms, you learn how to edit audio
by simply editing text, making the process faster, more intuitive, and
far more efficient. This course is built
for creators who want results without
unnecessary complexity. If you record
podcasts, voice overs, or spoken content, this workflow will save you
time and mental effort. So thank you so much for
listening to this clip, and I hope you will
enjoy the course, see you in the course.
2. Introduction to InShot and Walkthrough : Hey, everyone. Welcome
to the first lecture in my audio editing
using text cost. And in today's lecture, I'm going to introduce
one of the apps I'm going to use to edit
audio using text. And this app is called in short. Here's the app.
I've clicked on it. Now, this is available
on IOS and Android, and I'm using an
iPad to record this. So I have it on IOS. Now, this app has a free
tire and a pro tire. I would suggest you
get the pro tire, which is very inexpensive. In India, this costs around
1,300 rupees or $15. In the US, it costs $40 and
not for a month for a year. Now, this entire audio editing using
transcripts and using text can be done using some more advanced apps
such as Descript AI. But descript is
far too expensive. Compared to what I'm using
right here, in short, right? Descript will charge
you per month what in short charges you
per year, almost, right? So that way, this is a more inexpensive and
reasonably priced way of doing and like I said, DScript can do it, but
it's more video focused. And this workflow, which is my own workflow that
I'll teach you, it uses this in short app
and another app called Dolbon which I'll show you demonstrate in
the next lecture. But for the time being,
download in short. And like I said, if you
want to do it on the cheap, if you want to do
it inexpensively and make sure that you're not spending way too
much money to do this while you're
recording podcast and, you know, while you're
recording audio for different purposes, maybe courses, maybe some
other purposes, right? Maybe motivational speeches or whatever you are doing, right? If you are using my workflow, you can do it for as
low as $16 per year. You need to spend $16 per year, and you can do the
entire audio editing using text and using
AI for $16 a year. At least in India,
that is the price. Now, in the UK where I live, although my Apple
account is from India, in the UK, it does not
cost astronomically high. It costs more, but not as much as compared to
something like descript.ai. Even in the UK, it's around, I believe 35 pounds the last
time I checked per year, not per month per year, which is a very good deal. So I'll urge you to
get the software. Like I said, it has a free
tire and a paid pro tire, the free tire will
not allow you to do what I'm doing right
over here, right? So I'll click on open,
and as you can see, the app is right over here. And as you can see, this is
a video centric app, right? This does not have
an audio option. So we need to get audio into this using a
roundabout workflow. And it's a very easy workflow. It's my own workflow. But what you need
to do is, you know, what you will need to do is you will need
to click on video, and you'll need to get
one of these videos into the software, right? And like I said, this app has a pro tire
premium membership, and it costs $16
per year in India, and it costs a little
bit more in the UK. The US price I'm not sure about, but it costs a little
bit more in the UK, but like I said, still reasonably priced
compared to descript.ai. Thank you so much.
I'll catch you in the next lectter
and I'll show you and walk through Dolby on to show you what Dolby on can do. And then I'll
combine everything. And in three lectures, I'll demonstrate how you
can edit audio using tech transcripts
and AI. Thank you.
3. Introduction to Dolby On And Walkthrough: Hey, everyone. Welcome
to a new lecture. And in this lecture, I'll show you how
I'll use Dolby on a software that is
free to remove noise, to add equalization, to boost my audio and do a
bunch of other things. And Dolby O is free, is free of charge,
and you don't need to spend a penny on it. That's the best part
about Dolby on. So I'm going to click on Open. And as you can see, this
is the Dolby on interface. You can record stuff over
here using the microphone. You can record a video over
here using the video option. Right? And what you can do is you can kick off
for Live Stream two. So you can record audio,
video and livestream, but we are not concerned
about audio writer right now. While if you're using Android, you can record using Dolbon, and it's a great way to record. And I'll suggest if
you are using Android, please do record using Dolbon. But we are not going
to do that right now. What I'll do is I'll demonstrate this particular software
and what it can do. As I would say, as a beginning to
the entire workflow, which we'll be using clean up audio and edit audio
using text, right? So I'll use this particular
track called New Recording, which is something I recorded right now, and I'll play it. So as far as the Russia Ukraine
war goes, I believe in, right now, it's a stalemate, but frankly, speaking, Ukraine
has no chance of winning. So I have this his
Audio write over here. It's just that with Western Western you can do
with this audio, right? Now, you can go to tools. You have a bunch of
options over here, and I have my iPad in
landscape position, so it's appearing kind of
like this because it does not automatically switch to
landscape, but you can see it. You have tools, right?
And you have this option, which is like download option, and you can download
using messages, mail you know, you can download you can
download to SoundCloud. You can share audio and you
can share video, right? You can do all of these things
using the Download option. You have the star
option where you can star mark this recording, and you have the
three dots over here. And when you click
on them, you can see that you can add visuals. You can rename the audio file,
you can delete it, right? We'll come to this later, especially the add
Visuals option is how we are going to
convert audio to video. Right? And you have
tools over here. Look, follow my cursor. You have tools over here, right? And I'll click on tools.
And as you can see, you have style over
here, so you can choose different styles for your audio. I can use Tum let's
see how it sounds. Russia's advanced. But
Russia has what it needs. It has three if they
sue for B. Modes, the different styles that
you can apply to your audio. Kind of like mastering. Now, if you don't want to
do any of that and if you want to reduce noise,
let's listen to the audio. There's a lot of
background noise. Click on noise
reduction over here, and noise reduction runs
from gentle to strong. So you have at the lower
end of the spectrum, zero noise reduction, and at the highest end
of the spectrum, you have complete
noise reduction. I'll apply complete
noise reduction. You can choose what
you want based on the amount of noise
you have in your audio. My audio is very noisy. Now listen to this.
Let's compare to that. It's a lower end situation
between h and ear. Now, it's much better, right? Some of the background
noise is gone, of course. While I was recording this, I was in public and there
were other people around, so you cannot filter
that noise out. But, you know, most of the background noise
is gone, right? Now you can adjust tone. You have treble, mids and bass. You can adjust tone if
you want to adjust tone. So you can increase the treble. You can reduce the
treble below zero. You can increase the base.
You can increase the base, and you can reduce the
mits to minus seven, or you can increase the
base to plus two plus four, and it goes up to
plus 19, right? So you can do that.
Then you can add boost. You can boost your
audio recording. Let's listen to this.
France lost it. France wondered what he said. So if you add boost, you know, it makes your sound booming. It makes it more pronounced. And you can reduce
the boost level, too, in order to make your audio less pronounced less emphatic, right? That is what you can do. Okay. And you have
trim over here, and you can trim
the audio, right? And you can use this particular round slider where my cursor is Look there, my cursor is hovering over the slider, and
it's called start. You can use the slider.
You can pull it towards the right to
trim from the beginning. There or you can use the cursor or use a slider called end right over here
where my cursor is. And you can pull it to the
left to trim from the end. So that is Dalvon free
of cost completely. And in the next lecture,
I'll show you how I record my audio or my podcasts, and then you'll understand,
you know, what you can do. And for Android, like I said, I shot is kind of
cheaper is $10 in India, $16 on iPad, but $10
on Android in India. And I'll be on is free
everywhere, right? And in the UK, in shot is
around 30, $35 per year. And on Android is cheaper. Everything is
cheaper on Android. That does not mean
Android is cheap, but everything is
cheaper on Android. But in the UK it's
marginally higher price, but it's not too exorbitant, compared to descript, which is around $20 per month, right? Depending on the
geography, right? So this is done, and what I will do is, I'll end this video over here, and then I'll show you
how I record my audio. Thank you so much. I'll catch
you in the next lecture.
4. Recording Audio: Hey, everyone. Welcome
to a new lecture in the audio editing using
transcripts and text and AI code. And today, I'm going to show
you or in this lecture, I'm going to show you
how I record my audio. I use the voice memos app. Now, this is an app that comes
with your iPad for free. It's an Apple app,
and it comes with the iPad and with
the iPhone for free. So you do not need to buy it. It's already in
your iPad and IOS. And it's a great app, and I use it usually
to record my podcast. So I'll click on the app. And as you can see, I have
a couple of recordings, so I'll not be bothered about
those for the time being. What I'll do is I'll
record a new recording. And to do so, you got to
click on the record button. Now, if you have an Android,
you don't have this app. Android has its own
audio recorders depending on which tablet
or phone you're using. But in case you
want to, you know, apply some of the
advanced tools, the voice memos app on
iPad Allows, do not worry. You may not have those tools, but Dolby on can do whatever. And in short, and Dolby
on combined can do whatever the voice memos
app on iPad can do. I'll start recording, and
I've started recording, and whatever I'm saying from
now onwards until I stop the recording will be captured
by the voice memos app. And I'm recording this
in order to show you how you can use certain tools on the Voice Mimos app on iPad. So I'm going to click on Done
because I'm done recording, and I have my recording
right over here, right? Now, I can do some editing
right here. How do I do that? Go to the top right corner. You have this
option called Edit, click on Edit, right? So you can actually trim your audio by you
have the slider, playhead right over here
and on the playhead, my cursor is hovering right now. So so I can pull it towards the right to trim
or I can pull it towards I can click at the end and pull it
towards the left to trim. I can put it somewhere
in the middle, right? And it will do
nothing because it's a playhead the trick is either
trim from the beginning, which is what I'm
doing right now, clicking on the playhead and pulling it
towards the right, and you can click on the end and you can trim
from the end too, right? Now, I'm going to click on
the slider button over here. There are a bunch of sliders.
I'm going to click on this. And as you can see, you can
increase playback speed. Let's play this audio. And I've started recording
and whatever I'm saying from now onwards
until I stop the recording, it'll be captured by
the Voicemos app, and I'm recording this. As you can see, if I pull the slider to the right and increase the speed
of the playback, the playback becomes
really fast, right? But we don't want that. We don't want it
to sound garbled. And another thing you can do is you can enhance recording. It's an AI based tool that suppresses all the
background noise. It makes the audio recording
sound much better, but this is not available
on Android, by the way. Voice memos is not
there on Android, but you can do the
same thing using Dolby on as I'll demonstrate
on the next lecture. But for the time
being, you know, we are going to use
enhanced recording in voice memos app to suppress all the background
noise, and I've clicked on. I've toggled on
enhanced recording. I can also toggle
on Skip silences. What this will do is it'll skip all the silent
portions of the video. For instance, at the
beginning of the video, there's a silent portion. In between if there
are silent portions, it will skip all the
silent portions. And this is a double edge sword, because if you remove
all the silences, then your voice
might sound rushed. You recording might
sound very, very rush. And it'll sound extremely,
extremely fast. Now, some silences, if they're
too long, can be removed, but Skip silence is not really an ideal tool to edit
those silences out. I'll do them using in shot
in the future lecture, and you'll see how I can
do it using in shot. For the time being,
this was just to demonstrate how
skip silence works. But also, like I said, you know, enhanced recording is a great
function that is available. In voice memos to suppress
background noise. And like I said, skip
silence is a double edge. I'd rather not use
it in voice memos. I'd rather do this on in
shot. And I'll click on Done. And now I have it over
here as recording four. Now I'm going to save
this recording, right? What I'll do is I will press
on the recording, right? First, I will change the
name of the recording. I'll name it test because this is the
test recording, right? I'll click on return, and now what I'll do is I'm going to save this
recording to files. So I'm going to click on the recording and
the naming is done, and now I will click on this
particular button over here, which is the download button. And what I'll do is
I will send test. I'll save it to files right, and I'll save it in
the folder where I'm saving all my lectures. So I'll save it in that folder. Now test is saved. Now we'll see what we can do using Dolbon in
the next lecture. Thank you so much. I
hope you learned a lot, and I hope this helps you
catch you in the next lecture.
5. Convert Audio To Video And Edit Using Dolby On: Hey, everyone. Welcome to a new lecture in the
audio editing course. And today, I'm going to show you how you can do three things. First, clean up messy audio. Does not matter if
you recorded it on iPad or iPhone or Android
phone or Android tablet. You can use any
recording you have, and you can clean
it up on Dolbon. I'll show you how to
boost recording I'll show you how to improve the
quality of recording, and then I'll show you
how to create a video from an audio file
easily in 1 second. You don't need I
movies, final cut, filmora to create
an audiogram or create an audio file with a
still image that takes time. This will do it in 1 second. So first thing I'm going to
do is I'm going to import the test file that I recorded
in the previous lecture. I'll click on look at where my cursor is always
follow my cursor. I'll click on the
button over here. I'll go to Import from files. And what I'll do is I'll go to the audio editing
using text folder, and I'll import the
test audio file. And test is now in Dolby on. So I'll click on Test, right. What I'll do is then I'll
minimize this window. And as you can see, I have the tools,
all of it available. The first thing I'm going
to do is I'm going to convert this into Video How. Go to the three dots over here where my cursor is and
click on Add Visuals. And you can select which
visual you want to add. There are a bunch of options. Add any visual I
like the purple one. I'm going to click
on Select now. Look at where my
cursor is, right? Follow my cursor. I'm going
to create the select one. And now my audio is a video. Simple as that, right?
Look, it's a video. And I've started recording and whatever I'm seeing
from now onwards. It's an audiogram, right? So I'm going to minimize
the video again. Now I'll go to tools. The first thing I'll do is I'll clean up the audio
noise reduction. That's why I told
you, even if you're recording on Android and not on iPad and you don't have the enhanced recording
option, it does not matter. You can use Dolbon the noise reduction feature
in DolbuO to remove noise. So what I'll do is I'll just put in the strongest
setting over here. I will apply the strongest
noise reduction possible. If you have a cleaner audio, you can opt for level
five noise reduction. I don't have a clean audio. I'll opt for level
ten noise reduction, right, which will ensure that most of the background
noise is gone, right? And if you have
really clean audio, you can go for two no problem, but in this case,
I'll go for ten. Now, how does it matter? Noise reduction matters because noise reduction suppresses
the background noise, but it also suppresses the
quality of your voice, right? So if you're applying
more noise reduction, that means your voice may
sound kind of robotic. So the golden rules apply five, at least when you're
doing it on Doll Beyond. Apply five in the
sense that apply mid level noise reduction rather than high level
noise reduction, right? But if you have clean
audio, you can apply two, but you have really messy audio, you have to apply
ten, otherwise, it's going to sound really
crappy. I've done this. I have applied noise reduction, cleaned up the audio.
Now I can change tone. Now, let's say my
voice is mid range, so I want to accentuate
and emphasize on my voice. So I'll increase the
mid two plus four. Treble, I'll increase
two plus one, and bass, I'll increase
two plus one, two. Let's see how it sounds.
Until I stop the recording will be captured by
the voice memos. Now, if I increase the treble to less than 16, let's
see how it sounds. And I'm recording this. It sounds very trebly, right? Very trebly. So I'm
going to pull it back. I'm going to use treble too. This is how you can
adjust your base level, your treble level,
your mid level. I'll click on the
Tick Mark over here, and then I'm going to go to boost and boost the
recording, right? So that it sounds
really it sounds as if it's coming out of
a loudspeaker, right? In order to show
you how you can use certain tools on the
voice Mimos app on iPad. So as you can see, I
have boosted my voice. It's made my voice more
emphatic. Louder, right? It has more gravity. That is what you can do
with boost, right? Now, if you want to trim,
you know, you can trim. I would suggest not to use
trim over here because we'll use artificial
intelligence to edit the audio. We'll edit the audio transcript, and by doing that, we'll edit
the audio itself, right? Or in this case, the
audio grab the audio with this video label or rather video wrapper or
video, you know, cover. So I'm going to click on
the Tick Mark over here, and now what I'll do
is I'll click on Done. Look at where my cursor
is. I'll click on Done. And now what I'll do is I'm
going to export this video. Now, I can export as audio. I don't want to do
that. It's a video. I'll export as video. I'll click on I can
save video to photos, which is the image folder, image app on IOS, or I can use the more
video apps option. And this will start
exporting the video. Once it's exported, I get this I get this
list of options. So I'm going to save two files. Look at where my cursor is. I'm going to save
to files, right? And I'm going to save
in the same folder, I saved the audio file, and I'll named test. And now it's a video file, right? I'll click on Save. That's it. So we
have a cleaned up, nicely manicured, nicely processed audio
sound right now, right? And what we'll do
with this audiosund is we are going to edit this audio using
artificial intelligence in in short. Thank you so much. I'll catch you in
the next lecture, where I'll show you how to edit using artificial
intelligence, edit using text and
transcript in in short, and do it on the cheap or do it rather inexpensively
so that you don't end up spending a fortune trying to get your
podcast business running, trying to get your audio content
business running, right? The idea is to go lean. Everyone is talking about
lean is the buzzword. So if you can spend less to get the same results or get
better results, why not? Thank you so much. I'll catch
you in the next lecture.
6. Edit Audio Using Transcript And AI: Hey, everyone, welcome
to a new lecture. And right now I'm in the folder where I have my test video file. So what I'll do is I'll press
on the text and click it, and I'll go to share over here, and I'll share it to Ishot, which is my video editor, which I'll use to use AI to
edit using transcript, right? And as you can see, my
video is on is in short. Now, I'm going to actually discard this
for the time being. Now, if you want to import video using the video
option over here, right where my cursor
is, click on it. You can import the
video from your album. You can import it
from your photos, or you can import it from
other material, right? But since while we
were on Dolby on, we did not save the
video to photos. We saved it to files. You won't find the video
over here in photos. So what you can do
pretty much is you can go back to the folder where you saved your
video test video, and I'm in the folder right now. I can click on this test video. I can click on Share and I'll send it to Ishot in this manner. Now, if you want to
avoid all of this, just save it to photos
from Dolby One. While you're saving save
the video to photos, right? Is the basic save the
video option on Darby O. So now I have the
video. Let's play this. And I started recording and
whatever and seeing now, we have cleaned up the
video to a certain extent. Using the Dolby on noise
reduction feature, right? But I want to clean it up
further. What do I do? Now, I'll go to an option
over here known as volume. The tool over here that
I'll use is volume. I'll click on volume. The video, I think is loud enough. The audio is loud enough. I'll just click on D noise removes removes all
sorts of noise, right? It cleans up the audio
to a large extent. Even if Dolby on could not produce background
noise completely, you can come into In shot. You can come to Inshot and
use the volume option, and in the volume option, you'll find the denoise
tool and you can denoise. I'm going to click on
the tick Mark over here. Now, the volume option, the denoise option
is available in the free tire on Ishot. But what I'm going to
show you next is not available on the free tire.
You have to pay for it. And remember, if you're
using the free tire, there will be a watermark. If you're paying for
the software, well, you can use something
known as voice enhance. What does voice enhance do? It isolates your voice, it can either isolate the
background or the voice. So if you want to
focus on your voice, make certain that all
the background noise is absolutely suppressed. You can click on voice
only over here, right? So this is kind of a spectrum. At the left end of the
spectrum, you have voice only, you have voice isolation at the right end
of the spectrum, right at the end, you have
background isolation, right? Background only. And as you move from background to
the left, right? The voice becomes louder
and more in focus. And finally, when you reach voice only where my cursor is, at this point, you're just
going to hear the voice. So I'm going to
click on voice only. And as you can see, this is the in short software is using artificial intelligence
to make sure that all my background noise is
gone and only my voice. I'm sorry, recording and
whatever I'm saying from now on. Look at the quality
of the recording now. All the background noise
is gone because I've used voice isolation essentially voice only or voice isolation. Whatever you call it,
this is a great tool, and this will absolutely
clean up your audio. Click on the Tick Mark
over here, and that's it. You have an audio
that is completely free of background noise, right? Completely free of
background noise. Now, what do we do now? Now that we are done
with voice enhance, we are done with, you know, voice only, and we
have a clip which sounds absolutely clean,
professional level. What we need to do right now is we need to filter
out the silences, and if we have made a mistake
while speaking, right? If we have made a
mistake in terms of saying something
that is not factual, making a mistake with
some logical assumption, or if you're recording
audio content and you mispronounce something and
you get your facts wrong, you want to from the
recording, right? How do you do so? Well, you
have to use the AI cut. Tool over here. The
AICAtTol as you can see, my cursor is right on it. The AI cut tool
available only in the pro tire of the software. The free tire has
a lot of tools, but it won't allow
you the advanced AI based tools that in
short office, right? Obviously, right, if you're
using the free tire, then the problem is, you know, if you do edit something any video using the free tire,
there'll be a watermark. But if you pay In India, 1,300 rupees or $16 for the year and in the UK around 40
40 pounds for the year. If you pay that money, you get access to
the pro tire and it's far cheaper than
anything else out there, and you get this tool called
AICAt which is a great tool. Now I'm going to click on
it. And as you can see, what it'll do is
it'll autodtect and remove pauses and filler words in videos. This is
what it does, right? Look at where my cursor is. Auto detect and remove pauses and filler words in videos. Let's see what it does. And Valla it has auto
detected silences, right? It has auto detected silences. Now, along with the silence, the first thing I'll do is I'll delete the silences.
What do you do? It has already check marked
the silences, right? And you can see there's
a red check mark, red, not checkmark, but red cross over here, which means that
these portions of the video must be
and will be removed. So you have the red
crosses over here signifying the places
where there are silences, there's a long
silence, et cetera. Click on the tick Mark over
here, and that's it, right? The silences are gone. And
I've started recording, and whatever I'm saying from
now onwards until I stop the recording will be captured
by the voice memos app. So the silences are gone. As you can see, it's flawless. There is no disruption to the
flow of the audio, right? Now, what I'll do is I'll
go back to the edit option, and what I'll do is I'm going
to remove the first line, and I have started
recording and whatever, and the video is going to start from the audio
for the video is going to start from and whatever
I'm saying from now on. So what do? I just select
this particular line, this particular sentence,
right? I'll play this way. I'm recording this
in order to show you how you can use certain
tools on the voice. Now, as you see, this is the entire transcript of the
video file I gave in shot, and inshot is going through
all the sentences except whatever is marked by
the red cross mark. What does it mean? It
means that whatever I'm selecting for removal from the
video during the playback, the software will
remove those portions. It has removed all the silences, and it has removed
the first line. Now, let's say I don't want
to remove the first line. What I'll do is I'll just click on it again
and uncheck it. As you can see, the red
cross mark is gone. I'll remove the
second line, right? Now, let's play
this video again, and you'll see the second
line is no longer there. And whatever I'm saying from
now on was no longer there. Now, you can use certain
tools on the voicemail started recording until I stop the recording. Did you
see what happened? It started with and I
have started recording, and now it directly went to until I stop the recording
will be captured, right? So I'll start with and I
have started recording again to demonstrate
demonstrate this again. And as you can see, I've
selected the sentence over here, and whatever sentence I select, by the way, basically, the player will play
that sentence, right? Or play from that sentence. So if I select until I stop recording,
look at where my curse. There is always follow my curse. So if I select until I stop recording will be captured
sentence and click on play. Until I stop the
record. I'll play that. I'll play from that. We
play from that sentence. And what I'll do
is I'll start from the beginning and I've started recording, and I'll click on. I started recording. Until I
stop the recording will be. So as you see, this particular sentence
and whatever I'm saying, look at where my cursor is, and whatever I'm saying
from now onwards, I basically selected
it for removal. It has the red check
mark assigned to it. And during playback, the
sentence was removed. So you can actually remove portions of your
audio transcript, and this will change the audio. If you want to remove
a huge segment of your podcast or any other
audio recording you have, you can easily remove this using this tool. I'll
give you the transcript. You just select what
you want to remove. And once you've selected
what you want to remove, silence is awkward
phrasing, fillaers, all of that, you know, you know, right, et cetera, all of that. Once you've selected
all of that, and they'll have a red cross
mark assigned to them. Once you've done all of that,
just click on the Tik Moe, and we have cut the
video successfully. And what I'll do is I'll
play from the beginning. Until I stop the recording will be captured by the voice memos. And as you notice, it has
removed the silences, and it has removed the sentence. I selected for removal, and it starts with the sentence, the first sentence and directly goes to the third
sentence, right? Because the second sentence
I selected for removal. Now click on the
tick mark again. This process is done. We have successfully edited audio using the transcript and the text of the audio using the captions, using
artificial intelligence. That's it. That's how you edit audio using artificial
intelligence, using the transcript
and the text. You remove a portion
of the text, you remove silences,
and automatically, all the silences
will be removed. The text you have selected for removal will be removed, right? Now, once you're done
with this and you have your audio file cleaned
up audio file over here. Go to the export option
Export button over here. Look at my mine. Cursoris click on it. Click
on Save. It's saving. And now you can save to files. You can save to a
lot of other things. Just save to files,
right? What you're going to do is you're going
to save to files. I'm going to click
Save to files. I'll save it in the same folder where I've saved
everything else, and I'll name it,
test, edited, right? Perfect. Click on Save. And I'll see you in
the next lecture where I'll show you how you can reconvert this video into
audio easily, right? Thank you so much. I'll catch
you in the next lecture.
7. Convert Video To Audio: Hey, everyone. Welcome to the last lecture in this course. And today, I'm going to
talk about how we can convert video files to audio
files. Why do we need it? Well, we converted
our audio file, which we recorded using
voice memos into video file using Dolbon and we edited the file using
Dolbon and in short, using the AI cut to transcribe, rather to edit
using transcripts. And now that we have
edited the video file, we need to reconvert
it back to audio. Why? Because ultimately we
are dealing with audio? Objective is to create
a studio quality audio. What I'll do is I'll go
to this button where my cursor is with the
music note on it. In the sense, the symbol
of the music note on it. I'll click on the button
and now I'll go to the Import File option right
at the lower left corner, right, lower bottom left corner. I'll click on this and I'll
click on Import from Files. And I'm going to import
the test edited file. It's essentially the video
file that we saved after we were done with editing it using Dolbon and in short, you know, using AI to edit using transcripts and doing all
the other stuff we did, including voice isolation, background removal, all of that. So I'll import this into Dolbon. I'll click on this.
I'll click on Open. And this has been
imported to Dolbon. As you can see, we have the test edited
file right over here. Now, what I'll do is I'm going to go back to the main
screen or rather, I'm going to select
the text edited file, and we have the test edited
file right over here. I'll just play it for
your convenience. I started recording. Until I stop the
recording will be? So the file is right over here. I'll click on the
minimize button. Right now as full screen, I'll click on the
minimize button, just follow where my cursor is. And then what I can do
is I can go to tools and do all my noise reduction, tone change, boost, trim style
sort of operations again. You know, if someone is
finicky and wants to keep using noise reduction
to reduce noise, I would recommend against it. If you use too much
for noise reduction, your voice is going
to sound robotic. We have already done
enough operations on the audio and the audio is perfectly fit for consumption
at this point in time. So I'll not doing any of these. I'll just what I will do is I'll just click on Done
over here, right? And then what can I do? Well, I can click
on the three dots and I can rename the file. Let's rename the file and
call it final, right? Text, test, rather. Final. So right now, I'm calling it
test final, right? This is the final version of the recording that
we are going to save. And now what I'll do is I'll go to the Export button
right over here, follow my curse service
on the Export button. I'll click on the Export button. There are a bunch of
options over here, right? You can send via messages, you can post to social media. You can share the audio and
you can share the video. Last time, we shared
a video, right? We created an audio gram
and we shared the video, and we shared it to
more video apps. In the sense, we
exported it to files by using the share more
video apps option. This time around, I'm
going to share the audio. We have a video file, but if I click on
Share Audio and I'll click on the three dots, right? As you can see, my
cursor is hovering over the button with the three dots using which we can share audio. I'll share the video. And Dolbon will automatically convert my video to audio, huh? Well, I'll click
on the three dots over here, and as you can see, it has shared or rather saved the audio file
as an audio file. I just saved the video
that we created, the audiogram that
we created and edited right now
as an audio file. And I can save this two files. I'll click on Save to files, and I'll save it as
test final, right? No problem, no issues. I'll click on Save. And this has been saved as an audio file. The video has been
saved as an audio file. Let's check if it's
an audio file, and it's very easy
to check, right? I will go to the
Import button again, right over here on
the top left corner. And this is this is in
landscape, but, you know, Dolbon has difficulty switching between landscape and portrait. It's a problem with the app. It does not switch intuitively as easily as some other app. So please bear with me. And I'll click on the Import button. I'll click on Import from files. And as you can see
right now, right, I have the test final file
right over here, right? The test final file has been
saved as an audio file. Follow where my cursor is. My cursor is on the
test final file, and it has been saved as
an audio file, right? I've selected it,
right? So this way, you can easily convert a video file to an audio
file using Dolbon. So the workflow we used
was we recorded the audio, added some enhancements
to the audio, then we imported it into Dolbon. And after that, we
created an audiogram. We did some editing,
we reduced some noise. We added some features
to the sound, and after that, we
imported it into in short. Then we did some voice
isolation denoising. And after that, what
we did was we edited the audio of the video that we created using artificial
intelligence, using transcript. We did that. We saved it as the final version of our
video audiogram file, and then we imported the
video audiogram, right? We imported the video
into Dolbon and we re converted it
into audio file. We saved it as audio file. The video was
converted to audio. And that is how you
convert video to audio. Thank you so much. Thank you so much for joining
me in this court.
8. Outro: Hey, everyone. You have now seen how audio editing
can be simple, fast, and repeatable when you work with the
right workflow. What matters isn't
mastering tools, it's having a system
you can rely on. I have shared the exact process I use as a content creator, combining artificial
intelligence and text based editing to remove
friction from audio production. Take this workflow,
adapt it to your needs, and use it consistently. Thanks for taking this course. I am Ricky Lahiri, and I hope this
workflow helps you create better audio
with lesser effort. Thank you so much. Thank you for joining me in this course. I'll catch you in
some other course I'm teaching. Thank you so much.
Ricky Lahiri, Content Creator, Writer and Marketing Researcher
