Get the full source code of application here:
Show More Show Less View Video Transcript
0:00
Uh hello guys, welcome to this video. So
0:01
in this video, I'll show you a AI model
0:03
which is recently released by uh Mistral
0:07
AI company which is called as Voxil
0:09
which is a great alternative to tools
0:11
such as whisper API. So this is their
0:14
website vautil.io
0:17
TTS AI model which is texttospech. So
0:21
you can also try this by visiting this
0:23
website. Let me just turn on the volume.
0:26
So right here they or just give you this
0:29
demo
0:30
to answer your questions help with your
0:31
daily task
0:33
Frenchman speaking in English. So you
0:35
can to get started you can simply loging
0:38
in with your Google account and simply
0:40
click sign in.
0:44
So once you sign up you basically get 40
0:46
credits free credits to try out this. So
0:50
you basically get 40 credits.
0:54
So in the pricing model they do
0:56
basically the basic plan start from $29
0:59
per month. You get 500 minutes of
1:01
transcription per month. So it's using
1:03
the voxil AI transcriptions for your
1:06
audio.
1:08
So now there's option right here to try
1:12
out vauil like this. So either you can
1:15
basically generate
1:17
have your own audio file which is
1:19
present and uh this will actually
1:23
transcript.
1:25
So if let's suppose I have an audio
1:28
file.
1:36
So let's suppose if I have this audio
1:39
file right here
1:41
or we can even have uh let's suppose we
1:43
can even record that as well. So
1:48
I can simply say sample
1:52
audio file for subscription. So we can
1:55
basically download this sample audio
1:57
file.
2:03
So click on download.
2:08
So go to this any if you have your own
2:10
MP3 file as well, you can even do that
2:13
as well. So
2:17
right here you basically upload that. So
2:20
we simply go to the download section
2:23
inside audio.
2:36
I think that is present in the audio
2:41
folder.
2:53
Uh
2:56
just wait guys. Let me download this.
3:14
Okay. So it is there in the music
3:16
directory. So just wait I simply go to
3:20
the downloads directory and there it is
3:22
present in the music.
3:27
So yeah so you basically only PNG JPG
3:30
web form please select a valid image
3:32
file.
3:42
What is going on? Think I need to select
3:44
an audio file.
4:06
You provide the transcript here. You
4:09
basically select the model right here
4:11
and then it will try to
4:15
do this. So you need to have an MP3 file
4:18
right here. I don't know why it is not
4:20
accepting audio file for me but you can
4:22
try this as you can see the chats or the
4:27
cats AI unites them all in a unique and
4:30
powerful AI assistance always at your
4:33
disposal whatever to answer your
4:35
questions.
4:45
I think it is talking about the text.
4:48
Let me take the screenshot of this and
4:51
save it.
4:53
I think it is talking about this as
4:56
well. So if I go to this paste this
5:09
so definitely try this tool guys. If you
5:11
have an MP3 file you can use this
5:13
voxil.io model. It's a great alternative
5:18
tool to whisper. It's developed by this
5:20
company which is Mistral AI.
5:25
It's an open-source texttospech model
5:28
for transcription your text.
