#🧬│ai-chat
1 messages · Page 255 of 1
so is it "ladsplaining" when ladies do it? :)
yo
We call that Bitchsplaining
Hey folks! Newbie alert!
yo
hi
"Just for consideration, Mad Max was set in 2021... Is it socially acceptable to dress like this straight away, or do we give it a few weeks?"
"Hope ye like leather"
Does applio work well for you?
Can you give me links to Google Colab to create songs with AI?
It's pride month, you can't beat em so you might as well join em
hi, I was wondering how can I get a link code like this https://huggingface.co/kaengpil/seungmin/resolve/main/seungmin.zip
from the hug me ai voice source?
can someone help
I have an account alr
everytime i scream or like cough or smt like that my voicechanger jst sounds robotic can someone help me fix that
i usa wokado btw
im bisexual heh
theres more than screaming coughing
whispering and eating food
and stuff likemthat sounds robotic
when i do all those things and it sounds weird and obvious
well, now I know.
Give it a few hours with the right diplomatic resolve even the republicans would have a hard time disagreeing with.
what's the benefits of buying a model instead of just getting one from #1175430844685484042
also whats the difference between model training and a personal ai voice model
if you buy a model from a model master you're guaranteed good quality
voice models in #1175430844685484042 are a hit or miss
model training is the process of creating an ai voice model
Hi
hi
merhaba kolay gelsin
herkese
inanılmaz bir yer burası
ama level mı atlamam lazım
hi

Can anyone remember which option takes only the lead vocal and not the backing vocals in UVR?
hi
Sup
Yes
It’s open source so you can check the source code if ya wanted to
hello
@dusty dove I still can't access to the verified chat :/
OOF my bad
Ayo? @dusty dove level 8 !!! 
maybe I need to be more active idk
just posting your art probably will do the trick
There is no need if you need help with ai
You need level 5 tho
I know
this video worth? https://youtu.be/We5oYpCR3WQ
work?
well
Yes but the guide is bad
thats what i said
EOL - No further Updates
Github - Blanc-dot
Discord - Blanc_dot
Despite being end of life, most if not all information has not really changed, so should be very accurate until actual new stuff comes out.
Other Links
Antasma's Local Error Fixes
Antasma's Colab guide
Sushi's useful Links - You need...
i tried to install python and pytor but after 4 hours i want to eat a barrel of a shotgun
Use this guide instead, duckus missed a lot of things
You don’t need to install python and PyTorch
@nimble knoll use this guide instead
aight
used that video and it worked for me
Ayo? @pine tinsel level 1 !!! 
like the duckus one
well duckus said i need to install python and stuff
@orchid slate What program are you using?
amd
He’s wrong
ah okay so download the one he says
Isn’t the one he provides the Cuda one?
That wouldn’t work
to do what ? i am using many programs
The Cuda one won’t work on AMD
ohhhh right right
only NVidia works on Cuda
@nimble knoll https://huggingface.co/wok000/vcclient000/resolve/main/MMVCServerSIO_win_onnxdirectML-cuda_v.1.5.3.18a.zip?download=true here’s the DirectML one
The program is called VTuber Studio (you can get it from steam)
@orchid slate Write it to me
i dont have any experience with coding at all
Ayo? @nimble knoll level 1 !!! 
You don’t need to
so i follow the wokada instructions but for what is the last link you send
EOL - No further Updates
Github - Blanc-dot
Discord - Blanc_dot
Despite being end of life, most if not all information has not really changed, so should be very accurate until actual new stuff comes out.
Other Links
Antasma's Local Error Fixes
Antasma's Colab guide
Sushi's useful Links - You need...
yes
Here is the good guide
yes
It provides downloads, settings depending on GPU, how to fix lag etc
That’s the download for the voice changer for AMD GPUs
It’s also on the guide
ah ok
well in that case i will type my progress here when im finished with the stuff
thank you : D
@orchid slate How can I create a character like yours?
you can find videos on youtube how to use this program
Hayatında hiç sunucu görmemişsin gibi :D
Hm
Hay
Hai
нет
Is anyone good at making RVC Models type shit?
hi

guys what software can use as voice changer? the one i used stopped working
before i used w-okada
https://rentry.org/rvcrealtimeguide use this instead ig
Can someone make a MARINA voice model
When you make a dataset for rvc do you have to still cut the audio into short clips for the dataset?
nope
rvc does that, anyways
with preprocessing
Oh so I can add a full song for each one?
yeah
or just combine everything in one audio
Can someone tell me, how do these people make the ai voices sound so smooth? Are they using a different app?
https://youtu.be/koBcKtC-wpk when I download these models here and run it through RVC GUI it still sounds full of artifacts and unstable.
I think it might be through a text to speech thing?
elevenlabs
probably elevenlabs
you'd generate tts with a model that sounds kinda similar, then convert with rvc
That makes a lot of sense, thanks!
yw :)
Have a good day! ^^
you too! ✌️
hey guys my other discord got banned
1
how do i record the voice, or hear the voice model that i'm using
Ayo? @hallow dove level 3 !!! 
recording the voice could be done by connecting the cable into audacity, and it should automatically play your own voice back
why isnt my mic working i didnt everything
like w the cables n stuff discord wont pick it up as a mic
i found it. but the pth and index file aren't picked up
maybe i did smt wrong with the input and output device
send a screenshot in #✨│ai-help
anyone know an estimated time on how long rvc gui is supposed to take
Hi
im sorry for my loud mic
please unmute me i think i fixed it
i fixed my microphone im using my phone now
@tepid basin
Hi, I'm looking for proper vocal isolation to make a good AI cover. I tried MVSPE or something like that, but the queue is too big and I can't use it from the cloud to my phone. I also tried Apilo AI.
Or something like that, but the music sung by the model was not good, he was coughing, there were strange sounds, etc
There is also a problem here because I cannot find MyDrive to add vocals to the separation and music to another folder
????
@elder willow
In this case, when I have MP3 music, does it put it into Input folder?
Yes?
@elder willow
@covert lake
And vocals for output?
Folder
Vocals to Input and MP3 music to Input?
@elder willow
ERROR: [generic] '/content/drive/MyDrive/Separar or https://youtu.be/rWhlD4DqT3o?si=YpUy6pTVSdvsduD8' is not a valid URL. Set --default-search "ytsearch" (or run yt-dlp "ytsearch:/content/drive/MyDrive/Separar or https://youtu.be/rWhlD4DqT3o?si=YpUy6pTVSdvsduD8" ) to search YouTube
---------------------------------------------------------------------------
ExtractorError Traceback (most recent call last)
/usr/local/lib/python3.10/dist-packages/yt_dlp/YoutubeDL.py in wrapper(self, *args, **kwargs)
1605 try:
-> 1606 return func(self, *args, **kwargs)
1607 except (DownloadCancelled, LazyList.IndexError, PagedList.IndexError):
11 frames
ExtractorError: [generic] '/content/drive/MyDrive/Separar or https://youtu.be/rWhlD4DqT3o?si=YpUy6pTVSdvsduD8' is not a valid URL. Set --default-search "ytsearch" (or run yt-dlp "ytsearch:/content/drive/MyDrive/Separar or https://youtu.be/rWhlD4DqT3o?si=YpUy6pTVSdvsduD8" ) to search YouTube
During handling of the above exception, another exception occurred:
DownloadError Traceback (most recent call last)
/usr/local/lib/python3.10/dist-packages/yt_dlp/YoutubeDL.py in trouble(self, message, tb, is_error)
1010 else:
1011 exc_info = sys.exc_info()
-> 1012 raise DownloadError(message, exc_info)
1013 self._download_retcode = 1
1014
DownloadError: ERROR: [generic] '/content/drive/MyDrive/Separar or https://youtu.be/rWhlD4DqT3o?si=YpUy6pTVSdvsduD8' is not a valid URL. Set --default-search "ytsearch" (or run yt-dlp "ytsearch:/content/drive/MyDrive/Separar or https://youtu.be/rWhlD4DqT3o?si=YpUy6pTVSdvsduD8" ) to search YouTube```
@elder willow
/content/drive/MyDrive/Separar or https://youtu.be/rWhlD4DqT3o?si=YpUy6pTVSdvsduD8
That that?
You're all good, I'm not able to voice unmute while you're not in a voice channel, so next time you see me in there just @ me and I'll unmute you
whever i open the voice changer it says its waiting for web server and never loads
hello
delete stored_setting.json and restart okada
ty it worrked
yw :)
I don't understand it all
anyone ever have input only show system or file
.
didn't give mic permissions to the browser, i suppose
Help
does anyone know how to get the voice changer to be picked up in other apps
Ayo? @tardy igloo level 1 !!! 
Pls help
output_folder:
content/drive/MyDrive/Vocales
content/drive/MyDrive/Input Folder
I don't understand how to do it
It gives me errors as it is done now
You will have to download a audio cable like VAC Lite
@storm meadow
i just downloaded
FileNotFoundError Traceback (most recent call last)
<ipython-input-3-97d7db895b10> in <cell line: 74>()
72 extensions = (".mp3", ".wav", ".flac")
73
---> 74 uvr_cli(audio_input, output_folder, extensions, output_format, model)
<ipython-input-3-97d7db895b10> in uvr_cli(audio_input, output_folder, extensions, output_format, model)
37 audio_input = "/content/temp"
38
---> 39 for audio_files in os.listdir(audio_input):
40 if audio_files.endswith(extensions):
41 found_files.append(audio_files)
FileNotFoundError: [Errno 2] No such file or directory: 'content/drive/MyDrive/InputFolder'
could you help me figure out how to work the software
it looks rly complicated
to me atleast
Did you download VAC Lite?
yea
Run the setup64 file
And go through the setup
Make sure it’s NOT set as your default mic
@storm meadow
.
Make sure your directories don’t have any spaces in them
There aren't
I no longer have
content/drive/MyDrive/InputFolder
content/drive/MyDrive/OutputFolder
More errors
Is that the names of the folders on drive aswell?
Yes
what colab link do you guys use for making ai cover? mine doesn't work🥲
@storm meadow
-colab
Suggestions for @small trench
- Applio, by IA Hispano Google Colab
- RVC Disconnected, by Kit Lemonfoot Google Colab
- AICoverGen-WebUI, modded by Hina Google Colab
- AICoverGen-NoWebUI [English], by Ardha, fixed by Eddy, Hina and Gdr Google Colab
- AICoverGen-NoWebUI [Spanish], credits to Eddy, Hina and Gdr for translating and fixing Google Colab
- Ilaria RVC, by thestingerx Google Colab
- EasyGUI, by rejects Google Colab
- 🆕 UVR5 NO UI for Google Colab, by Eddy Google Colab
- Applio, by IA Hispano Huggingface Spaces
- Ilaria RVC, by thestingerx Hugginface Spaces
- RVC-HFv2, by r3gm Huggingface Spaces
- AICoverGen, by r3gm Huggingface Spaces
- Advanced RVC Inference, by r3gm Huggingface Spaces
- RVC v2 Huggingface version, by Clebersla Huggingface Spaces
If I’m not answering it’s because I don’t know
Me and anyone else here are not obligated to help
!howtoask
How To Troubleshoot 
- Don't simply mention your issue, like "
my rvc is not working". - Describe the step you are on, what you're trying to do, the RVC you're using, a screenshot, etc.
- The more context, the better.
- Don't be desperate. You can ping a Helper, but if they ignore, they aren't available/don't know the answer.
- It's okay if you're frustrated, but don't take it into this server.
- Don't DM without prior consent.
- Don't ask for every little instruction. Put your own effort & test things by yourself.
- Don't ask to ask.
- Check if your answer is a Google search away/on our guides website.
how do i open the program tho i cant find any guis that show change input to output or anything like that
You don’t
Bradley Swaile is a Canadian voice actor. His major roles include Light Yagami in Death Note, Rock in Black Lagoon, Kicker Jones in Transformers: Energon, and Nightcrawler in X-Men: Evolution. In the 1990s, he voiced Mousse in Ranma ½ and Teen Gohan in the Ocean dub of Dragon Ball Z. He has also voiced multiple roles in the Mobile Suit Gundam s...
After you set it up you set the output on w-Okada to line 1 @tardy igloo
/content/Music-Source-Separation-Training
Start from checkpoint: /content/models/MDX23C-8KFFT-InstVoc_HQ_2.ckpt
Instruments: ['Vocals', 'Instrumental']
Total files found: 0
0it [00:00, ?it/s]
Elapsed time: 1.01 sec
.

Where do you do the voices?
Ayo? @earnest pagoda level 1 !!! 
If I’m not answering it’s because I don’t know how to solve it
Me and anyone else here are not obligated to help
!howtoask
How To Troubleshoot 
- Don't simply mention your issue, like "
my rvc is not working". - Describe the step you are on, what you're trying to do, the RVC you're using, a screenshot, etc.
- The more context, the better.
- Don't be desperate. You can ping a Helper, but if they ignore, they aren't available/don't know the answer.
- It's okay if you're frustrated, but don't take it into this server.
- Don't DM without prior consent.
- Don't ask for every little instruction. Put your own effort & test things by yourself.
- Don't ask to ask.
- Check if your answer is a Google search away/on our guides website.

I didn't understand, I just asked where they make the voices for AI
Wasn’t talking to you
If you want to use the voices to make covers use RVC or applio
If you want to use the voices in realtime use w-Okada
-colab
- Applio, by IA Hispano Google Colab
- RVC Disconnected, by Kit Lemonfoot Google Colab
- AICoverGen-WebUI, modded by Hina Google Colab
- AICoverGen-NoWebUI [English], by Ardha, fixed by Eddy, Hina and Gdr Google Colab
- AICoverGen-NoWebUI [Spanish], credits to Eddy, Hina and Gdr for translating and fixing Google Colab
- Ilaria RVC, by thestingerx Google Colab
- EasyGUI, by rejects Google Colab
- 🆕 UVR5 NO UI for Google Colab, by Eddy Google Colab
- Applio, by IA Hispano Huggingface Spaces
- Ilaria RVC, by thestingerx Hugginface Spaces
- RVC-HFv2, by r3gm Huggingface Spaces
- AICoverGen, by r3gm Huggingface Spaces
- Advanced RVC Inference, by r3gm Huggingface Spaces
- RVC v2 Huggingface version, by Clebersla Huggingface Spaces
Recommend Applio huggingface?
Thank you, I would like to know if there is anyone here who changes faces on video
Facefusion to swap faces
thank you !!
This server is mostly for AI voices so you probably won’t get any support for it here
OK
hi
hi
It's possible or not
Rule 3c
What is your goal?
Test whether AI can do it
anyone know if theres any japanese ichigo voice models already for free? I didnt find any, its a little crazy there isnt one already.
yea
yoo people use my copypasta 
W
@elder willow hi
Path needs to be /content/drive/MyDrive/InputFolder and /content/drive/MyDrive/OutputFolder.
And the audio files inside /content/drive/MyDrive/InputFolder
Are you sure you put the "/" before the content?
Because my vocals are weak and I'm fed up with it
Send a screenshot, let's start from 0
Send me the complete path
fine
/content/drive/MyDrive/InputFolder
/content/drive/MyDrive/OutputFolder
I've never used AI voice model before but I heard you need CUDA cores to do (near) real time voice modelling. is dis tru?
I'm looking to get my first GPU. So, should I get an RTX then?
Models works for realtime with and AMD GPU too, but ya NVIDIA is better
Okay
FileNotFoundError Traceback (most recent call last)
<ipython-input-3-7e89cbd9cbd6> in <cell line: 74>()
72 extensions = (".mp3", ".wav", ".flac")
73
---> 74 uvr_cli(audio_input, output_folder, extensions, output_format, model)
<ipython-input-3-7e89cbd9cbd6> in uvr_cli(audio_input, output_folder, extensions, output_format, model)
37 audio_input = "/content/temp"
38
---> 39 for audio_files in os.listdir(audio_input):
40 if audio_files.endswith(extensions):
41 found_files.append(audio_files)
FileNotFoundError: [Errno 2] No such file or directory: '/content/drive/MyDrive/InputFolder'```
Did you give access to Google Drive?
Yes
lemme try rq
Hmmm it's working for me
Wtf
. Wtf
is there away to like just get the part of the code/lib that makes the tts 😭
Try changing the name of the folders
To Separar and Vocales
but... it's the same
do u have this "drive" folder here right?
yeah but i need this TTS for a project im making rn and its ran locally, so i wonder if i can like use one of the models from here somehow to make a tts with py /if it makes sens
How to search?
Like this
yes yes
Just clicking and opening folders
Yes?
yep, copy the path
and paste
do the same for the other folder
btw what's the format of ur audio files?
But the Vocales folder is empty, only audio for Separar, right?
MP3
ya, audio files needs to be in Separar folder, and the separated files will be saved on Vocales folder
Work 2 audio files found
Processing file: Power Play - Ja na
finally
hmmm, seems a bit much for my use case 😭, cuz basiclly i just wanted to put in a text into a program and boom it will have made a mp3 with the model. N the docs are a bit confusing so if i could get sum help with da
Ayo? @fleet creek level 1 !!! 
dunno wft happen
But now u can use it
just dropping files
u can delete the other folders that u made for test
Keep only the Separar and Vocales folders
And from now on, the vocals file in vocales for the model will work perfectly for singing without coughing and other strange voices, right?
Eddy
and the model that u re using
there are a looot of models
for a lot of things
each model is different
Use this?
Power Play - I'm coming for you (Official video) 2019(1)_(Vocals)_model_bs_roformer_ep_317_sdr_12.mp3
Bs Roformer is for vocal ans instrumental separation
that's the vocals file, ya
the other file is the instrumental one
I still have one
Power Play - I'm flying at you (Official video) 2019(1) [vocals]_(Vocals)_model_bs_roformer_ep_317_sdr_12.mp3
reload the drive page
Well, I have this one and this one
Power Play - Ja na Ciebie lecę (Official video) 2019(1) [vocals]_(Vocals)_model_bs_roformer_ep_317_sdr_12.mp3
Power Play - Ja na Ciebie lecę (Official video) 2019(1)_(Vocals)_model_bs_roformer_ep_317_sdr_12.mp3
Power Play - Ja na Ciebie lecę (Official video) 2019(1) [vocals]_(Vocals)_model_bs_roformer_ep_317_sdr_12.mp3
vocals]_(Instrumental)_model_bs_roformer_ep_317_sdr_12.mp3
So which one is correct for me?
Vocals one
And it's an empty vocal with only the singer?
Ayo? @elder willow level 10 !!! 
Yes?
The vocals file is the singer's vocal without the instrumental, like an acapella
It depends
From what?
If the audio still has reverb or backing vocals you should remove them
and if the model u re using is good
l What model will I use to remove it?
Reverb etc
I want to get rid of everything, I want to leave just singing without any background effects so that the cover will be good
So which model to use in uvr-5?
drop the result of the first separation vocal in DMs
The workflow is:
Bs Roformer (Vocal/Instrumental)
De-Echo-De-Reverb (Reverb)
UVR-BVE-4B_SN-44100-1 (Backvocals if so)
Move the vocals files that u have separate and it's now on Vocales folder to Separar folder
Instrumental,Vocals(Vocals),Vocals yes?
then process again with the de-reverb model, then keep the no reverb one, move again and continue
yep
This one too?
Power Play - I'm flying at you (Official video) 2019(1) [vocals]_(Instrumental)_model_bs_roformer_ep_317_sdr_12.mp3
nah, that's the instrumental
only the vocals files
Only if you need it, but if you don't need it then no.
But if you want to make a cover, you have to save it because you have to mix the parts later
So remove the instrumentals?
A okay
So Vocals files go to Separar and Instrumentals go to Vocales?
Yes ?
Good done
.
Yes ?
Did u remove the reverb?
I don't want to get rid of everything and leave only singing, so I have to remove the reverb?
All effects etc. are to be removed as desired
I want empty vocals
As I told you, you need at least 3 models to remove everything
.
But how to do it now if I have done everything, added instrumentals to Vocales and vocals to Separar
Process again with De-Reverb model
Bs rofermer I've already used it
ya ik, then De-Reverb
Output should be wav if your gonna train
Since wavs are loseless and MP3s are compressed
But they can produce big file sizes
Why does it take so long to remove reverb?
hey, 👋 i am new here
what model is this?
Hello
It’s the lil Wayne mixtape version da drought volume 1
ok
Anyone know any programs i can pair the voice changer to?
Ayo? @quiet drum level 1 !!! 
hi'
yo chatt
Ayo? @worldly breach level 1 !!! 
Discord
i mean ones that can alter the voice
a
hi
people on discord are saying i cut out a bit
is there a way to fix this?
when using the voicemod
voicemod?
Think it's gone
hi
W-Okada’s real-time voice changer
What is the best voice changer looking for one
-colab
- Applio, by IA Hispano Google Colab
- RVC Disconnected, by Kit Lemonfoot Google Colab
- AICoverGen-WebUI, modded by Hina Google Colab
- AICoverGen-NoWebUI [English], by Ardha, fixed by Eddy, Hina and Gdr Google Colab
- AICoverGen-NoWebUI [Spanish], credits to Eddy, Hina and Gdr for translating and fixing Google Colab
- Ilaria RVC, by thestingerx Google Colab
- EasyGUI, by rejects Google Colab
- 🆕 UVR5 NO UI for Google Colab, by Eddy Google Colab
- Applio, by IA Hispano Huggingface Spaces
- Ilaria RVC, by thestingerx Hugginface Spaces
- RVC-HFv2, by r3gm Huggingface Spaces
- AICoverGen, by r3gm Huggingface Spaces
- Advanced RVC Inference, by r3gm Huggingface Spaces
- RVC v2 Huggingface version, by Clebersla Huggingface Spaces
Can you use APPLIO without a Nvidia Gpu? (Locally)
...
without*
Имао
for generating audio yeah but its going to be really fucking slow on anything other than fcpe or rmvpe
For inference yes but it will be slow
You won’t be able to train
wherer are the downloads
Ayo? @young dune level 1 !!! 
what downloads
i cant find rvc or any of the downloads for the voice changers
i can only find the voice models
Last update: Mar 10, 2024
thank you
Is there a white plain t's voice model download
Hi im new
hi
yoo i how can my voice be clear using a virtual mic anyone?
i keep having some electrical sound when i talk
in okada its good not discord
same problem
sounds great in the app sounds staticky in discord
yep
what can we do
not sure
hello
an error keeps showing up when i try to download the model
I need help of someone who can use 11Labs voice cloning or can train similar models for a small project.
...
Benim adım Yoshikage Kira. Ben 33 yıllar eskisiyim. Benim evim kuzeydoğu seksiyonun içinde Morioh taki tüm villalar, ve ben değilim evli. Ben çalışıyorum olarak bir eleman için Kame Yu mağazaları, ve ben ev alıyorum her gün tarafından 8peme inde en sonunda. Ben içmiyorum sigara ama ben bazen içiyorum. Ben içindeyim yatağın tarafından 11peme ve yapıyorum ben emin alıyorum 8 saatlerin uykusu hayır farketmez ne. Sonra elde etmekin ılık sütü yapıyorum bunun hakkında 20 dakikanın gitmek yatak, ve ben etmek. Hayır problemler uyuyorum kalan sabahı beğenmek bebek. Ben uyanıyorum yukarı dışarı hiç yorgunluk sters içinde sabahın bende söyledi buradaydı hayır sorunlarda son teftişimde.
1 ping
me to
Ayo? @elder willow level 2 !!! 
Anime kızı amk
To use them locally?
yaa
Either search the model in #1175430844685484042 and click the hugginface link or copy the huggingface link and use it on a google colab
Or weights.gg,it has most of the aihub models there
what is huggin face
guys
Basically an ai website
Copyright
yes or nah
There's a download button
oo
Ayo? @somber ravine level 1 !!! 
is donald duck safe?
can you send me link??
it's copyrighted
what isnt copyrighted
Search on google
ok
Joe mama
Are you gonna use a colab?
what do you think is the best??
Colabs
like female voice
Idk i make mahiro ai covers and haven't used any other
nah its another
Locally on your pc?
see ur dm
Ok
joe mama alr
Ayo? @uneven seal level 1 !!! 
i came here from the video of yeet chris
link me the joe mama one
Guys, how do we install rvc on macos?
Hi
Hiii

Hi I did no reverb and what should I do next if it looks like this for me?
@stark scarab
I have 10 files when I did no reverb
Vocales folder
man adding autotune to ai covers makes them sound so much better to be honest
@storm meadow
YİAAAAAA bayıldım
Komedik harem animesi ama harem animelerine bin basıyor 😂
Anime 5 manga 29 şuan
Yeni mi çıktı
Geçen yıl ekimin 10'nunda başladı
Yeni sezon yeni yılda geliyor
Heee iyiymiş
İngilizce okuyorsan atayım mangadex linkini
Evet İngilizcem var
Ok atıyom bidk
tbh autotune fixes all vocals most of the time
guys whats the app to download ?
For AI covers?
yea ai voice changer
RVC
yea nice but wich one
Why when I made no reverb uvr all and bs rofarmer, I don't have no reverb vocals for refomer and uvr all in the files?
I want to shit
I only have the instrumental etc
And various ones, e.g. vocals instrumental uvr no reverb, but I don't have vocals no reverb uvr on the reformer
Ne içtiysen bana da ver
I am not gay
if the vocal suddenly goes high or low its kinda hard to hide
i mean you could use something like melodyne and the instrumental would prob just hide it
im the one and only sheriff
Hey guys, how do I transfer the changed voice from okada to apps like zooom and google meet when making video calls
Ayo? @bright idol level 1 !!! 
you need a virtual audio cable, check https://rentry.co/VoiceChangerGuide
EOL - No further Updates
Github - Blanc-dot
Discord - Blanc_dot
Despite being end of life, most if not all information has not really changed, so should be very accurate until actual new stuff comes out.
Other Links
Antasma's Local Error Fixes
Antasma's Colab guide
Sushi's useful Links - You need...
What
But 20 dollars is 20 dollars
I eat pancakes with bread if I have them
waves
Thanks, I've installed it, how do I start and use it?
now just set the cable as your output in okada
and set it as input in the program you wanna use it
guys
pls help me'
im stuck on: [Voice Changer][RVC]: update_settings gpu:0
[Voice Changer][RVCr2] Initializing...
gin_channels: 256 self.spk_embed_dim: 109
[Voice Changer] generate new embedder. (no embedder)
2024-06-09 14:17:57.7771898 [W:onnxruntime:, session_state.cc:1030 onnxruntime::VerifyEachNodeIsAssignedToAnEp] Some nodes were not assigned to the preferred execution providers which may or may not have an negative impact on performance. e.g. ORT explicitly assigns shape related ops to CPU to improve perf.
2024-06-09 14:17:57.7825447 [W:onnxruntime:, session_state.cc:1032 onnxruntime::VerifyEachNodeIsAssignedToAnEp] Rerunning with verbose output on a non-minimal build will show node assignments.
[Voice Changer] Loading index...
Try loading... model_dir\5\added_IVF304_Flat_nprobe_1_K9GorillaTagYT_v2.index
GENERATE INFERENCER<voice_changer.RVC.inferencer.RVCInferencerv2.RVCInferencerv2 object at 0x000001A490463D00>
GENERATE EMBEDDER<voice_changer.RVC.embedder.OnnxContentvec.OnnxContentvec object at 0x000001A4B8384B50>
GENERATE PITCH EXTRACTOR<voice_changer.RVC.pitchExtractor.RMVPEOnnxPitchExtractor.RMVPEOnnxPitchExtractor object at 0x000001A4B8384B80>
[Voice Changer] [RVC] Initializing... done
[Voice Changer][RVC]: update_settings serverReadChunkSize:256
[Voice Changer][RVC]: update_settings modelSlotIndex:1705728161005
[Voice Changer] VoiceChangerManager initializing... done.
[Voice Changer] MMVC_Rest initializing...
[Voice Changer] MMVC_Rest initializing... done.
[Voice Changer] MMVC_SocketIOApp initializing...
[Voice Changer] MMVC_SocketIOApp initializing... done.
Hi this me...
I'll be practising ai projects normally for my career growth.. so I'll need your help guys
Hope you are all doing well in life 🙏
Not mentally but yeah we are
Someone link me with a good Google collab thing
take some data science course
Yeah sure thanks...
What'd the channel I can find Google colabs one
Pn
Accidentally said Pn but sent it purposely
My online blasphemous player friend got blocked from another server for sending these 😂🤣
And yes there is one more besides that one
Hey, what channel can I find colabs
-colab
- Applio, by IA Hispano Google Colab
- RVC Disconnected, by Kit Lemonfoot Google Colab
- AICoverGen-WebUI, modded by Hina Google Colab
- AICoverGen-NoWebUI [English], by Ardha, fixed by Eddy, Hina and Gdr Google Colab
- AICoverGen-NoWebUI [Spanish], credits to Eddy, Hina and Gdr for translating and fixing Google Colab
- Ilaria RVC, by thestingerx Google Colab
- EasyGUI, by rejects Google Colab
- 🆕 UVR5 NO UI for Google Colab, by Eddy Google Colab
- Applio, by IA Hispano Huggingface Spaces
- Ilaria RVC, by thestingerx Hugginface Spaces
- RVC-HFv2, by r3gm Huggingface Spaces
- AICoverGen, by r3gm Huggingface Spaces
- Advanced RVC Inference, by r3gm Huggingface Spaces
- RVC v2 Huggingface version, by Clebersla Huggingface Spaces
@deft kiln
Thanks!
-colab
- Applio, by IA Hispano Google Colab
- RVC Disconnected, by Kit Lemonfoot Google Colab
- AICoverGen-WebUI, modded by Hina Google Colab
- AICoverGen-NoWebUI [English], by Ardha, fixed by Eddy, Hina and Gdr Google Colab
- AICoverGen-NoWebUI [Spanish], credits to Eddy, Hina and Gdr for translating and fixing Google Colab
- Ilaria RVC, by thestingerx Google Colab
- EasyGUI, by rejects Google Colab
- 🆕 UVR5 NO UI for Google Colab, by Eddy Google Colab
- Applio, by IA Hispano Huggingface Spaces
- Ilaria RVC, by thestingerx Hugginface Spaces
- RVC-HFv2, by r3gm Huggingface Spaces
- AICoverGen, by r3gm Huggingface Spaces
- Advanced RVC Inference, by r3gm Huggingface Spaces
- RVC v2 Huggingface version, by Clebersla Huggingface Spaces
idk if this is the right channel to ask but does anyone have an application or website where i can seperate vocals from the music?
-colab
- Applio, by IA Hispano Google Colab
- RVC Disconnected, by Kit Lemonfoot Google Colab
- AICoverGen-WebUI, modded by Hina Google Colab
- AICoverGen-NoWebUI [English], by Ardha, fixed by Eddy, Hina and Gdr Google Colab
- AICoverGen-NoWebUI [Spanish], credits to Eddy, Hina and Gdr for translating and fixing Google Colab
- Ilaria RVC, by thestingerx Google Colab
- EasyGUI, by rejects Google Colab
- 🆕 UVR5 NO UI for Google Colab, by Eddy Google Colab
- Applio, by IA Hispano Huggingface Spaces
- Ilaria RVC, by thestingerx Hugginface Spaces
- RVC-HFv2, by r3gm Huggingface Spaces
- AICoverGen, by r3gm Huggingface Spaces
- Advanced RVC Inference, by r3gm Huggingface Spaces
- RVC v2 Huggingface version, by Clebersla Huggingface Spaces
Ayo? @fringe hound level 1 !!! 
thanks
no i didnt meant to send you mb 😭
Last update: Feb 29, 2024
there's mvsep or cloud uvr
Does the voice blender work in Apillio?
hey
No cap
yo
Have the audio file of your song ready, & let's extract the vocals from it with an audio isolation software.
you can read our docs https://docs.aihub.wtf to know how to train!
Last update: Mar 10, 2024
Hi
hi
hi guys
💥
Hai
prob applio
or ila rvc mainline
https://colab.research.google.com/drive/1mHKTGH5e3SAyDSBss1KtiYRbDdQzwSMs
Then go with BVE
Why are easier colabs with less features are discontinued?,google?
google doesnt like webUI
for free users
Ilaria rvc mainline works tho
ay do u guys know what is the best girl voice model cuz those SUCK
(asking for a friend btw)
ooo ;-;
Ayo? @crisp inlet level 1 !!! 
and this post too
ehh its not good
Hello Aldreyna here. Nice to be with y'all
me too
Hi, I'm new here as well.😇
what are pretrain models for? Is it to make creating a real voice model better?
also i created a voice model but I wasn't able to change their octave of voice. Is this generally because of data set or because I didn't select pitch guidance enabled?
hi
hi
any1 want gta6 ?
you think it will be a big jump from gta 5?
it is !! this is so fu**ing realistic .. and a mf great storyline
@heady wing Where did you go? I'm stranded... Lost and Alone... @heady wing Where did you go? (Ok but no, like seriously... Where is he?) (Don't take this seriously😅) (I'm just trying to be funny, that's all.)
Ayo? @quasi badge level 1 !!! 
What did I do?
where is the voices?
Ayo? @errant valve level 1 !!! 
can somone help me out? For some reason everytime i try to open up voice modulation it instantly closes the terminal
im new here and i wanna ask. is it normal if my gpu goes to 100% for 1 milisec? its not constant, just jumps to 100 and then goes back to 0 or 15 when using w okada
thanks, mate. so its just the interface not calculating it properly
yw
hey my name is rahul and i am from India
unless it severely affects gaming performance while running it
i've never tried it with gaming but will update if it does
Ayo? @hybrid salmon level 1 !!! 
omds
can smb help me everytime i use my voicechanger on vc w smb then the voicehcanger works for the person tlaok
talking aswell? like this shouldnt happen i need help asap
i sue wokado btw
ppl
is there any AI do PPTs
it is tiresome 
Hello
yes unless you resist what Copilot offers
@yourusername
guys how do i connect my okoda to vcs?
yo
yo
how can i stop the delay on my voice changer
how do u get the voice changer files
hello
they help in training, btw check https://discord.com/channels/1159260121998827560/1233407331405004954
How long is the delay and what’s your GPU
There is always be some delay
?
you can search rvc ai voice model:
- #1175430844685484042
- #🔍│find-models
- https://weights.gg/
- https://huggingface.co/models (but watch out cus in hugging face there arent only rvc ai voice models)
- https://applio.org/models
- https://voice-models.com/
if there isnt one, you can:
- #1159289738314919936
- #1191429836321849435
- make it yourself with our docs guides https://docs.aihub.wtf/
ask in help channels
ask in #🔍│help-w-okada or #1192011222023950368
i think i done better now, just bit echoing and still not so real time
Ayo? @next plaza level 1 !!! 
btw do you have suggestion for female us speaker model
i figured it out
i heard these models arent trained for english speaker
idk much but maybe https://tome.app/
Anyone have a video of how to install rvc (not real time) locally, I cant find anything on youtube for some reason 
https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI this specifically?
other wise check out https://docs.applio.org/
Lemme check this out, I'm just trying to make ai covers and figure everything out, I just got this new computer with a 4060 and I was a mac person so I have no idea what I'm doing 😭
use applio then https://docs.applio.org/get-started/installation/
ok thx
Have a good week everyone!!
ae
So funny

Attention i quit using discord now
Whats the easiest way to do AI?
how do i verify?
Ayo? @true storm level 1 !!! 
bro someone just tried to hack my main account
Ayo? @willow warren level 1 !!! 
how do i verify??
q
What does unload voice in the interface section do
Im so lost ive read the manual
wdym? which one are you even talking abt
verify what
To do like ai songs
You can find out in our docs https://docs.aihub.wtf/essentials/how-to-make-ai-cover/
Have the audio file of your song ready, & let's extract the vocals from it with an audio isolation software.
it no work for me when i tried
Ayo? @grand swan level 1 !!! 
does not exsists
yes the old ilaria rvc mangio got removed, either check #📰│dev-updates or use the other cloud rvcs in the docs
like applio
!howtoask
How To Troubleshoot 
- Don't simply mention your issue, like "
my rvc is not working". - Describe the step you are on, what you're trying to do, the RVC you're using, a screenshot, etc.
- The more context, the better.
- Don't be desperate. You can ping a Helper, but if they ignore, they aren't available/don't know the answer.
- It's okay if you're frustrated, but don't take it into this server.
- Don't DM without prior consent.
- Don't ask for every little instruction. Put your own effort & test things by yourself.
- Don't ask to ask.
- Check if your answer is a Google search away/on our guides website.
and ask in help channels
k
I figured it out thaniks, my colab stopped for some reason
Does anyone know why my voice sounds raspy
Ayo? @summer sapphire level 2 !!! 
I tried using taylor swift 1970 and 2024 and same thing
let me in
?
you need to get level 5 by chatting (no spam)
Hi
chatting points +15
Ayo? @peak pine level 1 !!! 
funni coincidence 😭
+9999 aura points
Depends on the model quality, and also if the vocals of the song are cleaned good
do you know of any models that are good
uhh idk abt taylow swift models but, you can search rvc ai voice model:
- #1175430844685484042
- #🔍│find-models
- https://weights.gg/
- https://huggingface.co/models (but watch out cus in hugging face there arent only rvc ai voice models)
- https://applio.org/models
- https://voice-models.com/
if there isnt one, you can:
- #1159289738314919936
- #1191429836321849435
- make it yourself with our docs guides https://docs.aihub.wtf/
I got it from the #1175430844685484042
maybe try to see if there's a better quality one
The taylor swift one
I tried 2 but ill keep checking I think they had the most fire emojis
does it like just sound robotic?
@summer sapphire, I have found 1 results that match your search!
Can someone help me find the @inland dagger toothbrush one he said to find it in his weights profile but Idk where that is
Idk just want it
Also I fw the profile mine is the car they used in backr00ms
Thats where I found it
oh really? I just saw it but its fie
Can I see it
thanks bro
you should track downloades
and see how much you get
hi
Hi
gibt es leute die deutsch können ?
und mir evtl. helfen können bei der Ai Stimme Generieren"
NotADirectoryError: [WinError 267] Dizin adı geçersiz: 'C:\Users\kavak\OneDrive\Masaüstü\dataset.wav' please help
uh
yo can anyone help me, its not loading up anymore
and i have no pic perms so i cant even show
when i load it up its permenantly on a white screen and the command thing says "wait web server" for infinity of time
No
disappear from my sight
The dataset is on OneDrive that’s the problem
Move it to somewhere on your pc
just buy yourself another drive if you need storage
same problem
Ayo? @plush harbor level 1 !!! 
Prob accidentally put it on there
What’s the path?
D:\ses\ses\dataset.wav
bruh
Try putting it on the drive your booting from
not in OneDrive
check dm
It takes a long time to do something like this
I tested it for a very long time
depends on what gpu you are using and the video lenght ofc
you cant make it run in 10 secs on every video for every gpu 😭
Well, I want it fast
are you using the colab?
Huggingface
even worse 😭
its running on cpu not gpu
it will be slow asf for videos
And in colab it's 3 times faster?
Yes
either use google colab free daily gpu, or use kaggle gpu which is better and gives 30 hours daily, but you need a phone number
yes colab gpu is faster
More then 3 times prob
New to this, which should I use for training?
I've got a 1070, 1080ti, and a CPU w/ 2.3 GHz core clock, and 18 cores
1080ti is the best out of those for training
Alright
Would 1070 be similar enough to where I don't have to switch over to my 1080ti?
And, what would the CPU be looking like considering its core count?
Ayo? @fathom dune level 1 !!! 
No matter what you do not want to use cpu for training
Depends on the resolution and length
Tbf, it has 18 cores - which should affect at least some of the speed 🤣
But, no, I understand
21 seconds?
I dunno
Do I need to change the settings or leave the default ones to make it work?
And it looked real
?????
it depends on:
- video fps
- video lenght
- resolution
- and frame processors
It will probably not be 21 seconds
But what I mean is that the film lasts so long
you are face swapping a whole film?
21 sec
how even long is it
Yes
Video 20 seconds
a film of 20 seconds ?
Yes
yea that would be possible, ofc wont run it in like 20 secs, you prefer quality or speed?
if you get better quality, it will be slower ofc
if you want quality, for frame processors check:
- face_enhancer
- face_swapper
- frame_enhancer
if you prefer speed, check only:
- face_swapper
did you upload the source face?
Yes
you need to upload the source face, then the film as the target, and then check the frame processors as i said before, and then, click START
What frame processors???
If I chose a real model, how long will it take?
wdym with real model ?
and i cant estimate how long its gonna take, as i said there's different factors
guys, I'm lost. What is the easiest way to set up a text to speech (where i can use downloaded voice models). I tried to install xtts in python but I get errors
@stark scarab
Applio prob
srsly dont ping random people
you didn't close the colab page right?
Aaah, she shut up
Wtf
/content
sed: can't read /content/facefusion/facefusion/uis/layouts/default.py: No such file or directory
---------------------------------------------------------------------------
NameError Traceback (most recent call last)
<ipython-input-4-221c924b463b> in <cell line: 72>()
70
71
---> 72 if device=="cuda":
73 get_ipython().system('python run.py --execution-providers cuda')
74 else:
NameError: name 'device' is not defined
what
runtime -> disconnect and delete
then run Install cell, and then run cell
my friend was hacked with this cheat, memes come out, the cursor changes
how do you make your own voice for rvc
+15
-docs
Suggestions for @elder willow
- Full AI Voice Model Training Guide (local) by Christopher Villanueva
- Model training with Mainline RVC by Raven (ravencutie21)
- AICoverGen Colab Guide by Eddy (Spanish Helper)
- Create a model with RVC disconnected (colab) by Angetyde
Wrong server? We don’t have any game cheats or anything
Just ai voices mainly
its so complicated why cant i just use a minute voice clip of a voice and turn it into a voice
sry
That’s what your doing Buh
Well they explain it so weird and make me install a 4gb file
and everything for no reason
@elder willow
Ok ai is the process of training
It learns from something called a dataset
!mute 944533621358870548 permanent cock in VC
@papajto muted
Reason: cock in VC
Duration: Permanent
Which is a large amount of data used to make models or pretrains
Without this you wouldn’t be able train your own models
Since there is nothing to train off of
Basically any local ai tools will be a large file size
I dare you to train a model without a pretrain
For example: you can’t ride a bike (train a model) without knowing how to walk (the previous data it uses to help you)
If you care about storage you can use a HuggingFace space or Colab instead which hosts it in the cloud
But which both have limits
Hugging face is pretty valid to store your models
Balbal keeps all his models in hugging face and just loads the link with his RVC forks, works pretty good
hi
Shikanokonokonokokoshitantanshikanokonokonokokoshitantanshikanokonokonokokoshitantanshikanokonokonokokoshitantanshikanokonokonokokoshitantanshikanokonokonokokoshitantan
【Synopsis】
Koshi Torako, a high schooler, one day feels something cold hit her face. Looking up, she spots a girl stuck, her antlers tangled in power lines. Helping Shikanoko, a...
Who got wechat
🥶

how do i actually use the voice models once i download the file?
i use like 100% autotune on Fl studio lol
Ayo? @graceful violet level 1 !!! 
yo can anyone lmk
Does anyone know how to make a voice model?
the type of money i'd burn during black history month (My friend forced me to say it)
is the baseline pretrain default "assets/pretrained_v2/f0G40k.pth" the official one?
Ayo? @analog inlet level 1 !!! 
Ada yg punya Voice model versi Shino aburame dan Neji hyuga
guys why is it so slow for me when i'm using a custom model? 😦
and cheese?
English or Spanish?
i got 5700xt and theres like 23k delay lmao
?
Ayo? @summer sapphire level 3 !!! 
what is 23k
the res
just use cpu for inference
sorry im new
im using colab gpu rn its trash
taking like more than 200 sec
what length?
that's nothing far different from laptop cpu (esp 11th gen intel)
if 44k audio do i need to resample to32k?
Hello
I have a question, Makidanye
Are you Japanese?

我不是日本人
literally
Ayo? @coarse vessel level 43 !!! 

Ohhh you said "I'm [something] Japanese" and 不是 probably means "not", alrightt
So you're Chinese
我也不是中国人
Oki
我是土耳其人 
no
Sorry, I could not find models that match your search "dean martin"


AI HUB Docs