#โจโai-help
1 messages ยท Page 299 of 1
Don't always confuse Deiteris W-Okada with the "original version", as they are different versions made by different authors with similar UI.
Try Tg Develop W-Okada or Vonovox. https://docs.aihub.gg/realtime-voice-changer/local/tg-develops-w-okada-fork/ https://docs.aihub.gg/realtime-voice-changer/local/vonovox/
Last update: October 26, 2025
Last update: November 10, 2025
Vonovox can give better audio quality, but its UI is very different than other W-Okadas with similar features.
should i buy a 3070 8gb or a rx 6800 16gb
im so confused although the 16gb is tempting
ive heard that amd doesnt work with w-oakada?
okada
is that true?
That's just how that version launches, it's better than the original 1 million times, and Vonovox is better than the original by 1 billion times
Please help
C:\Users\user\Desktop\Applio>env\python -m pip install torch==2.3.1 torchvision==0.18.1 torchaudio==2.3.1 --index-url https://download.pytorch.org/whl/test/cu118
Looking in indexes: https://download.pytorch.org/whl/test/cu118
ERROR: Could not find a version that satisfies the requirement torch==2.3.1 (from versions: none)
ERROR: No matching distribution found for torch==2.3.1
First of all, why are you trying to downgrade the version of Torch from Applio?
does anyone have anything similar to Ilaria_RVC
what is spin embedder aand how do i use it
@dull swan do you know the name of this?

no mane, sadly idk anything about this

Im using Deiteris W-Okada b2332 fork,
I used to be able to run intensive games on high graphics and still use the voice changer reliably on windows 10
but after upgrading to windows 11, I can only run games on low-medium graphics or else the voice changer breaks completely
Can anyone help me? is there a fix?
anyone know how to download Vonovox
-rt
Guides for Programs that use RVC Models in Realtime for Calls/Games
A Realtime Voice Changer with similar performance to Wokada Deiteris Fork, with extra features, but supported only for Nvidia GPUs on Windows. and without cloud options GUIDE
A personal fork (modified version) of Wokada Deiteris Fork, it just adds some Quality of Life improvements to it like supporting Spin Embedder and Audio Effects. Don't expect too much about it since the creator made it originally as a personal project. GUIDE
Most suggested WebUI with the best general support for many platforms. GUIDE
For Windows Nvidia, Both Wokada Deiteris fork and Vonovox have similar performance & quality. Users should read the pros and cons for both and choose based on their differences, such as UI and Vonovox's paid effects.
Read Wokada Deiteris Fork Pros&Cons & Vonovox Pros&Cons
These options are not recommended for use.
Not suggested, older versions in youtube tuts are even way worse. GUIDE
The program is worse compared to the ones above, and much less updated. GUIDE
It's in the guide
Idk what could have caused that but if u have time to go back to w10 see if it makes a difference
if you're using RTX 50-series gpu, you should use the latest torch version and cuda 12.8 found in the latest applio version
you shouldn't ping random persons that may not know about your context instead of the helper role
!howtoask
- Check Docs & Guides: Your answer may already be in the AI Hub Docs or the https://discord.com/channels/1159260121998827560/1159513888199540817 channel.
- Search the https://discord.com/channels/1159260121998827560/1192011222023950368 : Look for existing posts that solve your issue. Do not invade someone else's post.
Tell your:
- Full GPU Name: (e.g.,
NVIDIA RTX 4060 8gb vram desktop) - Operating System: (e.g.,
Windows 11) - Detailed Description: What were you trying to do and what went wrong?
- Tutorial Used: Link to the guide you were following.
- Screenshot: A picture of the full error message.
To maintain a legal, safe & ethical community, we will NOT provide help for:
- ANY illegal activities.
- NSFW/Porn.
Requests for these topics may be ignored, not helped and result in moderation action.
- Be Polite & Patient: Our helpers are volunteers. You may ping the
Helpersrole once. - English Only: Please keep all conversations in English.
- Don't Ask To Ask.
probably something wrong with your internets
but on the other hand, the URL is wrong
there should be no 'test'
env\python -m pip install torch==2.3.1 torchvision==0.18.1 torchaudio==2.3.1 --upgrade --index-url https://download.pytorch.org/whl/cu118
Would anyone know why my Output Information says error when I try to covert a song on RVC
is vonovox premium worth it?
should i buy a 3070 8gb or a rx 6800 16gb
im so confused although the 16gb is tempting
ive heard that amd doesnt work with w-okada
is that true?
i dont believe it has premium?
unless you mean the premium effects
can someone help rq
amd works with wokada but doesnt work with vonovox
isnt vovonox a fork
whats the difference between vovonox and deiteris if u dont mind me asking
i dont use either of them so i have no idea
can u reccomend me a nvidia gpu i dont want smth too expensive near rx 6
6800
smth with good vram and i can play on 1080p
i would do 3070ti but its 8gb vram
so
4060/5060 Ti 16 GB or just 3060 12 GB depending on your budget
Hello guys. Can I use Vonovox with my GT1030 graphic card?
I don't know if there is a way
Vonovox only works with Nvidia
It could work but it's not gonna work too well, wokada deiteris even struggles with a 1660
and that's the most basic of the 3 up to date good voice changers
The other being wokada tg fork
im planning on installing that last
vonovox is not for me yet
if I want the voice to sound good should I invest in a better microphone?
or is it more gpu based
get RTX 2060 or 3060 depending on your budget
the latter is recommended spec for mainstream gaming usage
I did everything right in Discord, but the sound doesn't change
then you did not do everything right
how could we find what is wrong without your explanation?
!howtoask
- Check Docs & Guides: Your answer may already be in the AI Hub Docs or the https://discord.com/channels/1159260121998827560/1159513888199540817 channel.
- Search the https://discord.com/channels/1159260121998827560/1192011222023950368 : Look for existing posts that solve your issue. Do not invade someone else's post.
Tell your:
- Full GPU Name: (e.g.,
NVIDIA RTX 4060 8gb vram desktop) - Operating System: (e.g.,
Windows 11) - Detailed Description: What were you trying to do and what went wrong?
- Tutorial Used: Link to the guide you were following.
- Screenshot: A picture of the full error message.
To maintain a legal, safe & ethical community, we will NOT provide help for:
- ANY illegal activities.
- NSFW/Porn.
Requests for these topics may be ignored, not helped and result in moderation action.
- Be Polite & Patient: Our helpers are volunteers. You may ping the
Helpersrole once. - English Only: Please keep all conversations in English.
- Don't Ask To Ask.
the decent one in around 50 bucks should be enough
If my screenshot is not a W-Okada fork, then what is it called?
It means you didn't do anything right. It's best to explain about your issue (about using W-Okada) instead of a small rant.
why isnt there any beatrice 2 voice model?
but isnt 3060 12gb worse than 3070
how would that be better
It's more of trade-offs. An entry-level or mid-tier GPU has fewer clock speed and CUDA cores but has more VRAM, while a step-up or high-end one has more clock speed and CUDA cores but has less VRAM. It also happens with some other RTX series GPUs too.
Can anybody help me to generate a not shiny/glossy looking image nor a cute anime style, like the images im gonna send, if you can suggest any websites, styles, prompts, i would highly appreciate it
It's just a google drive folder no need to download anything i just want mor formal not glossy images like in the folder
While true that the preformance of a 3060 is some amount worse the reason it was suggested to you is becuase it has 12GB of VRAM opposed to 8
klm 4 is throwing me fits, are there any special paramaters that are non deafualt that i need to enable?
crash log:
โโโโโโ PRECISION: TF32 / FP16 - AMP
โโโโโโ cudnn.benchmark: True
โโโโโโ cudnn.deterministic: False
โโโโโโ Optimizer used: AdamSPD
โโโโโโ Using Validation: False
Failed to load checkpoint: 'emb_g.weight'. Using default number of speakers.
โโโโโโ Initializing the generator with: 1 speakers.
โโโโโโ Spectral loss: Single-Scale (L1) Mel loss function
โโโโโโ Vocoder: NSF-HiFi-GAN
โโโโโโ Starting the training ...
[ ] Loading pretrained (G) 'rvc\models\pretraineds\custom\D_KLM_HFG_48k.pth'
[ ] Verifying checkpoint for selected architecture: RVC
Error: Key mismatch detected. The checkpoint's parameters do not match the model's.
This may be due to a different architecture or a corrupted checkpoint.
Missing or unexpected keys details:
Error(s) in loading state_dict for Synthesizer:
Missing key(s) in state_dict: "enc_p.emb_phone.weight", "enc_p.emb_phone.bias", "enc_p.emb_pitch.weight", "enc_p.encoder.attn_layers.0.emb_rel_k", "enc_p.encoder.attn_layers.0.emb_rel_v", "enc_p.encoder.attn_layers.0.conv_q.weight", "enc_p.encoder.attn_layers.0.conv_q.bias", "enc_p.encoder.attn_layers.0.conv_k.weight", "enc_p.encoder.attn_layers.0.conv_k.bias", "enc_p.encoder.attn_layers.0.conv_v.weight", "enc_p.encoder.attn_layers.0.conv_v.bias", "enc_p.encoder.attn_layers.0.conv_o.weight", "enc_p.encoder.attn_layers.0.conv_o.bias", "enc_p.encoder.attn_layers.1.emb_rel_k", "enc_p.encoder.attn_layers.1.emb_rel_v", "enc_p.encoder.attn_layers.1.conv_q.weight", "enc_p.encoder.attn_layers.1.conv_q.bias", "enc_p
i used contentvac and rmvpe
best settings for vonovox?
!howtoask
- Check Docs & Guides: Your answer may already be in the AI Hub Docs or the https://discord.com/channels/1159260121998827560/1159513888199540817 channel.
- Search the https://discord.com/channels/1159260121998827560/1192011222023950368 : Look for existing posts that solve your issue. Do not invade someone else's post.
Tell your:
- Full GPU Name: (e.g.,
NVIDIA RTX 4060 8gb vram desktop) - Operating System: (e.g.,
Windows 11) - Detailed Description: What were you trying to do and what went wrong?
- Tutorial Used: Link to the guide you were following.
- Screenshot: A picture of the full error message.
To maintain a legal, safe & ethical community, we will NOT provide help for:
- ANY illegal activities.
- NSFW/Porn.
Requests for these topics may be ignored, not helped and result in moderation action.
- Be Polite & Patient: Our helpers are volunteers. You may ping the
Helpersrole once. - English Only: Please keep all conversations in English.
- Don't Ask To Ask.
please read this before asking
premium vonovox, low quality option does nothing
+1
@hot verge so uhh
is this the right place
ok ok that sounds good enough to me
so i can sort of help
I swear if somebody gets this to work for me
I will like
i don't know what I will do
but I will do something
anyways so
so
the problem is
error?
uhhhhhh
yeah I guess
lemme give you the rundown
I've been trying to use 'okada' because I heard it was good
and free
i started by downloading the whole thing from github here https://github.com/w-okada/voice-changer
and then realised that it didn't seem to go anywhere
so I found myself here: https://huggingface.co/wok000/vcclient000/tree/main
and tried to download the right one for my computer
and then it didn't seem to work
ok idek what the release is
ok right you downaloded form hugginface
this
also do you jabe nvidia gpu?
and are you winddows?
nope
and nope
I'm running this on a macbook air with an intel core i5 from 2017
first of all
am I cooked?
second of all PLEASE
like is this possible
do you see why my situation is so dire now
ok so
its
i5...
uh
maube
if you comprokise on latency
its prob possible
let me see
that doesnt matter you have an intel mac
uhhh
ok i have 2 ideas
one of them can work maybe
lets try first uh
go on
ok sure
what gpu are they using
I'm trying to do this on a macbook air with an i5 from 2017
mac
oh
intel i5
yeahhhh
ok
ok and what
unzip it
and run the like
the terminal thingy first?
and then the http thing second?
it seems there's a problem @hot verge
"zsh: bad CPU type in executable: /Users/admin/Downloads/dist/main"
mmkay
holdup let me make antoehr plan
do you have git
program
i was thinking maybe just git cloning it works
is that what you mean?
lol i just saw
sure sure
bro the most convoluted thing ever
I'm trying to install homebrew
so I can install git
so I can install a voice changer
yeah
"awww yeah it's a home brew"
I see
the fuck's a package manager
I see
I don't but like
I do
but like
I don;t
anyways it seems my computer is struggling to download homebrew
I pasted this code into the terminal which apparently installs homebrew
and its stuck on checking for 'sudo' access
the fuck is sudo
is that like judo
the command is /bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)"
so do i just type
sudo /bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)"
like just type "sudo" and then paste the thing?
you need to type
your password
sudo is like
giving it admin rights
on your computer
cus it needs to mess about with a ton of things
damn
that sounds scary
I feel like I'm a lamb being led into a kebab shop
and by that i mean
this feels like I'm just willingly installing a virus of some sort
i mean ive broekd a few linux installs
before
saved a few
in recovery mode
but you know
whatver
idek what that fucking means man
tehcncially you can get git
this is my only computer so like idfk dude
with no hoembrew
like it prob wont
do anything
mine only borked cus nvidia drivers got angry
but like you have no nvidia
git said i needed homebrew
that something gets messed about with your comptuer
awww man
maybe the virtual cable, ive hear ppl had issues with those
the fuck is a virtual cable
i dont know the chance
i thought that was for like
but its not very high
rerouting internal audio
oh of course
yeah ofc
bruh this install is stuck on
==> Checking for sudo access (which may request your password)...
Don't run this as root!
it just says that in my terminal
I DID WHAT IT ASKED
huh?
who was that and why was the message deleted
the fucks going on
idk man it said smth like "get support here" with a discord link
no!
==> Checking for sudo access (which may request your password)...
Don't run this as root!
this is the problem
apparently I shouldn't run this as root
i dont know im not that good at this either but i have an easier system to deal with
dude I feel like Joji in that one music video
slow dancing in the dark
i feel like this rn bro
man I need to paste a thing to install a thing so I can install a thing so I can install a thing so I can run thing that can install a thing that can run a voice changer
we dont know if itll work yet
it was just an idea i had that could have worked
and even if it works we dont know if your 2017 intel i5 can voicechange at reaosnable speed
ahh yeah
i was thinking LIVE voice changer
maybe I should give up man
maybe this all aint it
kicks can down the street
boefoe
- Check Docs & Guides: Your answer may already be in the AI Hub Docs or the https://discord.com/channels/1159260121998827560/1159513888199540817 channel.
- Search the https://discord.com/channels/1159260121998827560/1192011222023950368 : Look for existing posts that solve your issue. Do not invade someone else's post.
Tell your:
- Full GPU Name: (e.g.,
NVIDIA RTX 4060 8gb vram desktop) - Operating System: (e.g.,
Windows 11) - Detailed Description: What were you trying to do and what went wrong?
- Tutorial Used: Link to the guide you were following.
- Screenshot: A picture of the full error message.
To maintain a legal, safe & ethical community, we will NOT provide help for:
- ANY illegal activities.
- NSFW/Porn.
Requests for these topics may be ignored, not helped and result in moderation action.
- Be Polite & Patient: Our helpers are volunteers. You may ping the
Helpersrole once. - English Only: Please keep all conversations in English.
- Don't Ask To Ask.
my GPU is intel HD graphics 6000,
my operating system is... MacOS? I think thats what its called
macbook air 2017
with an i5 processor
I was trying to install Okada, and I got lost in a maze of files and errors
haishh
haishh?
I havent tried Okada local myself but i doubt it'll run man
yea you can't do anything local on GPU then, and CPU is extremely slow
why not?..
awwww
try cloud
awwwwwww man
id suggest using a cloud option then
awwww
local is probably not gonna work
a cloud option to do live voice changing?
how would that even work
yes
I mean you still can
-rt
Guides for Programs that use RVC Models in Realtime for Calls/Games
A Realtime Voice Changer with similar performance to Wokada Deiteris Fork, with extra features, but supported only for Nvidia GPUs on Windows. and without cloud options GUIDE
A personal fork (modified version) of Wokada Deiteris Fork, it just adds some Quality of Life improvements to it like supporting Spin Embedder and Audio Effects. Don't expect too much about it since the creator made it originally as a personal project. GUIDE
Most suggested WebUI with the best general support for many platforms. GUIDE
For Windows Nvidia, Both Wokada Deiteris fork and Vonovox have similar performance & quality. Users should read the pros and cons for both and choose based on their differences, such as UI and Vonovox's paid effects.
Read Wokada Deiteris Fork Pros&Cons & Vonovox Pros&Cons
These options are not recommended for use.
Not suggested, older versions in youtube tuts are even way worse. GUIDE
The program is worse compared to the ones above, and much less updated. GUIDE
i feel like joji in this gif
instead of the software using ur hardware's resources to inference the voice, it uses cloud to do those inferencing on other stronger computers for you
Hold on a second
its too much man
I think imma just give up
kinda like streaming yk
Last update: September 6, 2025
NVIDIA GeForce NOW
if ya want it

i would guide you step by step but iam sleep deprived and nor do i have my pc with me

i am also sleep deprived
I have school tomorrow dude
i can't stop you, but if you ever want to just ask
well you know
like Sun Tzu always said
"If fighting is sure to result in victory then you must fight"
they should really start making video guides fr
and I'm not sure if victory will ensue from this fight
or maybe i could do that
sun tzu perfected the art of fighting because he invented it
maybe
no no no
you have it all wrong
he knows about fighting more than you BECAUSE he invented it
and then he herd a pair of every animal into a boat and beat the crap out of every single one of them
and only THEN did he perfect it
bro actually fun fact about that
yea they should, griffith should do a voice over for them
because of that, every time a bunch of animals are together in one place it's called a zoo
Well, have a nice day
tick tock heavy like a brinks truck
man thats ingrained
into my fucking brain
I'm getting PTSD every time I hear Tick Tock
!howtoask
- Check Docs & Guides: Your answer may already be in the AI Hub Docs or the https://discord.com/channels/1159260121998827560/1159513888199540817 channel.
- Search the https://discord.com/channels/1159260121998827560/1192011222023950368 : Look for existing posts that solve your issue. Do not invade someone else's post.
Tell your:
- Full GPU Name: (e.g.,
NVIDIA RTX 4060 8gb vram desktop) - Operating System: (e.g.,
Windows 11) - Detailed Description: What were you trying to do and what went wrong?
- Tutorial Used: Link to the guide you were following.
- Screenshot: A picture of the full error message.
To maintain a legal, safe & ethical community, we will NOT provide help for:
- ANY illegal activities.
- NSFW/Porn.
Requests for these topics may be ignored, not helped and result in moderation action.
- Be Polite & Patient: Our helpers are volunteers. You may ping the
Helpersrole once. - English Only: Please keep all conversations in English.
- Don't Ask To Ask.
hi
henlo
should i use vonovox or okada
What GPU do you have?
rtx 5060
oh, damn, yea use Vonovox
thanks :)
Guides for Programs that use RVC Models in Realtime for Calls/Games
A Realtime Voice Changer with similar performance to Wokada Deiteris Fork, with extra features, but supported only for Nvidia GPUs on Windows. and without cloud options GUIDE
A personal fork (modified version) of Wokada Deiteris Fork, it just adds some Quality of Life improvements to it like supporting Spin Embedder and Audio Effects. Don't expect too much about it since the creator made it originally as a personal project. GUIDE
Most suggested WebUI with the best general support for many platforms. GUIDE
For Windows Nvidia, Both Wokada Deiteris fork and Vonovox have similar performance & quality. Users should read the pros and cons for both and choose based on their differences, such as UI and Vonovox's paid effects.
Read Wokada Deiteris Fork Pros&Cons & Vonovox Pros&Cons
These options are not recommended for use.
Not suggested, older versions in youtube tuts are even way worse. GUIDE
The program is worse compared to the ones above, and much less updated. GUIDE
um how do i download vonovox is there a guide i mean its kinda straight forward but i dont trust myself
um help pls ๐
this
right here for ya
Last update: November 10, 2025
do i have to download virtual audio cable
yes you do if you want to use it in Discord or games
hmm alright

what setup do i use for virtual cable ๐ sorry am kinda slow
there are like 3
i obv have a 64xbit operating system but there are 2 64xsetup
i understand it now ๐ผ

sorry one last question
go ahead
how can i listen to myself when using a virtual cable
So there is no monitoring in Vonovox, so you have to switch the output to your headphones/speaker(s)
but then people wont hear the ai voice ๐ค
i used okada like a year ago and i was able to do that
Hi guys, I installed Voice Changer and in the GPU settings, I only see the CPU option, not my graphics card. I have an RX 7600 8GB.
i have a weird bug where if i try inferencing using an rvc mainline model on applio it just flat-out sounds bad even if the input audio + dataset audio is completely clean
same works vice-versa (inferencing an applio model on rvc sounds bad)
is this a known bug/issue/idk or is there a workaround
model quality is also good so im not sure why its like this, its pretty much dissuaded me from using applio at all
GPU is NVIDIA RTX 3060 if that affects anything at all
edit: reinstalled everything, solved (hopefully)
How do I fix the robotic S sounds? 35 minutes of cleaned silence-trimmed training data and 350 epochs are still not enough. Could it just be simply because the training data doesn't contain much S sounds?
omg im sorry, i meant if you wanna hear it before you use it in Discord or games you need to switch to your Headphones/Speaker(s) then for people to hear them you use the virtual cable
!howtoask
- Check Docs & Guides: Your answer may already be in the AI Hub Docs or the https://discord.com/channels/1159260121998827560/1159513888199540817 channel.
- Search the https://discord.com/channels/1159260121998827560/1192011222023950368 : Look for existing posts that solve your issue. Do not invade someone else's post.
Tell your:
- Full GPU Name: (e.g.,
NVIDIA RTX 4060 8gb vram desktop) - Operating System: (e.g.,
Windows 11) - Detailed Description: What were you trying to do and what went wrong?
- Tutorial Used: Link to the guide you were following.
- Screenshot: A picture of the full error message.
To maintain a legal, safe & ethical community, we will NOT provide help for:
- ANY illegal activities.
- NSFW/Porn.
Requests for these topics may be ignored, not helped and result in moderation action.
- Be Polite & Patient: Our helpers are volunteers. You may ping the
Helpersrole once. - English Only: Please keep all conversations in English.
- Don't Ask To Ask.
yea i wanted to be able to hear myself AND in the same time them hearing me
i downloaded a voice monitor software and made it output the virtual cable and that worked
oh good, im sorry i was busy
no its all good already were a great help
Thank you, im glad i could help even a little
get the directml installation of one of following options (except vonovox)
-rt
Guides for Programs that use RVC Models in Realtime for Calls/Games
A Realtime Voice Changer with similar performance to Wokada Deiteris Fork, with extra features, but supported only for Nvidia GPUs on Windows. and without cloud options GUIDE
A personal fork (modified version) of Wokada Deiteris Fork, it just adds some Quality of Life improvements to it like supporting Spin Embedder and Audio Effects. Don't expect too much about it since the creator made it originally as a personal project. GUIDE
Most suggested WebUI with the best general support for many platforms. GUIDE
For Windows Nvidia, Both Wokada Deiteris fork and Vonovox have similar performance & quality. Users should read the pros and cons for both and choose based on their differences, such as UI and Vonovox's paid effects.
Read Wokada Deiteris Fork Pros&Cons & Vonovox Pros&Cons
These options are not recommended for use.
Not suggested, older versions in youtube tuts are even way worse. GUIDE
The program is worse compared to the ones above, and much less updated. GUIDE
- try testing lower epoch ones (around 50-200)
- if the dataset/source is in low bitrate mp3 compression (despite being processed/saved in wav format), it may be the cause
Can voice changer work on ios?
Or do i need a pc
never 
why so if an elephant can't fit on your car? please read spec requirements in the guide as above
That comparison doesnโt really explain anything. Iโm just trying to understand the technical reason iOS doesnโt allow real-time voice changing in regular calls. If there are specific spec requirements or API limitations, Iโd appreciate a clearer explanation instead of an analogy
Not trying to be rude at all
But yes ill read requirements
if the guide hasn't quite explained it, it needs some virtual cable program that only works on windows, linux or mac (different program for different platform)
no even one has managed to get it working under winlator
The data source is from my pc audio recorded with stereo mix, so I don't think audio quality is the issue.
uh
t=2025-11-18T05:47:39+0000 lvl=warn msg="Stopping forwarder" name=http-18888-dac13d8d-99d7-4c46-a0a1-a859a7cd2cf7 acceptErr="failed to accept connection: Listener closed"```
-# I'am using Kaggle, This specific issue never happened to me while using it yesterday i dont know why all of a sudden this is happening to me today.
**yes i did reinstall the kaggle notebook 3 times and did a clean reinstall always just the same issue happening to me here :P i dont know how to fix this**
Any Kind Hearted person pls help me. 
I found that ~50 epoch has least robotic sounding 'S'. Thanks. I'll try retraining the model in 40k, maybe 44.1k dataset doesn't do well with 48k training.
What is it you're trying to do?
@wintry acorn this happens when i use KAGGLE when clicking on start this is the error it gives.
im not sure if theres just something overall wrong with the kaggle servers
hm, I have no idea too sorry
any person with knowledge to this issue pls help
question
which fork is better
deiteris fork or TG Develops fork
I'd say deiteris is better as it's simple and easy to use but I have heard tg fork has more features tho the ui is totally different
too low epochs may have less likeness (sounding a bit off) & accent, so try compare with later epochs and the dataset itself
how do i set up my voice changer
it keeps saying {SIO} rconnection failed Error: xhr poll error
NVIDIA GeForce RTX 5070 with CUDA capability sm_120 is not compatible with the current PyTorch installation.
anyone know how to fix or alternatives?
upgrade to the latest version of torch
im using rvc1006
ahh i see
then you should use the latest version of Applio https://github.com/IAHispano/Applio/releases/tag/3.5.1
the og rvc might error out when trying to upgrade to the latest torch
do i just run the command under the start locally part?
sorry i dont properly understand this type of stuff </3
just get the applio release which is precompiled already (I mean no manual installation needed)
ohh right right
u are actually my savior it works
thank you so so much
!howtoask
- Check Docs & Guides: Your answer may already be in the AI Hub Docs or the https://discord.com/channels/1159260121998827560/1159513888199540817 channel.
- Search the https://discord.com/channels/1159260121998827560/1192011222023950368 : Look for existing posts that solve your issue. Do not invade someone else's post.
Tell your:
- Full GPU Name: (e.g.,
NVIDIA RTX 4060 8gb vram desktop) - Operating System: (e.g.,
Windows 11) - Detailed Description: What were you trying to do and what went wrong?
- Tutorial Used: Link to the guide you were following.
- Screenshot: A picture of the full error message.
To maintain a legal, safe & ethical community, we will NOT provide help for:
- ANY illegal activities.
- NSFW/Porn.
Requests for these topics may be ignored, not helped and result in moderation action.
- Be Polite & Patient: Our helpers are volunteers. You may ping the
Helpersrole once. - English Only: Please keep all conversations in English.
- Don't Ask To Ask.
Make sure to read help guidelines before start asking anything. First of all, what is your PC GPU? And did you follow any tutorial or guide before this? Because when you say "but I just set the program right bro", it doesn't refer to any issue.
This is the original, mainline version of RVC GUI. Not always recommended as your main RVC because this one was from 2023. Latest version of Applio RVC fork supports NVIDIA GeForce RTX 50 series GPU. 
If you could get W-Okada or any other AI program to "natively" work on Apple iPhone/iPad or even Android device, it would be a new and unlocked knowledge. If not, desktop computers (Windows, Linux) are still more preferred than the mobile ones.
Because both Apple iOS and Android devices have simplified audio system and unlike what in PCs, so the virtual audio programs like Virtual Audio Cable and VB-Cable are unlikely to work with such systems. While you could get other voice changer apps from App Store or Google Play Store that claim to change your microphone audio in real time, they won't be the same level as W-Okada.
What are your PC GPU and operating system? And which W-Okada version is this one?
-colab
Google Colab is a Cloud (Remote Good PC) Service. While the Free plan provides up to 12 hours of daily usage, the GPU is typically available for only about 4 hours each day on average.
by IA Hispano
Google Colab
by Hina
Google Colab
by Eddy
Google Colab
by Eddy
Google Colab
by Deiteris & Hina
Google Colab
by Shiro & Eddy
Google Colab
by Nick088
Google Colab
by Nick088
Google Colab
by Jarredou & Makidanye
Google Colab
hello, im trying to reroute audio from discord thoguh w-okada to my headhpones
i thought i could just rewire the cable backward but its protesting
and takes input from my mic instead
current setup
the normal vac didint work either
:(
im trying to pass audio from discord into the voice change and to my microphone
like im trying to change the voice of the people im listening to
on windows?
hey
excuse me
when a helper comes to this chat can you ming me
ping
@patent trellis
please explain what you need help with and someone can help you when they get the chance
!howtoask
- Check Docs & Guides: Your answer may already be in the AI Hub Docs or the https://discord.com/channels/1159260121998827560/1159513888199540817 channel.
- Search the https://discord.com/channels/1159260121998827560/1192011222023950368 : Look for existing posts that solve your issue. Do not invade someone else's post.
Tell your:
- Full GPU Name: (e.g.,
NVIDIA RTX 4060 8gb vram desktop) - Operating System: (e.g.,
Windows 11) - Detailed Description: What were you trying to do and what went wrong?
- Tutorial Used: Link to the guide you were following.
- Screenshot: A picture of the full error message.
To maintain a legal, safe & ethical community, we will NOT provide help for:
- ANY illegal activities.
- NSFW/Porn.
Requests for these topics may be ignored, not helped and result in moderation action.
- Be Polite & Patient: Our helpers are volunteers. You may ping the
Helpersrole once. - English Only: Please keep all conversations in English.
- Don't Ask To Ask.
ok
bro
so when i open the start up and opens command prompt then closes
@tame oracle
i need to know more, what is your GPU? what voice changer are you trying to use, did you follow a youtube tutorial?
yes the youtube tut
amd
im on school laptop
it worked last time
i deleted it for storage]
and i need it again
but what are the numbers after AMD?
let me check daddy

im looking it up, give me a minute
ok
So that's integrated graphics, you can't run any kind of AI on that
To run AI you need a dedicated graphics card
did you run it on CPU before?
and since you used a youtube tutorial its outdated anyway, if you want to run it on CPU i can't stop you but i'd suggest using a cloud option
wtf is cloud option
please be patient its not needed to ping me everytime
so you essentially get to use a remote PC that is more equipped for AI workloads like the voice changer, you just need a internet connection and if you use Kaggle a phone number to verify
are they free
yes they are free but you have limits, Kaggle has a 30 hours a week of free GPU time
can you help me set it up
https://docs.aihub.gg/realtime-voice-changer/cloud/tg-develops-w-okada-fork-kaggle/
there is a guide, but for any other questions yes i can
Last update: September 6, 2025
then you can use google colab but its has less free GPU time
Last update: September 6, 2025
here is a ming for your trouble
it wants me to use a code
and i have to have a hpone for that
unless you do it for me
wdym a code, are you using Kaggle or the Google colab link i gave you after you sai you don't have a phone number?
colab
Multi-factor Authentication
Use an authenticator app like 1Password, Google Authenticator, or Microsoft Authenticator to generate one-time passwords that are used as a second factor when you sign in to ngrok.
Enable or disable MFA at any time in the User Settings page.
Scan the QR code using your authenticator app
Or enter the code below into the authenticator app
KCT62Q6DAQTTW63YDXDAZI73ZKHCOM6F
Skip
Next
this is for ngrok
you should be able to skip Multi-factor auth
np
im on it
good
idk
i only had like 5 mins
i aint even have enough time to get my model in
im doing it again tho
i might go on my college account
ok yea, cuz it shouldn't be just 5 mins, and worst case google accounts are easy to make for alts
-colab
Google Colab is a Cloud (Remote Good PC) Service. While the Free plan provides up to 12 hours of daily usage, the GPU is typically available for only about 4 hours each day on average.
by IA Hispano
Google Colab
by Hina
Google Colab
by Eddy
Google Colab
by Eddy
Google Colab
by Deiteris & Hina
Google Colab
by Shiro & Eddy
Google Colab
by Nick088
Google Colab
by Nick088
Google Colab
by Jarredou & Makidanye
Google Colab
Anyone know why im getting this error message when opening the RVC Colab links to do the cells
Welcome to GitHub's home for real-time and historical data on system performance.
Does anyone have any reccomendations for making the chat gpt image generator generate more faithful representations of your face?
im trying to generate a profile picture for linkedin, like a professional headshot, and its definitley generating headshots, just of guys who look similar to me, I tried giving it a lot of pictures to pull from but its always just about as accurate
โWho is the best maker and designer of girls' voices in a language but an Arab?
What?
?
Hey guys I was wondering if anyone knows where i can get my hands on this tiktok voice. From some sites its called male-rubyy, others use it for the macha talking among us meme. it sounds like a funny flamboyant tts voice. I think it is also called ruby in the tiktok stuff.
this site has the voice under english(US) Male-Rubyy
if anyone has any idea let me know pls, I appreciate any advice
For this program (deiteris fork) + gaming is better the RTX 3060 12gb or the RTX 5060 8gb?
why would a 5060 have less gb than 3060
5060 tho will run it better
NVIDIA decided to have the base 5060 with 8gb of vram and the Ti variant has either 8 or 16 gb for whatever reason
that's quite strange
12 gb is better than 8 gb for modern gaming unless you stick on such light games like roblox
it very much is
that's what a friend told me
that the 3060 is trash despite its 12gb compared to the 5060
I have a 1660 super, should I continue using the deiteris fork of w-okada or switch to vonovox?
Vonovox will work, but usually works best with GeForce RTX 20 and up. Tg Develop W-Okada fork (b2377) is a continuation from Deiteris W-Okada fork.
The GeForce RTX 3060 also has the 8GB variant but the performance is pretty much similar to other RTX 3060 12GB variants. RTX 4060 only has 8GB, but a variant of RTX 4060 Ti has 16GB. The RTX 5060, despite its superior performance, only has 8GB.
There have been an earlier debate in here that concerns if 3060 12GB could be better than RTX 4060 or 5060 in a scenario where the VRAM size is prioritized over raw performance, although it depends on your use cases.
It's hard to pick one model maker who knows Arabic language because most of them speak English as one of their main communication, but you can make a free request for voice model of a famous celebrity who speaks Arabic in #1159289738314919936.
wdym "designer" 
how to input voice models
!howtoask
- Check Docs & Guides: Your answer may already be in the AI Hub Docs or the https://discord.com/channels/1159260121998827560/1159513888199540817 channel.
- Search the https://discord.com/channels/1159260121998827560/1192011222023950368 : Look for existing posts that solve your issue. Do not invade someone else's post.
Tell your:
- Full GPU Name: (e.g.,
NVIDIA RTX 4060 8gb vram desktop) - Operating System: (e.g.,
Windows 11) - Detailed Description: What were you trying to do and what went wrong?
- Tutorial Used: Link to the guide you were following.
- Screenshot: A picture of the full error message.
To maintain a legal, safe & ethical community, we will NOT provide help for:
- ANY illegal activities.
- NSFW/Porn.
Requests for these topics may be ignored, not helped and result in moderation action.
- Be Polite & Patient: Our helpers are volunteers. You may ping the
Helpersrole once. - English Only: Please keep all conversations in English.
- Don't Ask To Ask.
-rt
Guides for Programs that use RVC Models in Realtime for Calls/Games
A Realtime Voice Changer with similar performance to Wokada Deiteris Fork, with extra features, but supported only for Nvidia GPUs on Windows. and without cloud options GUIDE
A personal fork (modified version) of Wokada Deiteris Fork, it just adds some Quality of Life improvements to it like supporting Spin Embedder and Audio Effects. Don't expect too much about it since the creator made it originally as a personal project. GUIDE
Most suggested WebUI with the best general support for many platforms. GUIDE
For Windows Nvidia, Both Wokada Deiteris fork and Vonovox have similar performance & quality. Users should read the pros and cons for both and choose based on their differences, such as UI and Vonovox's paid effects.
Read Wokada Deiteris Fork Pros&Cons & Vonovox Pros&Cons
These options are not recommended for use.
Not suggested, older versions in youtube tuts are even way worse. GUIDE
The program is worse compared to the ones above, and much less updated. GUIDE
@viral mason help with importing voices to application
Yo so the one u downloaded from the yt tutorial is super outdated
What gpu do u have
a bad one bru nvidia rtx 4060
That's not bad at all
I've seen someone with a 730

U should try out Vonovox it's the current best realtime voice changer only works for Nvidia
Everything u need to know and download is in that first guide for Vonovox
U got any questions just ask me, if I don't answer I fell asleep
I'm not even supposed to be up rn I got work in the morning at 11 and it's 3 am
ill try not to bro i lwk have school tm andits 1 am but ty for the suggestion im downloading rn if ur cool w it ill lyk in the morning
I'm up for questions rn I don't mind
Oh I misread what I said my bad
Yeah I can try
Why isn't it working? I did everything correctly on AMD. Can you provide a photo of my settings? My PC, by the way:
RX570 graphics card
Intel Xeon E5 2650 v2 processor
Which specific program? W-Okada or RVC?
Your what is not working or something?
!howtoask
- Check Docs & Guides: Your answer may already be in the AI Hub Docs or the https://discord.com/channels/1159260121998827560/1159513888199540817 channel.
- Search the https://discord.com/channels/1159260121998827560/1192011222023950368 : Look for existing posts that solve your issue. Do not invade someone else's post.
Tell your:
- Full GPU Name: (e.g.,
NVIDIA RTX 4060 8gb vram desktop) - Operating System: (e.g.,
Windows 11) - Detailed Description: What were you trying to do and what went wrong?
- Tutorial Used: Link to the guide you were following.
- Screenshot: A picture of the full error message.
To maintain a legal, safe & ethical community, we will NOT provide help for:
- ANY illegal activities.
- NSFW/Porn.
Requests for these topics may be ignored, not helped and result in moderation action.
- Be Polite & Patient: Our helpers are volunteers. You may ping the
Helpersrole once. - English Only: Please keep all conversations in English.
- Don't Ask To Ask.
In RVC context, the index file contains the accent
My voice isn't working in the app, the microphone is fine, I don't know what to do. I've tried guides on YouTube.
Read help guidelines before start asking anything. First of all, W-Okada realtime voice changer or other RVC fork?
there are thousands of different ai apps
please elaborate

Sorry, yes, I mean W-Okada realtime voice changer, I have Wondows 10
did you come from a youtube/video tutorial about realtime voice changing? because those are old
you should also elaborate your pc gpu
Yes, I came from a video tutorial, my GPU is RX 550
all youtube/video tutorials are pretty outdated and use an over year old version of original wokada
delete it
if you have vb audio cable, uninstall it from windows app settings
Radeon RX 550 or RX 570?
sorryy rx 570
-realtime
Guides for Programs that use RVC Models in Realtime for Calls/Games
A Realtime Voice Changer with similar performance to Wokada Deiteris Fork, with extra features, but supported only for Nvidia GPUs on Windows. and without cloud options GUIDE
A personal fork (modified version) of Wokada Deiteris Fork, it just adds some Quality of Life improvements to it like supporting Spin Embedder and Audio Effects. Don't expect too much about it since the creator made it originally as a personal project. GUIDE
Most suggested WebUI with the best general support for many platforms. GUIDE
For Windows Nvidia, Both Wokada Deiteris fork and Vonovox have similar performance & quality. Users should read the pros and cons for both and choose based on their differences, such as UI and Vonovox's paid effects.
Read Wokada Deiteris Fork Pros&Cons & Vonovox Pros&Cons
These options are not recommended for use.
Not suggested, older versions in youtube tuts are even way worse. GUIDE
The program is worse compared to the ones above, and much less updated. GUIDE
read the wokada tg develop fork guide
don't expect it to work on intensive games ofc
Try Tg Develop W-Okada fork DirectML. https://docs.aihub.gg/realtime-voice-changer/local/tg-develops-w-okada-fork/ The program can at least work with AMD Radeon RX 570, although it can be slower than other 4-digit Radeon RX GPUs.
Last update: October 26, 2025
I'm going to use it for Discord
should work fine with the right settings then
okay
uhh idk but i switched to the one worm said and its lwk super good
<@&1159293204038955078> yooo guys how can i get the ai maker tag? i've already made a rvc model
<@&1159293140440723499>
yooo guys how can i get the ai maker tag? i've already made a rvc model
hii please wait for someone to answer your question in their own time rather than ping us all ^_^
Model maker role isn't even real trust
ok, sorry
no worries
do you know how can i make money with that skill?
Making ai models? I don't personally and u can't make any money here bc it's part of the rules but you technically can yes
As long as you know how to make good models
ohhh.
I'd say I make decent ones
have you ever made a penny with that?
Nope, I don't need money from what I do as I do it for fun
I have a real job anyways
ohh. can i ask what you doo if you don;t mind
I work at Walgreens as a cashier, it's not bad actually
It's my first job and pays decently
$15 an hour
great man,, i live in third world country so there is no any jobs or things like that
if i work like you they will pay me like 20$ a month in my country
We don't allow selling RVC models since a while
i don;t hvae access for that channel
No jobs at all?
there are jobs jbut they don't pay well
Oh
you have to select RVC enthusiast in the server guide
yea i know i'm just asking
anyone know why when I start my game the voice changer quits working
gets stuck on compiling jit model
yeah as soon as i closed the game it came back
Yo, im here, what's up?
can i share my screen
do i have to have colab open at all times
so it dont disconnect
cause if i change tabs it will lose connection
im uploading voice model rn
is there cerain settings in colab i need to enable
It shouldn't lose connection, maybe its a google setting, i know theres one that will offload tabs like that
ok
it says execution failed
Runtime disconnected
Your runtime has been disconnected due to executing code that is disallowed in our free of charge tier. Colab subsidizes millions of users and prioritizes interactive programming sessions while disallowing some types of usage as outlined in the FAQ. If you believe this message is in error, file an appeal. Please include any relevant context about your usage.
[SIO] rconnection failed Error: xhr poll error
look, im gonna be honest, this goes wayy over my head, i only use Colab like twice, have you had it running for a while maybe?
ERR_NGROK_3200
The endpoint donnell-sheaflike-hayley.ngrok-free.dev is offline.
no this my first time
the shit only runs for exactly 17,78 seconds
I really don't know that error, this is why we always say to use Kaggle cuz its newer and better, look im sorry but i don't know off the top of my head rn, i just got up
its all good

can someone help me with the voice settings? It seems like itโs not picking up correctly, it cuts out from time to time.
What does Voice Changer tell me in the terminal? Is this how it should be?
When I turn on the voice changer, the voice changer itself doesn't work.
What are u using it for hm?
maeasmr
What's that
How do I put pretrains here?
what old training software is this?
never seen it before
applio no ui
oh that's what it looks like on collab?
There you should enter the path to your custom pretrain (both G and D). If youโre using the original pretrain, leave it blank.
@viral mason help with vonovox audio routing to discord roblox etc
voice changer:
input: microphone
output: line 1
other programs:
input: line 1
output: headphones
what
ya but whats line 1
vb cable if u use that
How do i even install the voice mod program
I have been searching for a lot for the past 30 minutes
voice mod is a completely different software to wokada
I mean wokada
what gpu do u have
Anyone know where the uvr for the 50 series is
i s it like 4060 anything around that
Guides for Programs that use RVC Models in Realtime for Calls/Games
A Realtime Voice Changer with similar performance to Wokada Deiteris Fork, with extra features, but supported only for Nvidia GPUs on Windows. and without cloud options GUIDE
A personal fork (modified version) of Wokada Deiteris Fork, it just adds some Quality of Life improvements to it like supporting Spin Embedder and Audio Effects. Don't expect too much about it since the creator made it originally as a personal project. GUIDE
Most suggested WebUI with the best general support for many platforms. GUIDE
For Windows Nvidia, Both Wokada Deiteris fork and Vonovox have similar performance & quality. Users should read the pros and cons for both and choose based on their differences, such as UI and Vonovox's paid effects.
Read Wokada Deiteris Fork Pros&Cons & Vonovox Pros&Cons
These options are not recommended for use.
Not suggested, older versions in youtube tuts are even way worse. GUIDE
The program is worse compared to the ones above, and much less updated. GUIDE
the first guide has all the info u need
where is the uvr for the 50 series ?
@viral mason out of these which one to choose
i did all this and when i run start.bat it says press any key and nothing happens
run setup first then start
can someone gimme 1 on 1 help bruh i cant figure out vonovox and i cant find youtube tuts for it and i even asked cum chat gpt but he aint do nothing for me
-rt
Guides for Programs that use RVC Models in Realtime for Calls/Games
A Realtime Voice Changer with similar performance to Wokada Deiteris Fork, with extra features, but supported only for Nvidia GPUs on Windows. and without cloud options GUIDE
A personal fork (modified version) of Wokada Deiteris Fork, it just adds some Quality of Life improvements to it like supporting Spin Embedder and Audio Effects. Don't expect too much about it since the creator made it originally as a personal project. GUIDE
Most suggested WebUI with the best general support for many platforms. GUIDE
For Windows Nvidia, Both Wokada Deiteris fork and Vonovox have similar performance & quality. Users should read the pros and cons for both and choose based on their differences, such as UI and Vonovox's paid effects.
Read Wokada Deiteris Fork Pros&Cons & Vonovox Pros&Cons
These options are not recommended for use.
Not suggested, older versions in youtube tuts are even way worse. GUIDE
The program is worse compared to the ones above, and much less updated. GUIDE
What's your GPU?
nvidia 4060
ok great, first link then
cuz you didnt get what that guy said #โจโai-help message
Paid request and paid commission are not allowed in this server for now, only free ones are allowed. There might be some other places that would allow you to sell your models, but I'd rather not recommend doing it. 
do what in chat
What can I run?
I have a rtx 5070 with a Amd ryzen 7 9700x cpu
windowns 11

Because you asked for such too simple questions, I'm not quite sure what to answer. 
When I use weight, for "Kohane asuzawa' (Using for audition) sometimes the sh sounds crack
!howtoask
- Check Docs & Guides: Your answer may already be in the AI Hub Docs or the https://discord.com/channels/1159260121998827560/1159513888199540817 channel.
- Search the https://discord.com/channels/1159260121998827560/1192011222023950368 : Look for existing posts that solve your issue. Do not invade someone else's post.
Tell your:
- Full GPU Name: (e.g.,
NVIDIA RTX 4060 8gb vram desktop) - Operating System: (e.g.,
Windows 11) - Detailed Description: What were you trying to do and what went wrong?
- Tutorial Used: Link to the guide you were following.
- Screenshot: A picture of the full error message.
To maintain a legal, safe & ethical community, we will NOT provide help for:
- ANY illegal activities.
- NSFW/Porn.
Requests for these topics may be ignored, not helped and result in moderation action.
- Be Polite & Patient: Our helpers are volunteers. You may ping the
Helpersrole once. - English Only: Please keep all conversations in English.
- Don't Ask To Ask.
I want to know how be good at weight
I already knew
For voice models, there are in #1175430844685484042; certain exact voice models are also linked to Weights.com too.
I know but like
It cracks sometimes
So I want to know how to improve
So I can use it for audition
And can't be detectable
Are you talking about Weights website itself or a voice changer program? Because your statement is confusing to read.
I think the weight's website, like when you insert a voice
And the results comes good, but just a bit crack
So wanna improve
If it's a girl should I like raise my voice?
My saying is a rtx 5070 find for makeing voice modle?
By the way, locally RVC program like Applio RVC fork can be more reliable than Weights for AI cover, but the speed of conversion/inference depends on where you run the program. If you have male voice and the voice model is female, try raise pitch up to +12.
Okay
What about jammable?
It's quite hard to pick one best model from #1175430844685484042, but if one voice model was trained in low quality from start, you can't do much about it. If a voice model hasn't existed and you want them for your own, you can request one in #1159289738314919936.
I think weights is better then jammable
Any website that claims to use RVC voice model other than Weights, I don't know anything about that.
Yea the problem is that I don't really know which one is low quality (I kind of know due to what is sound and crack)
Ohh okay
This query just straight up more confusing. Did you do this as a troll/ragebait or some genuine question? 
I'm not sure about Roblox or VRchat, but this visual example could give you some ideas. 
i can hear myself in the browser but how do i make it work in apps
thank u bro i didnt know i needed a virtual cable and i also didnt know which inputs and outputs to use for applications, one thing i am wondering tho is how to hear urself? my mic and headphones are the same cus i got a headset so idk what to do about it
Paid version of Virtual Audio Cable (not to be confused with VB-Cable) gives you 256 VACs to use at once, but wow this list is just not only VB-Cable and the Voicemeeter.

idk what i got goin on fr
but do yk why the quality is so bad on discord? maybe its js settings but my mic alone aint too bad and when im only playing the audio from vonovox or whatever its called its super clear, idk if u can help with vonovox but if so pls lmk
how do i use the browser thing on apps? i click start and i just hear myself but how do i use it on apps
I'm more familar with W-Okada (and its fork versions), so anything about Vonovox would be a limited knowledge for me.
Deiteris and Tg Develop W-Okada fork versions are known to open your browser for their web UI. The "original" and outdated version of W-Okada opens its own program, though not always recommended to use it.
!howtoask
- Check Docs & Guides: Your answer may already be in the AI Hub Docs or the https://discord.com/channels/1159260121998827560/1159513888199540817 channel.
- Search the https://discord.com/channels/1159260121998827560/1192011222023950368 : Look for existing posts that solve your issue. Do not invade someone else's post.
Tell your:
- Full GPU Name: (e.g.,
NVIDIA RTX 4060 8gb vram desktop) - Operating System: (e.g.,
Windows 11) - Detailed Description: What were you trying to do and what went wrong?
- Tutorial Used: Link to the guide you were following.
- Screenshot: A picture of the full error message.
To maintain a legal, safe & ethical community, we will NOT provide help for:
- ANY illegal activities.
- NSFW/Porn.
Requests for these topics may be ignored, not helped and result in moderation action.
- Be Polite & Patient: Our helpers are volunteers. You may ping the
Helpersrole once. - English Only: Please keep all conversations in English.
- Don't Ask To Ask.
Make sure to read help guidelines before start asking anything back. 
windows 11
AMD Radeon RX 6550M
i downloaded the browser realtime voice changer client thing and i click start and when i talk i hear the voice cahnger. i dont know how to stop haering myself and use it in like a game like roblox
https://docs.aihub.gg/realtime-voice-changer/local/deiteris-w-okada-fork/#discord-
cant atach scresnhot
There has been a newer version of Deiteris W-Okada, though it developed by a different author; that one is Tg Develop W-Okada. https://docs.aihub.gg/realtime-voice-changer/local/tg-develops-w-okada-fork/ https://github.com/tg-develop/voice-changer/releases/download/b2377/voice-changer-windows-amd64-dml.zip
Last update: October 26, 2025
Many settings in Tg Develop W-Okada fork are pretty much similar to Deiteris W-Okada.
On Tg Develop W-Okada UI, this is the audio settings. The "monitor" is another output where you set this to your speakers/headphones to hear the program. To disable it, simply select to "No device detected" or "none".
How do I put pretrains there?
Like an alr existing pretrain
yall know a good e girl model that works with w okada's real time voice changer
im using w okada's voice changer it dosent seem to be working i have a laptop and using the laptop's mike is it cuz of that
the voice is really glitchy and not understandable
its super delayed and glitchy is it cuz of my bad laptop or some issue with the vb cabel
never waste your money on any sketchy apps that may be paywalled
You must navigate through the filebrowser of the colab that is on the left, if it does not appear, click on the folder icon and you will see it, it would only be right click on the existing file and click on copy path, that path you paste it in the cell and that's it, the colab will look for that path of the file and use it
Now that I realize, I think you meant downloading a pretrain
In the training part, you lower the final, you hit advanced settings
A custom pretrained checkbox will appear, you will click on it and a box will appear to upload the files
Or you can also create a cell to download them
I guess I should update the notebook to make it easier to download pretraineds
But what I'll do later

I can't help with the E-girl voice model, but I can focus on some W-Okada versions and their settings.
!howtoask
- Check Docs & Guides: Your answer may already be in the AI Hub Docs or the https://discord.com/channels/1159260121998827560/1159513888199540817 channel.
- Search the https://discord.com/channels/1159260121998827560/1192011222023950368 : Look for existing posts that solve your issue. Do not invade someone else's post.
Tell your:
- Full GPU Name: (e.g.,
NVIDIA RTX 4060 8gb vram desktop) - Operating System: (e.g.,
Windows 11) - Detailed Description: What were you trying to do and what went wrong?
- Tutorial Used: Link to the guide you were following.
- Screenshot: A picture of the full error message.
To maintain a legal, safe & ethical community, we will NOT provide help for:
- ANY illegal activities.
- NSFW/Porn.
Requests for these topics may be ignored, not helped and result in moderation action.
- Be Polite & Patient: Our helpers are volunteers. You may ping the
Helpersrole once. - English Only: Please keep all conversations in English.
- Don't Ask To Ask.
lol it was to troll my friends
can you help me solve the issue im facing
i got the latest version and i dont know what settings should i put could u help
its not working
i have a windows 11 laptop amd ryzen 5 5500U
that graphics card says 2 gb
8 gb ram
i downloaded w okada voice changer and i downloaded a model from here and when i try to used it in discord sound test the audio was very delayed and glitchy it was not working at all
is it because i have the settings wrong or because i have no mic and using the laptop's mic or is it a problem with my vb cable or its cuz my laptop ram is low
i have a windows 11 laptop amd ryzen 5 5500U
that graphics card says 2 gb
8 gb ram
or did i make an error while downloading
i used a video for tutorial i can send it if someone wanna help me
You just repeated about your laptop operating system and its GPU for 2 times, then you went on with very long messages combined almost of text wall. By the way, what I could understand about your query is that you have a laptop with Windows 11 with an AMD Ryzen CPU, the GPU name is not specified, confusing RAM and VRAM sizes, and that you might have follow a tutorial video from YouTube before.
im sorry
wait 1 sec
modern laptops with 8 gb ram should go into dumpster fire
16 gb should be the standard nowadays
im gonna get it upgraded to 16 soon
why does it even matter for a voice changer
AMD Radeon(TM) Graphics is an integrated GPU typically found in AMD Ryzen systems, contrast to dedicated GPU like AMD Radeon RX which is more powerful than the integrated one. Any AI program like W-Okada won't gonna work with that integrated GPU well, and attempting to get the program to work with an integrated GPU would only perform the fraction of your PC CPU. The VRAM size of any integrated GPU is typically shared with your main PC RAM, which is what you see there.
8GB RAM, while above of Windows 11's system requirements, won't be very ideal for high-performance gaming or when you run many programs/tasks at the time. 16GB and above is generally preferred over 8GB.
So, the only way to run W-Okada with more performance is to opt for online service like Kaggle instead of running locally. 
What does this mean?
so u basically mean i cant use it?
there has to be something i can do
will it work if i get my ram to 16 gb
its 8 gb rn
Even when you put another 8GB stick to your laptop, it won't do anything much about W-Okada.

so what do i do
do i need a nasa pc
to run it
I've already suggest one to you earlier.
i only have this laptop can i do something with it
Running rvc on laptop is possible, but only if you want to do inference, if you want to try Realtime, the best thing to do is to try alternatives in the cloud
i wanted to try real time on discord
i already downloaded models and w okada and the vb cabel
.
spent 3 hours lookin is there something i can do
whats kaggle
Follow this guide. https://docs.aihub.gg/realtime-voice-changer/cloud/tg-develops-w-okada-fork-kaggle/
Last update: September 6, 2025
so can i run it real time on discord if get 16 gb?
As much as I confirm, there's nothing you can do about getting W-Okada to work like that. Any dispute on why running W-Okada with only** CPU** and that 16GB RAM would be better and very ideal than the one with a powerful dedicated GPU? 
oh
so if i do all that with kaggle will it work
it looks very complicated

To request a voice model of a Pokemon character, ask for one in #1159289738314919936.
Everything is complicated at the beginning, but then it becomes easy
why do i need so much for a voice changer i thought it would be simple ๐ญ
if i follow this whole guide and do that will it work
and what does it do
open the app on some online cloud?
i already downloaded vb audio cabale and the w okada voice changer from git hub do i delte everything now
If I don't make visual examples of getting W-Okada to run from Kaggle, you wouldn't know how this is supposed to work. 
then give 
Just remove w-okada, you will need the V cable
but it says to download some other lite v cable in the guide
is kaggle an app or something
im confused seeing the programming thing
and how do i use it
Ah, then install it, I thought you meant that same
Hello guys i need help with something. I'm trying to clone a voice for sometime but since I have potato pc i couldn't do it. also I'm kinda afraid my gpu might caught on fire :). is there a way i could do in cloud?? i tried some it failed
It is simply a page that lends you a machine for 30 hours with two t4 graphics
i cant use it more than 30 hours?
not permanent?
No, they are on their terms, but don't worry, they reset that counter every week
so 30 hours every week
so will it open the w okada app for me?
will it look like the app
i can upload models and stuff
There's more you should know, but when you ask too many questions, I'm not quite sure which to answer, because I'm more of focusing on settings.
sorry im not used to talking like that ๐
just answer these
Don't repeat your same query for many times, and this #โจโai-help channel won't be where you request someone to add a voice model in #1175430844685484042. Hope this clears up. ๐
Cool.

Can anyone help me out ?
-rvc
See Applio RVC.
thanks
is there something i can do with my settings to make it work (real time)
it seemed to but working but voice is delayed and buggy
barely
also is voice.ai good? can i use it instead for real time in discord
It's not suggested
it's just making you pay for using RVC without any really benefits
