#✨│ai-help
1 messages · Page 276 of 1
it's an over year old version of original wokada
delete everything
dont trust video tutorials
Oh, where can I download the new one?
-realtime
Guides for Programs that use RVC Models in Realtime for Calls/Games
Most suggested WebUI with the best general support for many platforms. GUIDE
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
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 either wokada deiteris fork or vonovox
original wokada yes, wokada deiteris fork and vonovox no, you can read their guides
I downloaded wokada deiteris, how can I run it?
Nvidia GeForce GTX 1050 Ti
i3-9100
Windows 11
e girl trolling
https://www.youtube.com/watch?v=SxdnGxicJOg
bro still insist to use cloud services rather than own 4060
even the cloud cpu is actually slower than average pcs
E girl trolling is catfishing, which is illegal. You have been warned both verbally and via sapphire and continuing to ask will lead to further actions possibly like a ban
also that video is extremely outdated, u can delete everything and forget to e girl troll people
I managed to run it. Are there any specific settings to make it sound good?
is trolliing with any voice illegal?
yea but gpu is what im lookin at
can't train 160mins data in rtx 4060 Y_Y
@low shard how many silent training files
colab & kaggle are actually slower than ur 4060
no
my 4060 fails at pitch extraction
assuming it passess preprocess without bsod
try set cpu cores to 1
🥹 still would get limited by ram
as I have 16gb
yea last time I tried 20 minutes data set it went to 15.7GB
and kinda almost crashed the whole system

automatic slicing with many files and lots of threads would do that
it shouldnt go out of memory if you use Simple slicing method in preprocess
ohhh i used mangio then if i remember
as in causing error?
also can I put this to 0? @knotty moth
i'm not sure what to do with that
dont touch it
idk if it's causing hissing noise in mute parts
💀
ehh no increase decrease?
could you tell what does it do?
what do i do if the sound comes out choppy?
how many epochs you are at rn
perhaps you didnt do denoise & noise gate enough
Whats that
ahh i didn't preprocess my data
preprocessing and removing noise makes the output audio
sound robotic
after interference
like even tiny bit of noise reduction brings out that issue (I've tested within multiple checkpoints from 20-464 epochs for 1 hour training set)

lol idk where the epoch thing is
what even is that
ai voice changer
please elaborate:
- your GPU & PC spec and the operating system used
- what purpose do you want to do for?
- what kind of voice models do you want to use?
- what tutorial link are you using/referring to?
- show the screenshot of the program you're using, esp its version
what do i set my output and input as
im on 4080 and im trying to roleplay on fivem but the sound comes out choppy
im on windows 11
what kind of model you're using?
E-Girl | High Quality Female Voice | 350 Epochs | rvmpe | by zoka
please elaborate:
- what purpose do you want to do for?
- what kind of voice models do you want to use?
- what tutorial link are you using/referring to?
- which version of the program you're using
what was I supposed to say lol
didn't you get warned or something gang
when?
or was it another guy
I never got anything
idk there were new peeps here asking for egirl trolls
💀
im sorry but I'd assume you're doing e-girl trolling with that model
I'm not?
I need to sound like a girl because thats my character on fivem
thats what the admin said
also man when did your gpu change from 4060ti to 4080
💀
why did i get warned?
you are gonna get banned at this rate
🤗 cuz e girl troll is catfishing
and deceiving
im not e girl trolling
and it's kinda illegal in some countries i think
are you going to sound like a girl
for singing is deiteris or vonobox better? or doesn't matter?
and do you want to do that in public lobbies?
or private lobbies with friends or something
no its only on 1 server and the admin knows
still it's kinda dark spot i think

people troll others

and it's illegal it seems
everyone is gonna know im using a voice changer
cough cough
there are some models eh far superior
so it's dangerous
💀
what even is this server
and i would be like-- holy shit how good it is and literally people can fall
that model is from this server?
ehh is he even here?
So the server doesnt follow its own rules?
anyone can train epochs gang soo technically it's hard to ban the person unless he/she does something weird with it
its like asking to arrest the knife maker when there is a murder

Pretty sure it's the same
wym by that
catfishing is prohibited and tends to be using like anonymous e-girl models that dont have proof of consent with the voice owner
ok tyvm
tisss 
gpu rtx 4060 cpu i512400f
windows 11
anime char with friends
voice-changer-windows-nvidia-b2332
I'm not gonna catfish?
@proud dawn you can technically maybe record your own voice
latest
I don't even know how
you can use rvc and get help, for those good stuff
it kind of seems confusing to start
Im literally asking for help
but trust really easy with proper help
anything related to e-girl isn't going to get help bro
ehh
gpu rtx 4060 cpu i512400f
windows 11
anime char with friends
voice-changer-windows-nvidia-b2332
check here in discord
Yeah I got it. I'm gonna figure everything out by myself like I have so far
that's better, technically you can do whatever you want outside this server
yea your input device needs to changee
are you using virtual audio cable?
you need help setting it up?
Gonna get banned any moment now 🤣
unless you ask for e-girl stuff you won't
what should it be?
wait lemme show mine
virtual cable should be input in discord or any external game/applications
I have two questions.
-
Does enabling GPU hardware acceleration interfere with RVC voice changers? For example, causing resolution or quality issues?
-
What’s the best way to train voices using RVC on a 5070 Ti? I used to try the older “RvcwebUi” setup, but it only supported 40-series cards, so it didn’t work for me.
first change the output to virtual cable in
oh ok
website or discord?
and yup the input device must be the virtual cable out
in this image change output to virtual cable in
this fine?
can you do a help
what
then
now what it shows in output also send full screen shot
recording?
great
also you don't have to set line 1 as default device
if you are going to talk in discord
butt ahh
alright leave it like that
i set it as microphone
alright that works as well
ensures you talk via mic only in website
i think you are pretty much ready
this is good
or website
the sound comes via the website
so i gotta keep the website on while talking?
okay try this don't change discord settings leave input as Virtual Line
you need to talk into website
like ahhh you need to speak in the website
so the website outputs it to discord
so you don't talk in discord
you leave mic on in discord
and you go to the website
and speak in the website
ye i get it
no voice coming
on my alt
nor from the website
even tho echo is on
@oak edge 😭
gang what
im not really expert in the website
but try to switch your mic
in the audio
here
switch it to normal mic
leave the discord to line
don't change discord
i did that already
still same?
yes
damn
i never used that program you are running

yea ask when @simple ore or @knotty moth or @low shard is here ig
Does enabling GPU hardware acceleration interfere with RVC voice changers? for example, causing resolution or quality issues?
- What’s the best way to train voices using RVC on a 5070 Ti? I used to try the older “WebUi” setup, but it only supported 40-series cards, so it didn’t work for me.
generally I'd recommend turning hw acc off in browser and discord
latest Applio supports 5000 series
@simple ore hey uh
it doesnt work in discord
gpu rtx 4060 cpu i512400f
windows 11
anime char with friends
voice-changer-windows-nvidia-b2332
@knotty moth sry for ping
pick
what do i pick
either
it doesnt give me option to pick when i start the voice changer
i can help rq in https://discord.com/channels/1159260121998827560/1410290737094066258 btw
bet
@simple ore I'm trying to use TTS in Applio (idk is it Edge TTS ?) And it is throwing and error saying..
update applio
i see. its now on 3.3.1 i was using 3.2.9
please add it to #📰│dev-updates
3 3 1 should work
Is there any changes in new version, if you please add it to #📰│dev-updates so that everyone can know about it
@simple ore I updated the applio and it worked but only for one time. Now it's throwing same error again
Also it takes too much time to open than pervious version.
how big is the tts text?
2742 characters
I tried with 300 characters but it doesn't worked
Even with 30 characters it doesn't work
It only worked once. The movement I downloaded and extracted the New version and run it for first time, then it worked, but then I wanted to change the pitch but it throw the same error. I restarted my pc, but same error. Now I don't know what to do.
works fine for me
And this happened
But why not mine?
vpn?
No
Ooh
Tbh I just turned off my PC and I saw your message then I turned it on again so I decided to try one more time, it's strange, but it is working well now, Idk how. Please explain
Does it due to internet or something ?
are you in some weird country where western stuff is banned?
-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
I’m using WOkada Deiteris Fork, VAC Lite, and Voicemod. For some reason I can’t figure out the inputs and outputs. It seems like no matter what I do, the AI voice comes through repeatedly echoing until it is completely distorted.
Okay someone hook me up with the best ai assistants
Does someone know what pretrained base model is used by weights.gg for the rvc finetuning offered there? This is such a vast field, full of possibilities and methods, I was quite overwhelmed, coming from only knowing the training process on weights.gg - upload audio, click train.... I wonder why they basically offer absolute no customization and let users tinker with the settings or choose a different pretrain... and they don't even tell us anything about the settings they use at all, what's going on behind the scenes.
don't use weights to train
it's really bad
i need help if anyone is able to help i have nivdia gtx 1070 i think and i use windows
i try to use my voice changer through discord settings
i cant hear anything
Guys is there a chance to train RVC models locally with an AMD GPU?
@simple ore
I know there's an AMD version of Okada
But I'm talking about model training and inference
Maybe Applio for AMD?
if one of yall give me perms
i can show my settings
DirectML/ROCm
but i cant right now since i dont got perms
but my input is my mircophone and my output is the virutal audio cable line 1
and then discord its also virutal audio cable line one and the output is my headphone
how to open a ticket?
help\
depends on gpu
tickets are only for moderation, not help, do u need help?
Yes installing voivechanger
This is a General AI Server, AI has many fields, so we can't know your issue with little info
Please Elaborate:
- your PC GPU (Such as Nvidia RTX 3060, AMD RX 9070 XT..)
- your operating system (Like Windows 10, Windows 11, Linux, MacOS 26..)
- what you want to do? There isn't a program that does everything, there's a program for each thing:
- AI Covers
- Train RVC Models
- E girl trolling
- TTS
- Roleplay in VC
- Roleplay in Games
- etc
- what tutorial link are you using
- a screenshot of the program
I can help you if you elaborate, "voice changer" is too vague:
- your PC GPU (Such as Nvidia RTX 3060, AMD RX 9070 XT..)
- your operating system (Like Windows 10, Windows 11, Linux, MacOS 26..)
- what you want to do? There isn't a program that does everything, there's a program for each thing:
- AI Covers
- Train RVC Models
- E girl trolling
- TTS
- Roleplay in VC
- Roleplay in Games
- etc
- what tutorial link are you using
- a screenshot of the program
@bold steeple be sure to elaborate everything, this is a general ai server, and voice changer can mean over than 3 different programs
I am new to this and just want to have a realistic girl voice for an GTA RP server
you have to elaborate for me to help you, there's too many different programs and versions depending on the info i asked, there isn't a single program that does everything
with realisitic e girl voice, did u mean like e girl troll in a gta server, right?
Yes, a girl voice that sounds realistic
E girl trolling is catfishing, which is illegal. You have been warned both verbally and via sapphire and continuing to ask will lead to further actions possibly like a ban
Not sure which model you're talking about, but Codename's fork is **experimental **and really not suggested especially to people who aren't developers, as pointed out before in previous cases by other people like Lyery & Noobies: #🔥│model-maker-chat message #🔥│model-maker-chat message
if it has some specific vocoder or other setting that requires to be used in his fork, then it can't be used in wokada deiteris fork (which is what you call mmvc), it might be better to link the model or just try another one
that exists both for windows and linux btw
wdym with best ai assistants? like gemini on your android phone?
There's no need to use voicemod too, u can show a screenshot btw
is it possible to use CUDA, Okada with AMD GPU/CPU
you dont need to use CUDA, cuda is specific for nvidia, there's a specific version for wokada for amd gpus, and also CPU isn't that good, it would be better to first elaborate what's ur pc to check if it's good enough tho:
- your PC GPU (Such as Nvidia RTX 3060, AMD RX 9070 XT..)
- your operating system (Like Windows 10, Windows 11, Linux, MacOS 26..)
- what you want to do? There isn't a program that does everything, there's a program for each thing:
- AI Covers
- Train RVC Models
- E girl trolling
- TTS
- Roleplay in VC
- Roleplay in Games
- etc
- what tutorial link are you using
- a screenshot of the program
AMD 79 Series
Win11
Discord, Game Input
No Tutorial
Okada (Cannot send images)
My issue is opening the start https file in okada
I have python and pytorch downloaded but I cannot download cuda and it opens the https as a notepad file
!give-media-perms 1h @pallid blaze
so, are you trying to do like ai covers, e girl trolling, roleplay in games or roleplay in VC?
I am so stupid
because it depends on that
So
start http is from old original wokada, dont use it
I saw it opening as text, didnt realize it was command and I had to WAIT
yea you got the old original wokada which isnt suggested since like a year
What should I replace it with?
@pallid blaze there's newer programs, but it depends on your use case
there isn't a program that does everything
Just like
Casual conversation
Not really egirl but not really rp either
so like realtime voice conversion in games or vc?
Yes
also wdym with amd 79 series?
i can't find any gpus like that
at max, CPUs
I believe I have a 7900 XT
or 7090
Im not sure
the gpu is crucial,
You can check your pc gpu on Windows via:
ctrl+shift+esc (task manager) -> Performance tab -> GPU
AMD
Roger
-realtime
Guides for Programs that use RVC Models in Realtime for Calls/Games
Most suggested WebUI with the best general support for many platforms. GUIDE
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
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
Not installed yet
get wokada deiteris fork
Is it possible I could stream and have you walk me through this
💔
This the file?
Could you link that? Restarting pc to fix 86kb/s
Last update: August 14, 2025
This one is so much faster omg 😭
because you were using an outdated asf version lol
Hi everyone! I’m currently exploring AI anime lip sync solutions and have already started building my own in React using WhisperX with custom-made visemes. I was wondering if this is the right place to discuss projects like this, or if you’d recommend another community. Thanks!
Rerunning the file rn
@low shard Sorry if youre busy but its failing the same ones
i roleplay in vc i have nividia gtx 1070 im not using any tutorial link
and i came to you for the same problem last time
i tried the guide but its so vague im not a pro at this i dont know how to set it up i only know how to install
5 hour duration for 32-bit 48 khz stereo WAV format?
next time the duration is what you'd need to provide the info so no such calculation would be needed
select all the audio files then properties
I can't find extra in the collab itself
Also, how does one set up a dataset
Sorry, I'm new
I'm using Applio Colab
Alllllright.. Just uploading the voices. I'll get back to you
I'll check it out!
you can also consider the kaggle notebook as another option 
Last update: August 7, 2025
It says to run the extra cell after uploading my dataset to the cloud
Does the extra cell appear AFTER I upload my dataset?
.
Mine is just general question, I'm currently using vonovox and it's working wonders for me, for certain games like Rivals and Peak, it cuts out almost every sentence. Would I have to upgrade my PC, so it would basically have more power?
I'm not sure if that was the correct term...
I would like to use Voicemod so that I can add additional effects, filter out background noise, and easily switch to and monitor my normal voice.
If it’s echoing into Voicemod, it will echo anywhere else, so it doesn’t change much problem.
Planning to get an RX 9060 XT 16GB
I could show you a way to set it up but you'll need a couple more things, all free of course
Could put even cooler fx on it that voice mod could only dream of
I can't help rn tho as I gotta get some rest for my interview tomorrow
dose anyone know what to do i tried running the MMVCServerSIO and it said i dont have permision then it dissapeared
Any help would be much appreciated. I’ve just used Voicemod for a very long time and it includes all of my added effects and soundboards. I used to use WOkada with Voicemod a while back just fine but can’t seem to remember the correct inputs/outputs. Thanks! Good luck on your interview tomorrow.
Ty! You can add me on here and I can help in dms once I'm free^^
You’re too kind. Take all the time you need! 
My specs are Ryzen 7 3700x, 16 gigs of ram, and 2070 super. I just bought more ram today.
Does anyone know how I can use the new KLM6.1 pretrained model utilizing the new SPIN embedder? Do I use mainline RVC, Fork?
Please tell me, if I upload a file via MMVCServerSIO, apply a voice model to it, how can I download the final result as a WAV file? It seems that this cannot be done in a standard way, but is there anything that can be done?
does okada support SPIN?
@sacred summit what relaxed girl
yeah no w-okada supports contentvec it doesn't support spin yet
and i already told u that already 😭
would you say spin is better?
both of them are good
so how do i use it
BRO
IT DOESN'T SUPPORT SPIN
u can't use the model cuz its a different embedder
Using my CPU integrated graphics has less latency and better quality than my GPU even though its a 7900 XT?
how do I fix
yup...
the deteris fork
amd
did u use cpu
No
does it say this?
screenshot the whole ui
I have 3 options
CPU (Not used)
AMD Graphics (CPU Integrated, works best)
7900 XT GPU (Works horribly)
let me ss
show a screenshot of the entire ui
it says direct ml p - p
are you using it while playing a game?
close everything in background
play in 1080/720p
lowest graphics ever
also change crepe full onnx to fcpe onnx
60/30 fps cap
f0: rmvpe onnx or fcpe (rmvpe is best usually, fcpe is a bit worse but is lightweight)
extra: 1
on wokada deiteris fork, you can **optionally **use more advanced settings for benefits:
- Advanced Settings -> Force FP32 mode: on (THIS IS OFF BY DEFAULT! Turning this on improves stability. Increases VRAM usage by 200 MB)
- Advanced Settings -> Crossfade Lenght: Controls how smoothly the AI stitches different processed parts "chunks" of your voice back together. 0.1 for fastest voice, 0.15 for improved quality but increases delay by ~50 ms
- Reduce the delay on Windows via the Wasapi / Asio Guide
if you get a triangle next to ur gpu, always check it
wind energy
wtf
that gave me 146 ms
insane
\windenergy
huh?
need any other help?
how to use ai image in discoard
There's no discord bot for that in the server, but you can use https://voyages..weights.com/
I dont think so thank you
You're welcome 🤗
MMVCServerSIO Is Wokada Deiteris Fork, which is meant for realtime applications like Discord, not pre-recorded audios, are you sure you want both or just pre-recorded audios?
Hello I was using Google colab to try to install the voice changer but i keep getting this error message and i cant run it: "ERROR: Could not find a version that satisfies the requirement faiss-gpu (from versions: none)
ERROR: No matching distribution found for faiss-gpu"
does anyone have an idea on how to fix it?
Full GPU Name: Phyton 3 T4 GPU
Operating System: Windows 10
Detailed Description of the Problem: Attempting to run voice changer on Google colab, error while "Clone repository and install dependencies". The error: "ERROR: Could not find a version that satisfies the requirement faiss-gpu (from versions: none)"
ERROR: No matching distribution found for faiss-gpu"*
Tutorial Used (if any): https://www.youtube.com/watch?v=0uyGj7Fel58&t=173s
Screenshot of the Error (if any): https://imgur.com/mE3A5dk & https://imgur.com/a/Fh6wwcQ
that is pretty outdated
dont use video tutorials for ai realtime voice changers
also, colab is on cloud
Hmmm
did you check if your pc gpu is good enough to do it locally?
😭
XDDD
there's newer versions but it depends, you're trying to do ai covers, e girl trolling, roleplay in vc or in games?
asking because too many people get the wrong program since they confuse thinking a program does everything at once
valorant trolling mostly
valorant e girl trolling?
more like if i can find the certain voice of a agent
i wanna use it
to sound like them
yk?
oh so just roleplay of a valorant agent, right? not trying to trick people you're an e girl right?
yep
great then!
About Cloud, there are different services:
- Kaggles (30 hours weekly of better GPUs, T4x2 & P100, harder to use, requires an account and a phone number, doesn't allow a Web User Interface for free it usually doesn't get detected but if it does you could get in trouble):
- W-Okada's Deiteris' Fork Voice Changer Kaggle (the most free gpu hours)
- Lightning.AI (75 hours monthly of free T4 gpu, harder to use, requires an account and a phone number, allows web user interfaces) :
- W-Okada's Deiteris' Fork Voice Changer Lightning.AI (the safest for free)
- Google Colabs (4 hours daily of free T4 gpu, easy to use, require only a google account) :
- W-Okada's Deiteris' Fork Voice Changer Google Colab (currently works only on google colab PAID tier)
there is a lot of new stuff interesting
tell me actually whats the minimum gpu required to run it locally
for wokada deiteris fork, a gtx 900
but an rtx 20 series or later is recommended, especially for games
don't expect it to run on a 20usd cpu ofc 😭
I'm not sure but do you intend to "roleplay" in valorant while having the peeps consent and know that you're doing so?
but its mostly gpu right?
I see now what your concern is, no dont worry i dont take part in any bad stuff like that XD
do u play valorant?
Has anyone really dove deep into N8N for building workflows? If so how is it?
Really considering trying to make some and eventually sell them to a niche business
what kind of voice model do you want to use?
Well if you know valorant, Pheonix or Yoru, my mains
the game character right?
yeah
everyone knows without having to play the game 
I actually don't know those characters
I never played valorant nor watched it 
GPUs are crucial for AI, you could technically run it on good CPUs, but it wont be that good
yeah thats the point but my question is if my cpu is trash and my gpu is decent
would it run
it would run since it runs only on either GPU or CPU, not both, but ud kinda bottleneck your pc 
it's always better to have both decent/good parts ofc
as long it's not too ancient, even intel 10300F is still not bad when paired with a decent GPU
what GPU btw?
idk how the performance is on that
but i hope u wont do anything else ai related
bc amd sucks for AI support
also ngl 4gb vram limits it
It is a mid gpu but more than enough for valo and overwatch
And those basic games
That's why am buying it
Also I need a new monitor mine is only 60hz
AMD Radeon RX 6400
RX 6400 is a little better than iGPU
when i m running rvc it tells me ModuleNotFoundError: No module named 'tkinter'
what to do
Hello 
There's many different RVC versions,
Please Elaborate:
- your PC GPU (Such as Nvidia RTX 3060, AMD RX 9070 XT..)
- your operating system (Like Windows 10, Windows 11, Linux, MacOS 26..)
- what you want to do? There isn't a program that does everything, there's a program for each thing:
- AI Covers
- Train RVC Models
- TTS
- Roleplay in VC
- Roleplay in Games
- etc
- what tutorial link are you using
- a screenshot of the program
ihave an error when try to open voice changer (
[VCClient] Access http://127.0.0.1:18888/
[VCClient] wait web server...0 http://127.0.0.1:18888/
[Voice Changer] generate new embedder. (no embedder)
[Voice Changer] use torch contentvec [ONNXRuntimeError] : 7 : INVALID_PROTOBUF : Load model from pretrain/content_vec_500.onnx failed:Protobuf parsing failed.
[VCClient] wait web server...10 http://127.0.0.1:18888/
[VCClient] wait web server...20 http://127.0.0.1:18888/
[VCClient] wait web server...30 http://127.0.0.1:18888/
[VCClient] wait web server...40 http://127.0.0.1:18888/
[VCClient] wait web server...50 http://127.0.0.1:18888/
[VCClient] wait web server...60 http://127.0.0.1:18888/
[VCClient] wait web server...70 http://127.0.0.1:18888/
[VCClient] wait web server...80 http://127.0.0.1:18888/
[VCClient] wait web server...90 http://127.0.0.1:18888/
[VCClient] wait web server...100 http://127.0.0.1:18888/
[VCClient] wait web server...110 http://127.0.0.1:18888/
[VCClient] wait web server...120 http://127.0.0.1:18888/
[VCClient] wait web server...130 http://127.0.0.1:18888/
[VCClient] wait web server...140 http://127.0.0.1:18888/
[VCClient] wait web server...150 http://127.0.0.1:18888/
[VCClient] wait web server...160 http://127.0.0.1:18888/
[VCClient] wait web server...170 http://127.0.0.1:18888/
[VCClient] wait web server...180 http://127.0.0.1:18888/
[VCClient] wait web server...190 http://127.0.0.1:18888/
they say that on cmd
Just only pre-recorded!
then you can delete what you got
please tell me your pc gpu and operating system so i can give you the right program for pre-recorded audio speech to speech voice conversion :)
Best solution to prevent okada from picking up bg noise? (pc audio being picked up, dogs barking etc)
i'm guessing you're using wokada deiteris fork b2332 since i vaguely remember we talked before, use echo and sup1
Can anyone help me with installing the voice changer program?
me to ?? because i installed it but not starting when i clicled on it
Does anyone know how I can use the new KLM 6.1 pretrained model utilizing the new SPIN embedder?
Do I use mainline RVC, Fork?
i9, rtx3090, 63gb ram.
you use Applio
but the posted model is experimental, I dont think it was anywhere close to done
Hello :D
Please Elaborate:
- your PC GPU (Such as Nvidia RTX 3060, AMD RX 9070 XT..)
- your operating system (Like Windows 10, Windows 11, Linux, MacOS 26..)
- what you want to do? There isn't a program that does everything, there's a program for each thing:
- AI Covers
- Train RVC Models
- E girl trolling
- TTS
- Roleplay in VC
- Roleplay in Games
- etc
- what tutorial link are you using
- a screenshot of the program
Hello!
Please Elaborate:
- your PC GPU (Such as Nvidia RTX 3060, AMD RX 9070 XT..)
- your operating system (Like Windows 10, Windows 11, Linux, MacOS 26..)
- what you want to do? There isn't a program that does everything, there's a program for each thing:
- AI Covers
- Train RVC Models
- E girl trolling
- TTS
- Roleplay in VC
- Roleplay in Games
- etc
- what tutorial link are you using
- a screenshot of the program
From your experience, which KLM versions would you recommend for female singing?
can sb help me, i got 5070ti and 7 9800x3d, but w-okada still lagging while i use it as real time vc while playing games
it works fine if game is opened in a tray, but when i switch to game it starts lagging
in graphics settings i alr set priority to high, starting it with an admin
hey is there a possibility for me to make my custom AI model, and if there was. How do I start, and what would I need?
Hello ! Try pip install tkinter
-rt
Guides for Programs that use RVC Models in Realtime for Calls/Games
Most suggested WebUI with the best general support for many platforms. GUIDE
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
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 got you
I have a whole video on how to do it
it shows how to make one but not how to make the audio you use to make the model off
I should probably update this
still cant fix it
What type of AI Model? what's ur pc gpu and OS?
cloud shouldn't be his first option tho 
You're right, but it's the easiest and it's completely free
well a model that would automstically analyse football games like head to head matches between two teams and give best automatized betting advice on what to bet basically
something like this
https://www.sports-ai.dev/predictions

yessir gotta stay locked in
Will there be voices for low-end PCs, or am I screwed?
gamble a bit more lil bro
How do I get W-okado software? it keeps taking me to the website
do u use nvidia, amd, or intel
I got intel b580
Guides for Programs that use RVC Models in Realtime for Calls/Games
Most suggested WebUI with the best general support for many platforms. GUIDE
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
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
click the guide all u need is vac lite, and the download for the vc is in the guide as well
make sure u download the right one :3
if you need the direct link, it goes here
i could use some help with it too
I can help in the morning I gotta get some rest
friend me if you like or just ping me here in a few hours ^^
I'm washing my face off rn wsp
doesn't kaggle have backup
Y_Y I spent 13 hours yesterday in kaggle
training stuff
Mhm
and today when I log in the output directory is fresh
Did you set the variables thing to variables and files
i had variables and files on in persistence
O
Uhhhh
So that happens when it gets lazy and screws you over for no reason
and I'm gonna hit my quota i think Y_Y
WHAT THE FUCK
That's happened to me before there's literally nothing you can do about it
Btw just delete your account and remake with a different email
Ez fix
The nice 2 hours that gets you nowhere unless you pay 💞
and my drive auto backup
i'll pay when I get graduated as software engineer I hope

I'll never outright pay for ai, they can take my electricity bill or whatever
💀 EH I paid for gpt
does that count
Ask Nick
Is wha
eh like making ai answer whatever you ask without censorship
I'm not sureee
it's just for stories gang not the other stuff
I can just do it without telling anyone I guess unless it is against rules then uhh
😭 anyways that's the only reason I paid chat gpt and not ai dungeon it works fine after ig
yea if it's against that yea no discussion of how or what in here
Yuh

Idk how to even do it so I can't help with it anyway lol
i need emotional support now
I'm here for you 🩶
i just scrolled insta and found one friend's page
and suddenly i feel where I am at life
🤔🤔🤔
oooh okie okie lemmeee
Fill same details
The sample rate batch size etc and increase epochs
my audio not working for voice changer client demo
Hello 
For us to help you the best, Please Elaborate:
- your PC GPU (Such as Nvidia RTX 3060, AMD RX 9070 XT..)
- your operating system (Like Windows 10, Windows 11, Linux, MacOS 26..)
- what you want to do? There isn't a program that does everything, there's a program for each thing:
- AI Covers
- Train RVC Models
- E girl trolling
- TTS
- Roleplay in VC
- Roleplay in Games
- etc
- what tutorial link are you using
- a screenshot of the program
!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 3060) - 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 is very helpful.
To maintain a lega, safe & ethical community, we will NOT provide help for:
- (E girl, as an example) catfishing/trolling, scamming, impersonation.
- NSFW/Porn.
- Any illegal activities.
Requests for these topics will be ignored and may 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.
Excuse me, what is the best pretrein supplement at the moment?
guys how can i use the ai voice models i used to have a japanesee ai voice changer but now i cant find it anymore is there a client to help me use the ai voice models
Hello there!
Please Elaborate:
- your PC GPU (Such as Nvidia RTX 3060, AMD RX 9070 XT..)
- your operating system (Like Windows 10, Windows 11, Linux, MacOS 26..)
- what you want to do? There isn't a program that does everything, there's a program for each thing:
- AI Covers
- Train RVC Models
- E girl trolling
- TTS
- Roleplay in VC
- Roleplay in Games
- etc
- what tutorial link are you using
- a screenshot of the program
mostly for trolling
trolling how? what kind of voice model you're going to use?
when i go into a discord call or in a game the cable output for the voice changer dosen work :c

i need help :c
!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 3060) - 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 is very helpful.
To maintain a lega, safe & ethical community, we will NOT provide help for:
- (E girl, as an example) catfishing/trolling, scamming, impersonation.
- NSFW/Porn.
- Any illegal activities.
Requests for these topics will be ignored and may 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.
What troll? Troll your friends, or catfish using E-girl voice model?
basically making money while speaking like a girl, so yeah catfishing
Oh fuck. Sorry about that. 
Nah ur good, i think thats what most people use girl voice changers, basically talk about some nasty stuff and mske money.
are u trying to do that?
This is a General AI Server, AI has many fields, so we can't know your issue with little info
Please Elaborate:
- your PC GPU (Such as Nvidia RTX 3060, AMD RX 9070 XT..)
- your operating system (Like Windows 10, Windows 11, Linux, MacOS 26..)
- what you want to do? There isn't a program that does everything, there's a program for each thing:
- AI Covers
- Train RVC Models
- E girl trolling
- TTS
- Roleplay in VC
- Roleplay in Games
- etc
- what tutorial link are you using
- a screenshot of the program
soo when i try to create a img2vid i cant see the full image or the video? why is that?
:(
Definitely, that is easily the 90%. The other 10% is all of the normal stuff. I dont understand how some are still suprised by that.
Does bf 16 take longer to train than fp 16?
Yes
guys anyone can help me here
i have rtx 5070 ti oc
and i don't know how to use the program
i don't even know how to use the program
people put VOICE Models
and sound they create is different from what i hear from myself
it sounds so bad
idk why
for example i will show you one
real idk why too
About pitch and formant pitch stuff stuff keep tuning till you find one , you have 5070ti lower chunk to around 120ms and 2s extra and keep lower chunk, increase extra but the monitor has to stable at green
Wdym it cut out?
This is a General AI Server, AI has many fields, so we can't know your issue with little info
Please Elaborate:
- your PC GPU (Such as Nvidia RTX 3060, AMD RX 9070 XT..)
- your operating system (Like Windows 10, Windows 11, Linux, MacOS 26..)
- what you want to do? There isn't a program that does everything, there's a program for each thing:
- AI Covers
- Train RVC Models
- E girl trolling
- TTS
- Roleplay in VC
- Roleplay in Games
- etc
- what tutorial link are you using
- a screenshot of the program
there's thousands of voice changer programs
Please Elaborate:
- your PC GPU (Such as Nvidia RTX 3060, AMD RX 9070 XT..)
- your operating system (Like Windows 10, Windows 11, Linux, MacOS 26..)
- what you want to do? There isn't a program that does everything, there's a program for each thing:
- AI Covers
- Train RVC Models
- E girl trolling
- TTS
- Roleplay in VC
- Roleplay in Games
- etc
- what tutorial link are you using
- a screenshot of the program
that's outdated asf,
delete everything
are u trying to do e girl trolling like in the video
This is a General AI Server, AI has many fields, so we can't know your issue with little info
Please Elaborate:
- your PC GPU (Such as Nvidia RTX 3060, AMD RX 9070 XT..)
- your operating system (Like Windows 10, Windows 11, Linux, MacOS 26..)
- what you want to do? There isn't a program that does everything, there's a program for each thing:
- AI Covers
- Train RVC Models
- TTS
- Roleplay in VC
- Roleplay in Games
- etc
- what tutorial link are you using
- a screenshot of the programThis is a General AI Server, AI has many fields, so we can't know your issue with little info
Please Elaborate:
- your PC GPU (Such as Nvidia RTX 3060, AMD RX 9070 XT..)
- your operating system (Like Windows 10, Windows 11, Linux, MacOS 26..)
- what you want to do? There isn't a program that does everything, there's a program for each thing:
- AI Covers
- Train RVC Models
- TTS
- Roleplay in VC
- Roleplay in Games
- etc
- what tutorial link are you using
- a screenshot of the program
Please Elaborate:
- your PC GPU (Such as Nvidia RTX 3060, AMD RX 9070 XT..)
- your operating system (Like Windows 10, Windows 11, Linux, MacOS 26..)
- what you want to do? There isn't a program that does everything, there's a program for each thing:
- AI Covers
- Train RVC Models
- E girl trolling
- TTS
- Roleplay in VC
- Roleplay in Games
- etc
- what tutorial link are you using
- a screenshot of the program
E girl trolling is catfishing, which is illegal. You have been warned both verbally and via sapphire and continuing to ask will lead to further actions possibly like a ban
Also that video is extremely outdated, delete everything and forget about catfishing
catfishing in itself is not illegal
E girl trolling is catfishing, which is illegal. You have been warned both verbally and via sapphire and continuing to ask will lead to further actions possibly like a ban
I'm trying to get an voice and the sample sounds sooo goood while when i use it it sounds so bad
catfishing only becomes illegal once youre trying to use it for other illegal activities, which can then be added as an additional charge. but cafishing itself is NOT illegal
it leads to illegal things, it's not allowed
it doesnt necessarily, no
elaborate what i asked
it's written right in the server rules and help guidelines, that you should have read when joining
it's written right in the server rules and help guidelines, we don't allow it
yeah I did, and im not saying that he should have asked it, but catfishing is not illegal
that's not allowed at all either, it's written in the server rules and help guidelines
that's still e girl trolling which is catfishing, still not allowed and you admitted to doing it
yeah per rules youre not allowed to ask about it here
catfishers won't get help
Train RVC Models but i want to understand how this one works first so i can create my own you know
GPU : 5070 TI
OS : Win 11 Pro
you have admitted to wanting to do e girl trolling
Nick can you help me
NSFW isn't allowed either
can't help u :p
@viral mason dont help catfishers
My GPU is AMD Radeon RX 7700 XT
My operating system is windows 11
I'm just trying to troll my friends i used a tutorial to setup the program and i have it open and it works but the voice is so bad
you meant like this because of my powerful GPU ?
I hadn't read the entire conversation yet I was still looking at the messages from 11 am (my time)
Also, no need to ask @viral mason , nobody is allowed to help you for e girl trolling as it's catfishing
there's so many losers here man (egrill catfishers)
99% of the times people use it for profit, tricking, and other bad things
and then flex it on tiktok "e girl dicord free nitro" 
I'm just trying to troll my friends
like, e girl troll your friends?
Meanwhile i use and toture my throat to have as high as hyperfem and as low as boy voice🥀
idk if that's any better lmao
Im voice artist and singer tho
My job
😔
they are banned dw, they keep asking over before over and over in the server and now even dming multiple people about it, just ignore them lol
thats just your perception of things
that's cool actually
nah I've seen the people that join for the voice changer and they're....
yeah
they're all the same
well like I said
Nick i will show you example of my experience @viral mason @low shard
GREG-TEST-OUTPUT.wav
is the model publisher recording
and other one is mine .. how come the voice sound so bad like this ?
unless they want to actually use it for a good reason like for playing as a star wars character or whatever
don't judge me im tryna be david baszucki 
yeah that's completely fine and allowed, that's d&d roleplay, not trying to trick people for free e girl skins or things like that
I have seen, hundreds and hundreds, of people trying to e girl troll with statuses such as "spoil me" with only fans even and other very weird shit (which ofc got all banned)
WHY IS IT CUTTING LIKE THAT ?
sorry, but you want to train an rvc model right?
oh yeah
check applio https://docs.aihub.gg/rvc/local/applio/
Last update: August 9, 2025
wasn't that roblox ceo
there was some drama related to some moderation ceo
idk ngl
yeah
i understand @low shard but i want to understand how you hear your voice in best way because i don't want to train something then later on think as if its " sucked " because of dataset i wanna make sure i understand how it works like why this eminem model cutting ? even though the publisher made a recording without any cutting
listen to this and this
what settings do u have in the voice changer?
as you said it's roleplay about roblox ceo or smt, you should try wokada deiteris fork https://docs.aihub.gg/realtime-voice-changer/local/deiteris-w-okada-fork/
Last update: August 14, 2025
share a screenshot of ur whole program settings
is that deiteris?
copy these just as a start, your seettings atm are the reason it's cutting out
change them if it causes too much delay and such
will this fix so all models stop sounding bad?
I believe that is the same one you have rn
its worse
yeah I have no idea
@low shard then nick is the only way
can sb help me pls, i have 5070ti and 7 9800x3d, but w-okada still lagging when i use it while playing games, it works fine if game is opened in a tray, but when i switch to game it starts lagging. in graphics settings i alr set priority to high, starting it with an admin
i was using it with 2070 gpu in a same conditions, everething worked fine
You're using an older version of the voice changer it seems
I'm not sure what GitHub page you got that from but I recommend using either Vonovox or Deiteris
I see you have Nvidia so you can use either
Download them from the guide
-realtime
Guides for Programs that use RVC Models in Realtime for Calls/Games
Most suggested WebUI with the best general support for many platforms. GUIDE
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
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
ill try ty very much
Np I enjoy helping ppl ^^
how to make my own rvc?
Is there not a simple way to just take a voice sample. and use that to make a crappy AI voice that can sing along to music? Thats all I need
Huggingface?
There is a simple way to take a voice sample but not to make a crappy model because nobody wants that
Where can I find the simple way?
I could show u how, if you're fine with doing it online
It takes hours to train any model but cleaning audio and then starting the program that does the work does it take long
All free btw
Yeah sure, that works
Alr u can add me and do this in dms if you want just so you have all the information saved somewhere where you will always have it and not get it mixed up in a server if you want
is there a way for me to just pin Vonovox onto my taskbar with no issues?*
you have to open it the same way every time with the start thing you can't pin it
darn okay
i don't have to set it up every time though right?
nah you only have to use the setup once
okay thanks
np!
any idea why its doing this?
-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
-# kaggle is better than collab
are you trying to train a model?
can you help me solve this please
solve what
is this for the voice changer or
If you need urgent help, please checkout our AI Hub Docs or ask for help here following the [Guidelines](#1402790586028789830 message)
voice changer
do u use nvidia, amd, or intel
nvidia
cool
what version of the voice change is this btw, if u got it from a yt video it's prob outdated
u can download one of the two from this
-realtime
Guides for Programs that use RVC Models in Realtime for Calls/Games
Most suggested WebUI with the best general support for many platforms. GUIDE
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
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'm not sure I've seen that link before so most likely outdated compared to the newer stuff
it was working fine yesterday
idk how the code works so I just recommend using something that I know is new and being worked on like Vonovox
i see
tyty
i'll try the first one in the embed
good luck, if u need more help ask me or some of the helpers/mods
they know more
unfortunately this one is also doing the same thing
its not loading the UI
that's odd
idk if this is AI help but i can't seem to get w-okada forked to swap input audio. Anyone ran into this or have a solution?
nvm figured it out since it uses a browser (chrome for me) for its interface, you have to change the input there and not the program. (if anyone else runs into this)
im trying to make a cover using applio kaggle but it wont load, idk if it's my internet, i didn't have any issue yesterday
i pressed the convert button and it's been loading for like 10 minutes
Hi
yo when is the new w-okada gonna come out
what do you expect of it?
where did you get it from? it seems like a sketchy application possibly hiding some malware
its from the guide itself
which guide duh?
it doesn't seem to come from ours https://discord.com/channels/1159260121998827560/1393389200862089240
do u know a fix to this
the ui appears blank for me no matter which version i download
the request goes through but ui wont load lol
no it must be coming from some sketchy yt tutorial, not that you found it out of blue
....
it comes from https://rentry.co/VoiceChangerGuide
and it refers to like a strange e-girl server
which concludes you might have got scammed
dude
its literally a guide i got from this server itself
idk why're fixated on whether i got it from yt
idk where u got the link to this server lmaoo
idk it
stable better quality and faster
bruh
probably the old one? didn't recall that much
yeah
i downloaded old one to see where my issue comes from
its happening to me on both old and new aswell
I remember their former name was Raven/Blanc-dot, and now their repo has been archived 
this was the old one in last year
yeah i remember
this helps with delay? like it js repeats what u say like 5 secs after
How do i make a model sing a song without the song in the background?
voice isolation
duh
i mean i use delteris rn how do i make it sing without me needing to say anything
like text to speech but with song
hey guys, i am pretty new to the whole Voice Changer thing, anyone down to help me with it? i just cant seem to figure out how to make it sound good/ ''realistic :(
not a scam, it seems a rewrite of https://rentry.co/voicechangerguide
Guide Written by:
Github - VTArcelia
Rewrite (some formatting will be done later), some information changed, and made for Windows+Nvidia only now : To see the guide from before the changes go to rentry.co/VoiceChangerOG
This means AMD/Mac was removed, but the information still exists from the li...
anyways, it's outdated
that's a bot
for what?
are you asking someone what coding language u should do?
this is a general ai server so you need to elaborate for us to hep you
Hello, with "voice changer thing" you coud mean more than 3 programs with eahc different version,
Please Elaborate:
- your PC GPU (Such as Nvidia RTX 3060, AMD RX 9070 XT..)
- your operating system (Like Windows 10, Windows 11, Linux, MacOS 26..)
- what you want to do? There isn't a program that does everything, there's a program for each thing:
- AI Covers
- Train RVC Models
- E girl trolling
- TTS
- Roleplay in VC
- Roleplay in Games
- etc
- what tutorial link are you using
- a screenshot of the program
the settings are different per user
Please Elaborate:
- your PC GPU (Such as Nvidia RTX 3060, AMD RX 9070 XT..)
- your operating system (Like Windows 10, Windows 11, Linux, MacOS 26..)
- what you want to do? There isn't a program that does everything, there's a program for each thing:
- AI Covers
- Train RVC Models
- E girl trolling
- TTS
- Roleplay in VC
- Roleplay in Games
- etc
- what tutorial link are you using
- a screenshot of the program
are u using wokada deiteris fork b2332 and not some random youtube video tutorial, right?
he said it's raven's archived repo
mmm weird
where do i download gabox fv6 model
whats the best e-girl model
Read the help guidelines before you start asking anything here.
am i the only one having issues with trying to download deitiris vc?
or is it just an isp issue on my side
Where do you use UVR5? Local or online?
even with a download manager it just fails to download at 1gb and goes temp unavailable
Make sure to check your internet connection. Fast internet/Wi-Fi is always recommended.
hi, does anyone know of any AI vocal synth (like vocaloid, ace studio, synthv) site/software that can sing natively in Polish?
are u trying to do e girl trolling?
internet is fine have managed to download wokada the old one wo an issue
have tried everything including resetting my router it always fails at exactly 1.06gb
i'm guessing ur talking about wokada deiteris fork b2332
the only thing I've found is Maghni AI but it's not released yet and doesn't even have an ETA
yes
Please Elaborate:
- your PC GPU (Such as Nvidia RTX 3060, AMD RX 9070 XT..)
- your operating system (Like Windows 10, Windows 11, Linux, MacOS 26..)
- what you want to do? There isn't a program that does everything, there's a program for each thing:
- AI Covers
- Train RVC Models
- E girl trolling
- TTS
- Roleplay in VC
- Roleplay in Games
- etc
- what tutorial link are you using or download link
I also found this site called melobytes.com but the "realistic" (AI) voices seem to ignore language settings 
3050 TI
Win 11
Roleplaying in VC
https://github.com/deiteris/voice-changer/releases/download/b2332/voice-changer-windows-amd64-cuda.zip.001 (saw this from the AI guide)
and the "non-realistic" voices sound like that computer from the 60s
get it from https://docs.aihub.gg/realtime-voice-changer/local/deiteris-w-okada-fork/ instead
Last update: August 14, 2025
UTAU isn't AI
it's very outdated and very complicated to use
trust me I've tried
im assuming this part here: Download AMD, INTEL and CPU on Windows
The latest version as of December 7th 2024 is: dml-b2332 (click here to download)
I prefer manual music composing. 
nope, it depends on your pc gpu, you got an nvidia gpu, get the nvidia one (you dont have an rtx 5000 serie gpu, dont get that type of nvidia download)
I want it to be manual too but also realistic
I see thank you
yw
No, this one is for AMD/Intel GPU. You have NVIDIA GeForce RTX GPU, so download the one that says NVIDIA instead.
local
Hi guys! Quick question, I need to voice clone, and I have 13k hours of ptbr speech (already as flac and edited). I need it for reading, not singing. What do you guys think is better: Titan+RVC2 or I’m better of just training it from 0? And would this setup give me a very close pitch? I’ve tested titan+rvc2 with 30 min dataset but I was not near close the voice, ~300 epochs
I know UTAU can be realistic but it's near impossible to do unless you've been studying this software since the day it came out in 2008 
i suck at singing 
titan creates harmonic distortions which is bad, u should use legacy core if you're gonna use a pretrain
there's two versions tho, one for spin and one for contentvec
tho they're both being remade I believe
Thanks! Do you think training from scratch with ~13 hours not worth it?
I'm not entirely sure if that's enough data as I don't train from scratch but you could always ask around, or just go for it
same
Please Elaborate:
- your PC GPU (Such as Nvidia RTX 3060, AMD RX 9070 XT..)
- your operating system (Like Windows 10, Windows 11, Linux, MacOS 26..)
- what you want to do? There isn't a program that does everything, there's a program for each thing:
- AI Covers
- E girl trolling
- Train RVC Models
- TTS
- Roleplay in VC
- Roleplay in Games
- etc
- what tutorial link are you using
- a screenshot of the program
we talked before, you were using wokada deiteris fork b2332 for your rtx 3050 on windows, what errors?
im using the fork voice changer and whenever im using it normally without playing any game it works okay but whenever im playing a game the voice pitches goes so high and the voice doesn't work smoothly
it used to work great in the prev versions but now it lags and i can't use it anymore while playing game any help?
Hello, it's hard to understand what program and version you're talking about
Please Elaborate:
- your PC GPU (Such as Nvidia RTX 3060, AMD RX 9070 XT..)
- your operating system (Like Windows 10, Windows 11, Linux, MacOS 26..)
- what you want to do? There isn't a program that does everything, there's a program for each thing:
- AI Covers
- E girl trolling
- Train RVC Models
- TTS
- Roleplay in VC
- Roleplay in Games
- etc
- what tutorial link are you using
- a screenshot of the program
gtx 1660 super
wi 10
wanna use goku voice in valorant
using fork nvidia
b2332- nvidia cuda
play on lowest graphics, 1080/720p 60/30 fps cap, close everything else in the background
show an entire screenshot of the program without cropping out anything while the game is playing
hey, using L40 Appolio RVC training on cloud, im not sure if i did it right but i set my batch size to 40, my vram's only using 22/48gb. Should i crank it up to 80 or is that something i musnt do?
uncheck sup1, use rmvpe without onnx
on wokada deiteris fork, you can **optionally **use more advanced settings for benefits:
- Advanced Settings -> Force FP32 mode: on (THIS IS OFF BY DEFAULT! Turning this on improves stability. Increases VRAM usage by 200 MB)
- Advanced Settings -> Disable JIT compilation: off for faster loading speed of the program, on for slightly better performance (10-15 ms) for Nvidia only)
- Advanced Settings -> Crossfade Lenght: Controls how smoothly the AI stitches different processed parts "chunks" of your voice back together. 0.1 for fastest voice, 0.15 for improved quality but increases delay by ~50 ms
- Reduce the delay on Windows via the Wasapi / Asio Guide
ok should i do this
can someone help me out for a voice model that i want to host it on my computer :)
yes
it's optional
Does applio colab by IA support applio 3.3.0?
I wanna use the new legacy core pretrain model
it uses Applio 3.3.1
also Cloud shouldn't be ur first option
u should firstly check if your pc gpu is good enough to run it locally
Well, my laptop is trash so I can't train locally🤣🫠
What do you suggest?
Welp, in that case then you should use cloud
Applio Kaggle and Lightning.AI give more free hours which is better for training, but ur choice since they are harder to setup than colab
Yes, my gpu is intel hd 4600 (don't bully me😭)
Ok thanks bro
CalledProcessError Traceback (most recent call last)
/tmp/ipython-input-1040336288.py in <cell line: 0>()
23 for package in pip_packages:
24 print(f"Installing {package}...")
---> 25 subprocess.check_call(['pip', 'install', '--upgrade', package])
26
27 #Fix torch error on model load
/usr/lib/python3.12/subprocess.py in check_call(*popenargs, **kwargs)
411 if cmd is None:
412 cmd = popenargs[0]
--> 413 raise CalledProcessError(retcode, cmd)
414 return 0
415
CalledProcessError: Command '['pip', 'install', '--upgrade', 'fairseq']' returned non-zero exit status 1.
how do i fix this?
Hello!
Please Elaborate:
- your PC GPU (Such as Nvidia RTX 3060, AMD RX 9070 XT..)
- your operating system (Like Windows 10, Windows 11, Linux, MacOS 26..)
- what you want to do? There isn't a program that does everything, there's a program for each thing:
- AI Covers
- Train RVC Models
- TTS
- Roleplay in VC
- Roleplay in Games
- etc
- what tutorial link are you using
- a screenshot of the program
yw
i am using rvc v2 disconnected but i clicking install dependencies and waiting but its giving error
rvc v2 disconnected is ancient, it's abandoned since months #📰│dev-updates message, don't use it
@forest kiln please elaborate your pc gpu, operating system so i can give you another program to train RVC STS models
oh how can i create model then?
win 10 and i am using amd
AMD makes both CPUs & GPUs, I need the GPU name
You can check your pc gpu on Windows via:
ctrl+shift+esc (task manager) -> Performance tab -> GPU
and btw win 10 support is ending in october 2025
amd radeon rx 580 2048sp
oh that's pretty old, i mean it could theoretically train locally but it has low vram and not enough gpu power, so in your case it's better to use cloud
Train (make) RVC Models on cloud:
- Prepare the Dataset
- Setup RVC:
Choose a cloud way to use RVC,
- Google Colabs (max 4 hours of daily T4 16gb gpu not granted for free, but easy to use, there's a paid tier):
- Kaggles (a bit harder to use and needs phone number but gives 30 hours weekly of better gpus, either T4x2 16gb each or P100 16gb, only free):
- Lightning.ai (Kinda hard, needs login, no issue with web uis or anything, but only free 15 credits monthly, Free Studios run 24/7 but require restart every 4 hours. There's a paid tier):
- Applio (UI)
- Be sure to know about the tensorboard
Google Colab = Easier but risk of getting disconnected
Kaggle = Harder but more gpu time
If you want the easiest way and for free, is using https://weights.com/ which uses RVC
RVC Inference (use models) on pre-recorded audio on Cloud
You can use either:
- Weights.com: Easiest Possible Ever Automatic
- Ilaria RVC Zero: Fast and free on cloud
- Applio UI Colab: RVC Fork with some extra features like TTS
- RVC AI Cover Maker UI: Automatically Separates the Vocals and Instrumentals, converts the voice and mixes them back
ok thanks
you're welcome, let me know :)
Can someone tell me why the voicechanger is not working as well as it should? Is it just incompatible with my gpu?
Hello, it's hard to understand which issue you are having
Please Elaborate:
- your PC GPU (Such as Nvidia RTX 3060, AMD RX 9070 XT..)
- your operating system (Like Windows 10, Windows 11, Linux, MacOS 26..)
- what you want to do? There isn't a program that does everything, there's a program for each thing:
- AI Covers
- Train RVC Models
- E GIRL Trolling
- TTS
- Roleplay in VC
- Roleplay in Games
- etc
- what tutorial link are you using
- a screenshot of the program
Arc A750, Win 11, just wanna try out the voice changer lol
i had help from a friend who guided me through the basics
just downloading the program and installing a simple voice
I see, Intel Arc A750 GPU,
could you please share a screenshot of your entire program/error and the tutorial link ? Because there are too many voice changers to know which one you're using and what error you're having
it's not really an error, it's just that the voice is not actively working in realtime. The voice cuts out and it's pretty bad, so i was wondering if it was because of my gpu?
like, it's really choppy even if i set it to lower chunks
it can be related to:
- the voice model
- what you're using it for, like roleplay in discord vc, or a game like gta 5, like if your GPU can handle it
- the program you're using
- the settings
That's why I would kindly ask you this info :)
most likely bad settings
can you elaborate on program?
like the download / tutorial link you're using, because i can't know if you're using the right program or an outdated version off 2 years ago
gotcha
@low shard is it alright if i send you a friend req so i can send you ss?
or you can just send me one, that works too lol
he can give u image perms
