#voicechanger not working
1 messages · Page 1 of 1 (latest)
Elaborate
RVC = Retrieval-based-Voice-Conversion, the best Speech To Speech AI Models (on v2), Inferences (use models) pre-recorded audio (ai covers) and train (make) models. Technically, Mainline RVC does have a go-realtime.bat (aka RVC-GUI), but it's pretty messy and outdated so it's extremely not suggested for realtime.
Wokada = uses RVC for realtime inference. There's 2 main versions, Original made by Wok, and the most suggested one is Deiteris Fork (modified version)
What's your PC GPU? What you want to do? What is the issue?
Oh just checked #✨│ai-help message
Be sure to set rmvpe without onnx
Extra to 2.7
Chunk to 400
And lower game graphics to the minimum
Be sure to close useless programs
Also uninstall vb audio cable and get vac lite from the deiteris fork guide which you used to get the program
Nvm I installed the wrong version sorry
My friend told me to download a version but it wasn’t the right one
be sure it’s the wokada deiteris fork version b2332
you seemed to have it in the screenshot
do NOT use video tutorials if he’s suggesting you one
they use an old original wokada
Alt
the updated version is https://docs.aihub.gg/rvc-voice-changer/local/deiteris-w-okada-fork/
Last update: May 5, 2025
did he send u a yt tut lol?
Yes
tell him that those use an old version with worse performance and quality
Ok
it’s an old orignal wokada with messy code
not worth at all if u don’t want to waste ur time
read the guide i sent you, send it to him too
don
e
i installed it
its still not detecting
i dont even hear my voice
Show a screenshot of ur wokada
wdym
That's the programs name
ok
Wokada got 2 versions, original wokada and deiteris fork
I gave you the deiteris fork link which is the best
that's the old original wokada
do NOT follow video tutorials for AI programs, for example wokada video tuts arte old
uninstall it
read this guide
it's the only way to get the updated one
using video tutorials or keeping to use the old version won't fix anything
ok
what do i use then
what do i use
Read the guide he sent to you carefully before you ask anything.
i just dont find it
what don't you find?
it's all written in there
you need to read all the steps
if you don't, you won't be able to use the program then
reading the guide is a must for you to understand the program
ok
but wich one do i download
you got an nvidia gpu and are probably on windows, download the nvidia windows version of wokada deiteris fork
ok
i did
alr
show a screenshot
here
are you sure it's the b2332 version? the latest wokada deiteris fork opens in the browser and not in it's own window
it is
can you help me please
i dont have much time left
voicechanger not working
ok i gtg sorry
ill be back
are you sure?
it displays as it's own window
Yes I showed the window
yeah and it’s not supposed to open in it’s own window
be sure u deleted all of the original wokada and that it opens in ur own browser
Oh ok
Is there a specific version of Detris fork W-Okada that opens its own separated window and not browser? The Detris fork W-Okada I use opens a browser.
If you have run both original and fork W-Okada versions at the same time, whether by unknowingly or not, close them and then run fork W-Okada again.
Words alone aren't enough to imagine, so this is what Detris' fork W-Okada supposed to look like.
It runs my browser
First
And I do smth else so it opens the app
that’s not suggested
don’t do that
Ok
it doesn’t have it’s own windows to not cause any performance issues
Ok
Yes
set output to line 1
Wdym f0 to rmvpe
u can also optionally get better quality and stability at the cost of delay if u enable force fp32 mode in advanced settimgs
select rmvpe, not rmvpe_onnx
Do not. Don't do anything you don't know outside what suggested in guide. If you confuse yourself one more time, you will be cooked.
Ok
you will be cooked.
btw no need to say that

To spam send emotes, this is not where you do this.
Audio client or server?
And what do I put in monitor
Optionally, to hear what W-Okada outputs, you can set monitor to your "speaker or headphone".
Your choice, client can use echo/noise suppression while server has less delay
Which do you need?
Your headphones optionally to hear urself
This is what server audio mode looks like, you can do this when you wanna get less audio delay as possible. But you won't be able to use any of noise gate ticks above when select to server mode.
try using WASAPI instead of MME in server mode
close useless programs in the background, what program are u using wokada deiteris fork with?
ok
still not replacing my voice tho
well, first of all ensure you're running the cuda one, not directml
that'd be the only explanation for " super delay " as long you have all set right ( chunk stuff and all of that
Unless you're an amd user or something then idk, can't help
i dont have super delay anymore but its not replacing my voice
wdym
close programs in background
are u using wokada deiteri sfork along with a game?
why reply my same comment twice?
did it "replace the voice" previously with the client mode?
otherwise, check the selected audio devices by showing here
wdym
wokada deiteri sfork
oh
This is Detris' W-Okada fork. https://cdn.discordapp.com/attachments/1371568582848417834/1372882565949816874/image.png
yes i have it
and im using it on roblox
i use MMVCServerSIO_win_onnxdirectML-cuda_v.1.5.3.15
have you been told to use the better fork version? https://docs.aihub.gg/rvc-voice-changer/local/deiteris-w-okada-fork/#windows

That version of W-Okada is the original version, and it's outdated. Use fork W-Okada instead for better performance.
no
ohhh
where is it
Did you forget where download link is? The guide link has already sent by another mod. https://docs.aihub.gg/rvc-voice-changer/local/deiteris-w-okada-fork/#download-nvidia-on-windows
Last update: May 5, 2025
oh
this app cannot run in your pc
it says
show a screenshot
Later I can’t
alright, keep us updated
make sure you've actually got the version as shown above and double click MMVCServerSIO.exe
if it may be corrupt, try redownloading it without antivirus enabled temporarily that may interfere
also before downloading, try scanning your system
Ok..
HI
Buh. For a normal conversation, go to #✦│chat or #🧬│ai-chat. If you want any help about W-Okada or other AI program, make a thread in #1192011222023950368.
yes but
i downloaded 5000 rtx one
where is 4070 one
Last update: May 5, 2025
download the normal nvidia version
you got a 40 serie, not 50
where is the 40 one?? can you show me
there's no specific one for 40 serie, only the 50 serie has a specific one
oh
all the other nvidia gpus just use the normal nvidia one
so i download the 50 serie?
no.. you got 40 serie, download the normal nvidia one
where
this is the link ^
click it
Download NVIDIA on Windows
?
alr
be sure to also get vac lite https://docs.aihub.gg/rvc-voice-changer/local/deiteris-w-okada-fork/#virtual-audio-cable
Last update: May 5, 2025
and to uninstall vb audio cable and the old program you had
this one u used and prob got off youtube #1371568582848417834 message
MMVCServerSIO.exe
nono
the MMVCServerSIO_win_onnxdirectML-cuda_v.1.5.3.15 folder
its old
delete it
alr, but the version you had is old, you can simply delete it
if you have vb audio cable, uninstall it from app settings
alright, get vac lite and wokada deiteris fork from the guide then
alr get wokada deiteris fork too
alr
lmk
Last update: May 5, 2025
can y help
uninstall vb audio cable from app settings
you didn't
uninstall it from app settings
set gpu to ur rtx 4070
f0: rmvpe without onnx
chuunk: 80
extra: 2.7
input: ur microphone
output: line 1
monitor: to hear urself optionally, ur headphones
what browser do u use
wdym gtx 1070
chrome
it should work fine
try the settings i told u
alr
on wokada, you can optionally:
- Force FP32 mode: on (THIS IS OFF BY DEFAULT! Turning this on improves stability. Increases VRAM usage by 200 MB)
- Disable JIT compilation: off for faster loading speed of the program, on for slightly better performance (10-15 ms) for Nvidia only)
- Reduce the delay via: https://docs.aihub.gg/rvc-voice-changer/local/deiteris-w-okada-fork/#reduce-more-delay
Last update: May 5, 2025
https://docs.aihub.gg/rvc-voice-changer/local/deiteris-w-okada-fork/#adding-models
You can search rvc ai voice models at:
- #1175430844685484042
- In #🔍│find-models , Do /find with @west jungle
- https://weights.com/ (login required)
- https://huggingface.co/models (but watch out cus in hugging face there arent only rvc ai voice models)
- Suggested Models for Realtime Voice Changing (Wokada)
- https://voice-models.com/
- https://thevoicemodels.com/ (for Turkish Models, login required with discord and level 2 on their server)
if there isnt one, you can:
- make it yourself with our docs guides
- Be aware that we don't allow any model request, so don't fall for any "pay me 20 dollars and i will make the model for you" dm
Last update: May 5, 2025
:wave: @wheat prawn, How can I help?
Available Commands:
• @weights find <query> or /find <query> - Search for RVC Voice Models
• /create - Create an AI Cover
• /image - Generate an Image
yeah, set extra to 2.7
as monitor, yes
add a model
try the optional settings for better quality and delay if u want
then set the other program input as line 1
then just click start
ok
headphones as monitor, microphone as input
can u help pls
its for roblod
elaborate, what's the issue?
roblox
did u set input as line 1 here?
like i still hear my voice
no
do it
ok
also, be sure you didn't miss this step
yeah but
what
i dont hear anything now
@pure island be sure you did this step
don't miss steps, or it can fuck up your entire audio system
so i did it basically i set at default my recording and playback things that i use
thats what i need to do?
you need to set your usual devices as default recording and playback
no one can know what are your usual devices than you
the microphone you always use, the output device you always use
yeah
show a screenshot
i set at default
show
show ur program and roblox settings
oh its a laptop gpu
then you need to click stop, and increase chunk (delay) to 250
nononoooo i need to download another thing?
laptops are weaker
no just have more delay, thats all, no need to download anything else
also be sure to close everything in the background
and play at roblox lowest settings
wdym
you need to play every game at lowest graphics settings while using the voice changer
you can't expect to play on high settings while using an intensive realtime ai task
oh ok
still
i cant hear
anything
show a screenshot of ur roblox settings
seems good
well
show a screenshot of ctrl+windows key+v
what windows version are u on
but output is auriculares
11
is it selected to that, at the bottom right?
it needs to be basically enlighten to mean that its selected
it should have a recetangle around it to mean its selected
yes
if it still doesn't work, try rebooting your pc
start mmvcserversio.exe, roblox, and test it again
ok
now output is varios microfonos
like my mic
and output is my headphones (auriculares)
i changed it
ok working
any other issues?
but not replacing my voice
its gonna be a loop
somethings wrong
maybe my pc maybe what u send is incorrect
yes
what?
show a screenshot again of ur program settings and roblox
wokada too
that's done already
go to settings > system > audio and show a screenshot
oh
i see now
the problem
i think
it gotta be line 1 the output i think
idk
its almost 3 am for me
i need to soon
i just wanna finish a problem
its maybe the model
idk
bc voice working
wdym?
voice is appaearing
but isnt changing my voice
but i notice my voice like a little changed
so maybe its the model
the settings are fine, try another output device (like another pair of headphones), or try another model
there's thousands of ai models
not all are good
i dont have another headphones, can i use my pc mic
i meant as output device, anyways try first another model
bruh
doesnt work
isnt model problem
i tried a model thats working (i tried on applio too)
like it doesnt replace my voice
and i dont hear the voice
u there?
tell me if theres no fix bc i gtg soon
i gtg in 10 minute
bc its 3 am in 10 minute
alr i gtg
u tell me tomorrow
bye
send me a screen record tmr, showcasing use case, roblox settings, wokada settings, windows settings, and be sure to put the obs (or whatever u use to screen reocrd) input setting to line 1
@thorny herald
make your own help post
Don't invade others post
@thorny herald all your messages have been deleted here, elaborate in your own help post
And don't randomly ping staff
ok
i cant screen record
so
!give-media-perms 1h @pure island
did you mean you don't have perms to send it?
nono
i mean somethings wrong whit my video thing
and when it was working files were too big
what?
like it doesnt open
you can just use the obs program
OBS (Open Broadcaster Software) is free and open source software for video recording and live streaming. Stream to Twitch, YouTube and many other providers or record your own videos with high quality H264 / AAC encoding.
i wanted to check how you sounded
i sound whit my real voice like nothing changed
which is why i wanted to hear it by you screen recording and using the input as line 1, while also showing all settings
Wdym you can't? You can just use OBS to screenrecord
Or is the issue fixed?
i dont wanna show my voice
screenrecording with line 1 input would mean that its using the converted voice, not your voice
if you want instead you can show the screenshots of your windows, wokada, and roblox settings instead, and try one of our suggested models https://docs.aihub.gg/rvc-voice-changer/local/deiteris-w-okada-fork/#models-to-try
Last update: May 5, 2025
ok now it works!!!
but
delay
IT WORK
OMG
TYSM
BEST AI HUB EVER
U GUYS ARE THE BEST
I FIXED IT
BEACUSE MY MAIN WAS LINE 1 SOMEHOW
you're welcome


