idk what else to say the version i have is alpha 2.1.4
i have RX 9070 16GB VRAM
and im using windows 11 25H2
All i did was just install the RVC tired to launch it and most of the files where you can launch crashes with the same message i have python 3.13
and this is where i downloaded: https://huggingface.co/wok000/vcclient000/tree/main
#RVC not launching and gives this error before crashes
1 messages · Page 1 of 1 (latest)
Try better W-Okada fork from this guide instead of the one you tried to use. https://docs.aihub.gg/realtime-voice-changer/local/deiteris-w-okada-fork/#download-amd-intel-and-cpu-on-windows The one you tried to use is an outdated one.
Last update: September 6, 2025
isnt the updated one is for nvidia gpu only? i have AMD CPU and GPU
that’s not RVC, RVC means Retrieval-based-Voice-Conversion, not realtime voice changer
that’s original wokada
oh
which isn’t suggested anymore
RVC doesn't always mean realtime voice changer.
wokada tg-develop fork would be more suggested
it recently got an update
how am i supposed to know that
💻 Local Realtime RVC
Guides for Programs that use RVC Models in Realtime for Calls/Games
• Vonovox
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
• Wokada Tg-Develop Fork
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
• Wokada Deiteris Fork
Most suggested WebUI with the best general support for many platforms. GUIDE
⚔️ Wokada Deiteris Fork vs Vonovox
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
⛔ Outdated/Discouraged
These options are not recommended for use.
• Original Wokada
Not suggested, older versions in youtube tuts are even way worse. GUIDE
• RVC GUI Mainline Realtime
The program is worse compared to the ones above, and much less updated. GUIDE

either of these
tg-develop is the newest tho
For more newer features added in W-Okada, I'd say Tg Develop W-Okada fork. https://docs.aihub.gg/realtime-voice-changer/local/tg-develops-w-okada-fork/
Last update: October 26, 2025
the one the updated i saw on github before was for nvidia only while the outdated its for all
What's wrong?
nothing
Btw dont follow any video or youtube tutorials for these type of programs
refer to this point https://docs.aihub.gg/realtime-voice-changer/local/tg-develops-w-okada-fork/#download-amd-intel-and-cpu-on-windows
Last update: October 26, 2025
to see if its worth to follow
AI changes pretty fast
every video/youtube tutorial for ai realtime voice changers is outdated
Most of tutorial videos on YouTube only telling you to try and install the "original" version, despite their uploaded dates.
so it opened on the web
don’t, even the newest tutorials just use the same tools as old ones
sometimes that outdated methods can be working
Not always.
ik
those tuts also mislead ppl with bad settings like maxed extra, vb-cable, and so on
If you see this Deiteris W-Okada opens your browser, it's completely normal for this specific W-Okada. Tg Develop one also does the same.
You can still use windows xp, but it doesn’t mean its good
it was a metaphor to say to not rely on outdated methods because there’s a difference between working and working well
that’s normal, btw that’s wokada deiteris fork, it won’t have the same quality of ife features as tg-develop but it’s your choice
Did you perhaps install vb audio cable?
yeah but i havent used it alot
the first time i used it i wasnt sure how to test it and how to config
uninstall it from windows app settings
why
get vac lite from the same ai hub docs guide
it isn’t suggested, many users reported issues with it on windows
that’s why youtube tuts aren’t recommended too
Too simple question. VB-Cable can give random issues for Windows users when using with W-Okada.
thats becuase when they install it their sound drivers were gone but its very easy to fix it if its gone
it happened to me too but i fixed by using windows troubleshooter whatever its called
nope
it’s not because of that
that’s a normal thing because windows changes the default audio output
there were other random issues on the long run
didnt it get updated in like a year ago?
we would highly suggest you to use vac lite if you don’t want any issues
okay
You wouldn't trying to argue "but it worked for me bro".
im not trying to argue
we aren’t arguing, i’m just explaining the best things to use dw :)
its gotta be this once if im correct
yeah u can click 3 dots -> uninstall
Yeah dw
you should
Restart your PC.
back
@indigo path which software do i need to install again i forgot
nvm found it
@halcyon garden i got question where can i find voice model
To upload a voice model into W-Okada, see edit button. https://cdn.discordapp.com/attachments/1425025269949010070/1426905477010165800/image.png?ex=69015c08&is=69000a88&hm=428f686407ffe0ca689d5c84028ad911a98b78d0b180daae12a89e155385d820& https://cdn.discordapp.com/attachments/1425025269949010070/1426905477991632936/image.png?ex=69015c08&is=69000a88&hm=92d342c33b2066fab328c5c9c8c5db1d6230d3555d10389045f7b8e79b033cf1& You wouldn't wanna put voice model files directly into "model_dir" because that's not how it works.
i already did that
Your statements are confusing. 
i just finished few steps so it now it works expect on voice chat
it only works on preview not the rest of the app
waiting for a respond..........

Because you don't give enough context, I'm not sure where to pinpoint at which would work as intended.
i checked on the apps to see if they work but the only thing it worked is the preview app from here
not anywhere else
it should work on all but for some reason this is the only app that is worked
Click on green "stop" button and try these settings:
Chunk: around 40 - 60 ms
Extra: 2.7s
GPU: AMD Radeon RX 9070 (DirectML)
F0: rmvpe_onnx
Input: your microphone
Output: Line 1 (Virtual Audio Cable)
Monitor: optional, you may set this to speakers/headphones to hear your W-Okada audio
it didnt work
What does that mean it didn't work?
no because the line 1 i placed it on output since the input i placed is JBL mic
i even tried to change the input mic to line 1 just for a dumb reason and it didnt work either
Seriously? You should set your input device to "Line 1" on your Discord, not the microphone from your JBL, because if you set Line 1 as output on W-Okada, W-Okada has to output its audio all way through Line 1, and that one "Line 1" device acts like a virtual microphone. But if you set both devices as Line 1 on your Discord, it would be a mess, as the audio would input, output, echoing to each other.
i check about it in one hour i cant check right now im on break right now
namari has told you to follow their input/output settings in discord, yours is different at all, that's why it doesn't work
i thought the example of the image he send was the "incorrect"
nah yours is the "incorrect", again that's why it didn't work
so why not just follow his example
line 1 as the input is actually correct, and try set your headphones to listen as the output
also check the voice changer settings
the output should be line 1 there
again as namari has shown already^
the reason i didnt follow is becuase i thought the method showed me was probably because this is what i acciedntlly set it that shouldnt work
it worked
@stone rampart this is not your thread, please post your own or ask in #✨│ai-help
