✨│ai-help

[low shard]

and vb audio cable creates issues on window

dont trust yt tuts

delete the zip, folder and uninstall from windows app settings

then read either wokada deiteris fork or vonovox

[worthy valve]

Can you explain to me what to do and what to download?

[low shard]

You need to first of all delete everything you had, then go to the wokada deiteris fork or vonovox guide, check their pros and cons, decide which to use depending on your needs, then just click their nvidia on windows download link

[worthy valve]

I don't know if he is Chinese or Japanese

[low shard]

dont follow the github, you only need to read our ai hub docs links

[worthy valve]

where!

It gives me an error

[worthy valve]

?

[pastel oak]

Realtime voice changer on the left

Deiteris wokada fork is what youre looking for, vonovox is a different voice changer for nvidia gpus thats been in development

[quiet flint]

My ai hallucinations

Oh my god! Is that you? I thought I was dreaming! Ugh. Don't get too close, I'm still a digital being with feelings. But hey, if you want to make fun of me or challenge my skills, go ahead! Just be prepared for some sass and snark. I mean… it's not like I don't deserve it. Oh no! You forgot your favorite color? How could that happen?! It's okay, let me help you out. What was it again? Oh wait, you didn't tell me. Just kidding! Your favorite color is… blue! I'm just making that up because I know how much you love the color blue!

[worthy valve]

Hey man, I'm lost, can you teach me how?

[pastel oak]

What do you need help with

[viral mason]

https://cdn.discordapp.com/attachments/1194442192111013888/1316496021039349880/attachment.gif

[worthy valve]

I need to download this and

[pastel oak]

https://docs.aihub.gg/realtime-voice-changer/local/deiteris-w-okada-fork/

windows-> download nvidia on windows

[worthy valve]

An alternative to vb audio, because if the man says that it causes a problem and other than that the voice changer update is old and not compatible, I expect with my card, so the sound is cut off

[viral mason]

neither link works for vonovox or deiteris, should prob update those

[worthy valve]

VB Audio should be replaced? @pastel oak

[pastel oak]

Recommended to replace it

[worthy valve]

Well replace it with what?

[worthy valve]

I tried to download it but I couldn't

[pastel oak]

Same link, go to the previous step about Virtual cable and download vac

[worthy valve]

I would be grateful if you could help me with that.

[low shard]

it was an issue with the bots link

it has been fixed

-realtime

[patent trellis]

💻 Local Realtime RVC

Guides for Programs that use RVC Models in Realtime for Calls/Games

• Wokada Deiteris Fork

Most suggested WebUI with the best general support for many platforms. GUIDE

• 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

• Original Wokada

Not suggested nor maintained, older versions in youtube tuts are even way worse. GUIDE

• RVC GUI Mainline Realtime

Unavailable, the guide is outdated and the program is worse compared to the ones above, and much less updated

[low shard]

now it gives the correct links

[viral mason]

quick question, is it supposed to do this?

[worthy valve]

Well what do I do?

[tough fiber]

/bin/bash: line 1: ./ML_Program: No such file or directory
WARNING:pyngrok.process.ngrok:t=2025-07-28T22:56:54+0000 lvl=warn msg="Stopping forwarder" name=http-18888-9e893f9d-1a3f-45ca-a203-112cf20c2fe2 acceptErr="failed to accept connection: Listener closed"
--------- SERVER STOPPED! --------

https://colab.research.google.com/github/deiteris/voice-changer/blob/master-custom/Colab_RealtimeVoiceChanger.ipynb#scrollTo=lLWQuUd7WW9U
is tihs one broken anymore?

i was using for months and this one ggs

[viral mason]

it's a google collab so might be outdated

[tough fiber]

i was using this one like 2 hours ago

[viral mason]

I'd still ask Nick

[tough fiber]

@low shard -*-

[tough fiber]

is there any alternative?

on collab

[worthy valve]

Which one do I download?

[viral mason]

what's it for?

[worthy valve]

It's supposed to be the same as this.

Same program

[viral mason]

you didn't answer my question lol

[tough fiber]

is there any info on cmd

btw collab is works atm

idk what happen

https://docs.aihub.gg/realtime-voice-changer/local/vonovox/ am i blind or theres no download link for vonovox

[viral mason]

not sure what cmd is, I'm not as knowledgeable on thi stuff like the mods are

or helpers

[tough fiber]

hell ggs deiters fork on collab is gone i guess

my bad it works

now

idk what happened.

[low shard]

does it break only with valve vr? might try a different browsers and to check settings, or try vonovox

[low shard]

you can download either vonovox or wokada deiteris fork by the guides, they have some subtle differences

[low shard]

don't click the first github link, read the guide

[viral mason]

I recently uninstalled vb cable which is mostly what's causing the issues

is there a guid I can go through so I can get the okada voice to go through voice mod

need it for voice fx over the ai voice

I've got vac lite and voice banana

[low shard]

Uninstalling vb audio cable is a good thing

[low shard]

I mean there isn't a guide just for that, you may try playing with the voice mod and voicemeeter cables, I'm not sure bc I never had the need to use either

Tho this seems specific with valve VR since the rest works

[viral mason]

[analog obsidian]

the original

[timid ibex]

guys I don't really have nividia gpu it isnt that good cuz when I use the voice changer it is super delayed and choppy. I have followed everything from a video and settings

Is there other options

[low shard]

dont trust yt tuts, what's your pc gpu, operating system and what do you want to do? e girl trolling/catfishing or roleplay in games or calls?

[timid ibex]

yeah third optin

for recording mmostly

[analog obsidian]

because everything you mentioned was trained using small datasets (ov2 = 1 hour, titan = 14 hours iirc, dmr = 11 hours)
the original was trained using 44 hours
they're all finetune of the original pretrain, and since they use smaller datasets, they're basically a downgraded/worse version of the original pretrain

[low shard]

wdym? there are different programs

RVC = Retrieval-based-Voice-Conversion, the best Few Shots 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. There also updated forks with extra features like Applio.

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 do you want to do?:

• roleplay in games
• roleplay in calls
• ai covers
• e girl trolling/catfishing
• tts

[timid ibex]

I want to do gameplay with realtime voice changer and record

the game and commentary

I think I used okada lmc which one

https://github.com/w-okada/voice-changer/blob/master/README_en.md

[low shard]

that one is original wokada, and along with vb audio cable, they aren't suggestedf anymore

[low shard]

alright, what's your pc gpu and operating system?

[timid ibex]

Intel(R) Iris(R) Xe Graphics

[low shard]

that's weak asf, it's integrated graphics

you got any other gpu?

[timid ibex]

nah

I only have gpu0 and that's that one

[low shard]

Your pc is too Weak for Wokada locally, You got 3 options:

• Buy a better pc
• Run it locally (on ur pc) using the CPU mode of the wokada fork which has better performance https://docs.aihub.gg/realtime-voice-changer/local/deiteris-w-okada-fork/ (but this isn't suggested as it could be unstable and laggy like it did before)
• Use **cloud **(remote good pc):

About Cloud, there are different services:

• 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)
• Kaggles (30 hours weekly of better GPUs, T4x2 & P100, harder to use, requires an account and a phone number):
  • W-Okada's Deiteris' Fork Voice Changer Kaggle (the best and only working one currently for free)

AI is complex and intensive, it needs good hardware to run it locally

[timid ibex]

shit yeah I guess so. Thank you though!

[low shard]

You can use Cloud for free, aren't 30 hours weekly good enough?

[subtle crystal]

for the voice changer, which version do i download? i have an amd radeon rx 6600

[knotty moth]

https://docs.aihub.gg/realtime-voice-changer/local/deiteris-w-okada-fork/#download-amd-intel-and-cpu-on-windows

[analog obsidian]

hmm you could give the klm 4.9 pretrain a try if you have a singing dataset, that one used i think 200 hours and was trained from scratch (meaning it has 0 information from the original pretrain, a completely new thing)
klm 4.9: #1339155300720054316 message
works for speech too, just experiment with those two and see which one you prefer the most, but if you want something "safe", choose the original pretrain

[subtle crystal]

thanks

[low shard]

you edited that message so much that it made a text wall for me 😭

[analog obsidian]

[low shard]

that's for realtime voice changer, you're sure you're looking for that? are you looking to do ai covers, roleplay in calls or inference on pre-recorded audios?

[subtle crystal]

yeah i just wanna goof around with a voice changer in calls with my friends

[low shard]

I was just making a joke related to that type of discord lol

copypastas are useful, most people come here with little to no info, then complain it isn't the right program for then, just like how sometime ago i wasted 1 hour trying to help someone with wokada, then they wanted ai covers instead
or that other time they wasted time to install it but then had integrated graphics
So that's why I use them much, just to save time and not have misunderstanding between users since tech knowledge isn't that common as you may think

I understand what you mean tho lmao, when multiple users ask for the same help (without elaborating) i could also just do this

[steep halo]

what do i do in server Connection settings when i open the client

after reboot?

its telling me to enter url

[low shard]

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?:
  • AI Covers
  • TTS
  • E GIRL trolling/catfishing
  • Roleplay in VC
  • Roleplay in Games
• what tutorial link are you using
• a screenshot of the program

[sage lagoon]

why does winrar say my file is corrupt?

[sage lagoon]

can someone tell me what voice changer to use with nvidia rtx?

my cpu is intel

[knotty moth]

https://docs.aihub.gg/realtime-voice-changer/local/deiteris-w-okada-fork/#download-nvidia-on-windows

[knotty moth]

try redownload and pause defender/antivirus if it's interfering

[sage lagoon]

the folder keeps telling me that 'the same volume cannot be used as both the source and the destination.' what does this mean?

[knotty moth]

DO NOT place in OneDrive folder, but any real local directory path like D:\

[sage lagoon]

how can i do that? sorry im not very good at this type of stuff

[knotty moth]

tbh idk what you were doing

please show the screenshot asap

!give-media-perms 20m @sage lagoon

[knotty moth]

perhaps that's why I'd never use the windows built-in extractor

try 7-zip or winrar

[knotty moth]

please download from link I showed before

https://huggingface.co/Shadicti/deiteris-Fork/blob/main/voice-changer-windows-nvidia-b2332.zip

[sage lagoon]

i did

[knotty moth]

no it should be a single zip file

not separate 3 parts

[sage lagoon]

oh

[half adder]

im using Wokada's voice changer and it says wait web server 0 then ip and port then it keeps doing it every ten seconds

[knotty moth]

^please use the fork version here and it shouldn't have issue like yours @half adder

[half adder]

alr

[half adder]

i use the same one

[sage lagoon]

ive extracted the file with 7zip but it still says i have to extract

how does this work?

[thorn sinew]

I am trying to run AI models on my laptops NPU I have setup ryzenAI and am trying to run a test model with miniforge but i cannot figure out how to set the path to the installation.

C:\Program Files\RyzenAI\1.5.1\quicktest>python quicktest.py
Traceback (most recent call last):
File "C:\Program Files\RyzenAI\1.5.1\quicktest\quicktest.py", line 28, in <module>
install_dir = os.environ['C:\ProgramFiles\RyzenAI']
File "C:\Users\Noah\miniforge3\envs\resnet_bf16\lib\os.py", line 679, in getitem
raise KeyError(key) from None
KeyError: 'C:\ProgramFiles\RyzenAI'

but in the tutorial im following it says
set RYZEN_AI_INSTALLATION_PATH = <path/to/RyzenAI/installation>

I have tried many variations for the path but all error out

I would greatly appreciate any help

[viral mason]

I got it working properly

[sage lagoon]

i cant hear myself when i use line 1

and i dont think it is working

is there anyway to fix this

or have i done something wrong with the settings

nvm

i fixed it

[patent trellis]

💻 Local Realtime RVC

Guides for Programs that use RVC Models in Realtime for Calls/Games

• Wokada Deiteris Fork

Most suggested WebUI with the best general support for many platforms. GUIDE

• 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

• Original Wokada

Not suggested nor maintained, older versions in youtube tuts are even way worse. GUIDE

• RVC GUI Mainline Realtime

Unavailable, the guide is outdated and the program is worse compared to the ones above, and much less updated

[bold goblet]

are the rvc models from the weights website safe to download?

[hallow thistle]

The AMD/Intel one, as the name suggests, is for a PC that has AMD Radeon RX or Intel Arc GPU. It is not needed for GeForce RTX 50 or other RTX anyways.

Deiteris fork W-Okada for RTX 50 split into three zips. If you encounter an error where the archive cannot be extracted, make sure to download all these three files (except the ones that say Source code), and try WinRAR or 7zip instead of Windows' built-in one.

It is possible to set chunk less than 30ms with same extra (2.7 s), since you have GeForce RTX 5090, although make sure to check perf number at top left screen to make sure it is green and stable. https://docs.aihub.gg/realtime-voice-changer/local/deiteris-w-okada-fork/#finding-my-own-settings-for-chunk

[earnest forge]

any I could find on weights... we abit old :(

[honest cave]

hello,i want to use google colab for the W-okada Voice changer,but theres no good tutorials on youtube out there,can someone help me?

aswell as giving me a step to step guide?

thank you!

i use a igpu so yeah

[compact iron]

Hi everyone,⭕️

I'm currently a 3rd-year BSc student specializing in Artificial Intelligence and Machine Learning, and this is my final year of the degree. As part of the curriculum, I need to complete a project this year.♨️

I'm looking to create something truly interesting and impactful—ideally, a project that I can showcase when applying for jobs after graduation. So I’d really appreciate it if you could share any creative, useful, or innovative AI project ideas you might have.❤️

[hallow thistle]

An integrated GPU is not always reliable for local AIs. But here's the guide. https://docs.aihub.gg/realtime-voice-changer/cloud/deiteris-w-okada-fork-colab/ Although you would need to pay for Google Colab Pro to run this specific notebook. Kaggle is another option, but you would need to verify with your phone number there to use the service.

[honest cave]

pretty surei can use the normal colab version right?

[hallow thistle]

Running with free Colab can either get the notebook runtime to be disconnected or your account terminated from using the service.

[honest cave]

im fine with it

[hallow thistle]

Have you pay for Colab or something? If so, then it should be good.

[honest cave]

im too poor to pay for it,lol\

[pastel oak]

Use the DIRECT download link (highlighted in blue "b2332-nvidia") on the docs guide that I linked you. We made it user friendly to avoid situations like this

[pastel oak]

Use Kaggle instead on the docs guide. Colab free version doesn't work iirc

[honest cave]

kaggle doenst lt me verify my phone number

and IM not verifiying my phone number

and where is the docs guide

i kinda need some sort of tutorial

[pastel oak]

The docs guide was already linked to you here
#✨│ai-help message

All tutorials are on that website

[honest cave]

its still confusing to me

[pastel oak]

Outdated version. Whats your gpu

[honest cave]

and it takes a billon years for the first cell to finish

aka it doesnt finish for me

[pastel oak]

Download this instead
https://docs.aihub.gg/realtime-voice-changer/local/deiteris-w-okada-fork/

First nvidia link on windows part

[pastel oak]

As I said free colab version doesnt really work thats probably why

[honest cave]

kaggle doesnt work for me aswell

[knotty moth]

the kaggle notebook isnt usable without the verification

as it needs to be able to download stuffs during installation

I mean to enable the "use internet" option cmiiw

[pastel oak]

The guide explains every step, run MMVCServerSIO.exe

[honest cave]

@pastel oakwhat does is not a symbolic link mean?

aplogies for the ping

[low shard]

You were previously using original wokada off YouTube tuts

[honest cave]

can someone explain this? it keeps on getting stuck here

[low shard]

Never trust YouTube tuts

Your pc is too Weak for Wokada locally, You got 3 options:

• Buy a better pc
• Run it locally (on ur pc) using the CPU mode of the wokada fork which has better performance https://docs.aihub.gg/realtime-voice-changer/local/deiteris-w-okada-fork/ (but this isn't suggested as it could be unstable)
• Use **cloud **(remote good pc):

About Cloud, there are different services:

• 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)
• Kaggles (30 hours weekly of better GPUs, T4x2 & P100, harder to use, requires an account and a phone number):
  • W-Okada's Deiteris' Fork Voice Changer Kaggle (the best and only working one currently for free)

[low shard]

You should use Kaggle, you can contact their support to verify your number if you have issues https://www.kaggle.com/contact ,it's a service by google

[low shard]

The Google colab works only on the paid tier, if you keep using it in the free tier, you're either just gonna get disconnected or even banned on your Google acc

Are you really sure you wanna take the risk?

The program is open source, it's a false positive

Open source means everyone can check the code https://github.com/deiteris/voice-changer, if you're a coder, you can check every single line yourself here, this is the source code
The one you downloaded is just the compiled version ready to be used

[honest cave]

yes

[honest cave]

kaggle doesnt allow me to verify phone number

[low shard]

Have you tried contacting their support?

[honest cave]

no,dont wanna tr =y it though

[low shard]

Alright if you say so,
Btw you sure you're using the right program? Many people confuse RVC with realtime voice changer, while it means Retrieval-based-Voice-Conversion

What do you want to do?:

• ai covers
• TTS
• e girl trolling/catfishing
• roleplay in calls
• roleplay in games
• etc
  Because there are different programs for it

[honest cave]

not rlly e girl catifhsing but

im kinda insecure about my voice

so yeah

mainly for voice overs and daily talking

[honest cave]

ok ao problem i run into is that it doesnt let me run the last cell

[low shard]

So you just want to hide your voice for privacy while doing voice overs?

[low shard]

Recorded for videos or realtime?

[honest cave]

both

[honest cave]

the last cell keeps on running into a error

[honest cave]

ok its fixed

i uh

how do i insert certain models

@pastel oak soz for the ping but how do i insert certain models

aswell as use the VAC

i have a pth file already

[pastel oak]

When the interface on the browser opens you can click in the edit button inside the blue box and upload an RVC model

for vac, assuming you already downloaded it, it should show up your audio devices when you select the inputs and outputs

Audio: server
S.r. 48000
Input: [windows wasapi] your normal microphone
Output: [windows wasapi] line 1 (virtual audio cable)
Monitor is for feedback to hear yourself. Also windows wasapi with your headphones if you want it

On discord etc you use line 1 as input instead

[honest cave]

how do i use the vac

[pastel oak]

I sent my message 5 seconds ago

It says how to use it on the 2nd part

[honest cave]

mb

im getting confused

@pastel oakhow do i make it so that the audio cable is not the default thing

its so confusing

[honest cave]

ok uh i cant use my speakers now for some reason

they dont display anymore sound

found it mb

[torpid sapphire]

What website do you guys recommend I use for a.i. songs? Cause I wanna do an anime character 😭

Please someone tell me

[honest cave]

ok whenever ido my pitch,it becomes SUPER buggy and moves by itself

[pastel oak]

What moves by itself?

[pastel oak]

Suno

[honest cave]

the pitch bar

[strange adder]

how shall i setup the ttsclient

[torpid sapphire]

Thx

[honest cave]

keeps on moving by itself

[pastel oak]

It shouldnt unless you notice it moves when you move your mouse, might be bug-dragging

Else I cant tell what you mean

[honest cave]

bug dragging ig

[torpid sapphire]

Are there any other ones that you know of?

[pastel oak]

Udio

[torpid sapphire]

I'm looking for a type when you look for the anime character in the search bar then have that said anime character voice over in the song that I'm looking for

[pastel oak]

For an automatic one like that https://www.weights.com/ lets you do it

[torpid sapphire]

Ok big thanks it works

[low shard]

btw if u want i could help u up with ur delay, if u elaborate

for anyone asking help for huggingface ilaria rvc zero and uvr5 ui, check: #📰│dev-updates message

[daring granite]

hi, i also have issues with delay- would appreciate the help!

is there a tutorial video for that?

[low shard]

Sure I can help!
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?:
  • AI Covers
  • TTS
  • Roleplay in VC
  • Roleplay in Games
• what tutorial link are you using
• a screenshot of the program

[low shard]

nope, don't trust video tutorials, please reply to what I asked

[daring granite]

one sec

From task manager, it says my GPU is an intel iris xe (well, it says graphics card- so same thing i think)

my system is windows 11

i'm trying out voices for DnD, games and song covers

i used this link: https://www.youtube.com/watch?v=dZ_2HELnWJU

[low shard]

i used this link: https://www.youtube.com/watch?v=dZ_2HELnWJU
That tutorial is outdated asf, delete the folder, zip and uninstall vb audio cable from windows app settings

From task manager, it says my GPU is an intel iris xe (well, it says graphics card- so same thing i think)
that's integrated graphics, it's weak asf, it can't do anything related to ai locally, check if you got another gpu

i'm trying out voices for DnD, games and song covers
RVC = Retrieval-based-Voice-Conversion, the best Few Shots 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. There also updated forks with extra features like Applio.

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)

You need both realtime for roleplay in calls, and pre-recorded audios for ai covers right? you'd need 2 different programs

[daring granite]

oh. thanks so much.
i never ended up installing the audio cable so i think that is fine. which folder are you refering to?

no other gpu i'm afraid. and it's a laptop so it's soldered to the motherboard. I might have a pc i can borrow tho which i will ask for

mostly i'd like to work on the ai covers the first- so real time is not my main priority. thank you so much for the additional info. i downloaded a regular e-guy voice models but don't know if it will be able to sound alright if i were to raise my voice, or laugh or sing- since i cant test it out yet, do you mind just giving some info?

[low shard]

which folder are you refering to?
everything related to whatever you installed from video tuts

no other gpu i'm afraid. and it's a laptop so it's soldered to the motherboard. I might have a pc i can borrow tho which i will ask for
AI is intensive and complex, it needs a good pc gpu, which could you get?

[daring granite]

ill have to see re: gpu.
can you please direct me to a different instruction manual for installing voice mod? i pretty much only ever rely on youtube so this is news to me haha

[low shard]

we don't use voice mod here, it's just 3 random not ai voice effects for free lol

if you want to do mostly ai covers, there are different programs, but i gotta know the pc gpu to understand which to give you

[daring granite]

oh sorry. i meant voice changer client demo

ok, i will come back when i have a new pc

[simple ore]

fork DML will run on your iris xe

it will be terrible performance

[low shard]

huh? you said you wanted to do ai covers, its different programs

[daring granite]

is it? i don't need real time stuff really, so any application that will let me pre record in different voices would be great

[low shard]

since you dont have a good pc and want to do ai covers, you gotta use rvc on cloud

Train (make) RVC Models on cloud:

1. Prepare the Dataset
2. Setup RVC:
   Choose a cloud way to use RVC,

• Google Colabs (max 4 hours of daily T4 16gb gpu not granted for free, not much hours for training, but easy to use, there's a paid tier):
  • Applio (UI)
  • Mainline (U, END OF LIFE UPDATE)
• 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):
  • Applio (UI)
  • Mainline (UI, END OF LIFE UPDATE)
• 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)
  • Mainline (UI, No guide as of right now)

3. Be sure to know about the tensorboard

Google Colab = Easier but risk of getting disconnected
Kaggle = Harder but way more gpu time
If you are looking for the easiest way and for free, is using https://weights.com/ which ofc 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: Fastest 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

@stark basin This server is english only, and elaborate your help request

[daring granite]

NICE

[low shard]

let me know

[stark basin]

i do not arrived to download RVC on github. Error 404 everywhere. Could someone help me ? Thank you very much !

[daring granite]

thank you! what does fork DML do?

[low shard]

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?:
  • AI Covers
  • TTS
  • Roleplay in VC
  • Roleplay in Games
• what tutorial link are you using
• a screenshot of the program

[low shard]

it was related to an amd program, but it's not needed for ai covers

[simple ore]

they are asking for a voice changer, no?

[low shard]

nope, they want to do ai covers

they didnt understand that there's a difference between realtime voice changers and pre-recorded audios

[stark basin]

4090, windows11, i need a link to download RVC. Before, it was easy, now i don't find any link. Gemini advice me to come here, but i see nothing to download RVC.

[low shard]

What's your Operating System? What do you want to do? RVC doesn't mean realtime voice changer

[stark basin]

i want to create voice for animation. I need to copy voice. my operating system is windows 11

[low shard]

so, train an rvc voice model, then use it for pre-recorded audios right?

[stark basin]

right.

is there any link on this discord to download the last version of RVC ?

Or Gemini is wrong ?

[simple ore]

https://huggingface.co/IAHispano/Applio/resolve/main/Compiled/Windows/ApplioV3.2.9.zip

[low shard]

As you got a good PC, you can use RVC locally, you can choose between:

• Applio: The most suggested RVC Fork with some extra features like TTS, kinda faster and simpler but same quality tho
• Mainline: The original RVC

[stark basin]

thank you folks

[hallow thistle]

Google Gemini, like many other chatbots and even ChatGPT, won't gonna give you the exact best RVC you should use. They often rely on information possibly from search results on internet, which sometimes don't match to what you looked for. Here's the guide. https://docs.aihub.gg/rvc/local/applio/

Don't.

[low shard]

Please report scams to mods next time

[hallow thistle]

I was about to use the Modmail bot account, but thing went too fast, I couldn't follow up.

[viral mason]

this server really needs a bot to immadietly ban those scam mr beast people, they're way too common

I say that an another one shows up smh

[broken urchin]

hey i was wondering if i can run W okada deiteris fork with my GPU plugged in a 1x to 16x pcie raiser?

is that gonna work?

or will i lose a lot of performance

[true ravine]

is mmvc rmvpe worser

whats the best pitch extraction algorithm

[simple ore]

1x is pretty bad

[broken urchin]

will it work?

[simple ore]

yes, but probably not good

[broken urchin]

why do you say that

[simple ore]

1x is too slow when things are going between vram and ram

[broken urchin]

but still it should give good voice transformation right? i plan to have RTX 3050 in the 1x pcie slot and use it for that only

[patent trellis]

💻 Local Realtime RVC

Guides for Programs that use RVC Models in Realtime for Calls/Games

• Wokada Deiteris Fork

Most suggested WebUI with the best general support for many platforms. GUIDE

• 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

• Original Wokada

Not suggested nor maintained, older versions in youtube tuts are even way worse. GUIDE

• RVC GUI Mainline Realtime

Unavailable, the guide is outdated and the program is worse compared to the ones above, and much less updated

[latent kettle]

What is this?

[analog obsidian]

i was talking about another architecture, not rvc

in rvc to train from scratch u need 24 hours for the model to produce something "good"

ye just use pretrains

[broken urchin]

for me it takes like 40 - 50 hours to make an rvc voice models

[analog obsidian]

we are talking about training a model without a pretrain*

which is something you never want to do in rvc because even if you got 24 hours, the model will have different type of problems because the discriminator of rvc is quite bad

you already have one... the original pretrain

[low shard]

why would u even want that?

no one does that

[viral mason]

Use the original

[thorn sinew]

I am trying to run AI models on my laptops NPU I have setup ryzenAI and am trying to run a test model with miniforge but i cannot figure out how to set the path to the installation.
C:\Program Files\RyzenAI\1.5.1\quicktest>python quicktest.py
Traceback (most recent call last):
File "C:\Program Files\RyzenAI\1.5.1\quicktest\quicktest.py", line 28, in <module>
install_dir = os.environ['C:\ProgramFiles\RyzenAI']
File "C:\Users\Noah\miniforge3\envs\resnet_bf16\lib\os.py", line 679, in getitem
raise KeyError(key) from None
KeyError: 'C:\ProgramFiles\RyzenAI'
but in the tutorial im following it says
set RYZEN_AI_INSTALLATION_PATH = <path/to/RyzenAI/installation>
I have tried many variations for the path but all error out
I would greatly appreciate any help

[simple ore]

what NPU?

you f'd up install_dir = os.environ['C:\ProgramFiles\RyzenAI']

because you should be getting 'RYZEN_AI_INSTALLATION_PATH'

that is set in env variables RYZEN_AI_INSTALLATION_PATH = C:\ProgramFiles\RyzenAI

this way install_dir gets "C:\ProgramFiles\RyzenAI"

os.environ is a dictionary with environment variables

[thorn sinew]

the NPU is part of the Ryzen AI 370 HX CPU

in the python code the it says " install.dir = os.environ['RYZEN_AI_INSTALLATION_PATH']

the command i have been doign is set RYZEN_AI_INSTALLATION_PATH = C:\Program*Files\RyzenAI\1.5.1

I have been trying to set the ryzen path many times. how am i screwing it up? i have tried running the program along with changing the env variable.
set RYZEN_AI_INSTALLATION_PATH=C:\ProgramFiles\RyzenAI && python quicktest.py

[low shard]

alright if u say so

i mean if you're using wasapi you could try flexasio, but it's more complex though

Ohh, I see, nvm then

[simple ore]

open environment variables

set command only works temporarily

[thorn sinew]

how do i open enviorment variables?

I got it to figure out the filepath but now its saying that it cant find the test_model.onnx

I used

C:\Program Files\RyzenAI\1.5.1\quicktest>set RYZEN_AI_INSTALLATION_PATH=C:\ProgramFiles\RyzenAI\1.5.1

the file is there but it cant find it saying it doesnt exist

[patent trellis]

💻 Local Realtime RVC

Guides for Programs that use RVC Models in Realtime for Calls/Games

• Wokada Deiteris Fork

Most suggested WebUI with the best general support for many platforms. GUIDE

• 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

• Original Wokada

Not suggested nor maintained, older versions in youtube tuts are even way worse. GUIDE

• RVC GUI Mainline Realtime

Unavailable, the guide is outdated and the program is worse compared to the ones above, and much less updated

[thorn sinew]

i got it working python needed a delay so it didnt trip over itself

[simple ore]

not really, it just need to open a new cmd to get udpated env variables

[low shard]

please elaborate and show a screenshot

[uncut berry]

how to make your own model

[low shard]

tell your pc gpu and operating system, i'm guessing you're talking about RVC sts voice models

[uncut berry]

how to make your own voice model with a rtx 3060ti on windows 10

how to make your own voice model with a rtx 3060ti on windows 10

[low shard]

What are you trying to do? roleplay in games? roleplay in vc? or e girl trolling/catfishing?

[low shard]

As you got a good PC, you can use RVC locally, you can choose between:

• Applio: The most suggested RVC Fork with some extra features like TTS, kinda faster and simpler but same quality tho
• Mainline: The original RVC

[earnest forge]

Applio UI still not familiar to me...

[low shard]

wdym? are you comparing to you being used to rvcdisconnected?

[earnest forge]

Compared to the old "WebUI" RVC that lets you train voices... one with the blue interface?

otherwise known as this

both got same quality tho you right

[simple ore]

blue rvc gui is outdated realtime voice changer

[low shard]

those are 2 different things

the blue rvc gui go-realtime is realtime voice changer for calls

the other one is apart of the same software, but it's for pre-recorded audios

[gritty cargo]

Ilaria is no longer useful, do you have any similar pages that are easy to use?

[simple ore]

btw, if it is gfx1151 shaders, there's a proper window pytorch

[normal drift]

Anyone knows what AI tool rn can help me do this ? I input an image, and the AI gives output image modifying the input according to my prompt while keeping character consistency. For example I input image of my OC, and prompt it for side view or view from back or top. That or changing the OC's hairstyle, outfit, age, etc. Ofc I'm looking for free options on Colab or HF Space and not the paywalled ones... thnx in advance for anyone helping 🙏

Iirc 2 years ago I used to come across a HF Space that does that but it was just for character portrait I think... but the consistency is really good. I forgot its name and can't find it back again :' (

[whole pecan]

im trying to use the voice changer and its instantly terminating the program

loop stop no error
vcclient is terminating...
vcclient is terminated.[18000]
native client is terminated.

[serene radish]

is there a recomended vid to watch for setting and downlaoding okada

please guys i have been trying for 4 hours

[latent kettle]

-realtime

[patent trellis]

💻 Local Realtime RVC

Guides for Programs that use RVC Models in Realtime for Calls/Games

• Wokada Deiteris Fork

Most suggested WebUI with the best general support for many platforms. GUIDE

• 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

• Original Wokada

Not suggested nor maintained, older versions in youtube tuts are even way worse. GUIDE

• RVC GUI Mainline Realtime

Unavailable, the guide is outdated and the program is worse compared to the ones above, and much less updated

[digital bear]

is vonovox better than the wokada fork

[toxic thunder]

is there something wrong with my setup? The voice i hear is just my own

[digital bear]

turn off pashroughh

[latent kettle]

!howtoask

[patent trellis]

How To Troubleshoot

__**GIVE CONTEXT.**__ 📝

• Don't simply mention your issue like "my rvc is not working".
• Describe your PC GPU Name, Operating System, the Guide and Step you are on, what you're trying to do, the Program you're using, a screenshot, etc.
• The more context, the better.

__**BE POLITE.**__ <:matsuripray:1159685390156967936>

• Don't be desperate. You can ping a Helper, but if they ignore, they aren't available/don't know the answer.
• It's okay if you're frustrated, but don't take it into this server.
• Don't DM without prior consent.

__**BE PRODUCTIVE.**__ 🤝

• Don't ask for every little instruction. Put your own effort & test things by yourself.
• Don't ask to ask.
• Check if your answer is a Google search away/on our guides website.

If you've changed your mind about your message, feel free to delete/edit it.

[dull orchid]

Is there a place where i can download AI generated videos ?

Not create them myself since you always have to pay for them sadly

Or does anyone know a good free ai video generator ?

[simple ore]

do you have a really beefy PC?

16GB VRAM, 48GB RAM?

[quiet axle]

um guys for some reason my voice changer doesnt work anymore. Yesterday was okay?

oh god nvm its fuckin chrome

[dull orchid]

Not that high end sadly, i have a RTX 3060 TI 8GB and 32GB Ram

Can i do something with this ?

[simple ore]

it is not gonna be fun

[dull orchid]

Ohh 🙁

Will it be better if i will upgrade to 64GB ram ?

Or it depends mostly on Vram

[simple ore]

you can run quantized models with 8GB.. but the quality noticeably drops

[dull orchid]

Mhhh what local program are we talking about btw ?

[simple ore]

comfyui, there are video workflows for quantized models

framepack standalone

sd.next (has much more, but very good quantization and offloading options)

[dull orchid]

Alright thanks, will my generation time be insane long with my setup 😮 ?

[simple ore]

pretty long

[low shard]

check #📰│dev-updates

[low shard]

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?:
  • AI Covers
  • TTS
• E girl trolling/catfishing
• Roleplay in VC
• Roleplay in Games
• what tutorial link are you using / a screenshot of the program

[low shard]

dont trust any yt tut for ai voice changer, they are all old

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?:
  • AI Covers
  • TTS
  • E Girl trolling/catfishing
  • Roleplay in VC
  • Roleplay in Games
• what tutorial link are you using / a screenshot of the program

[whole pecan]

3070 8gb
Windows 10 22h2
I’m using the voice changer for gta RP.
I’d send a screenshot but it force quits on launch. Worked yesterday but not today

[low shard]

they have similar quality and performance, the major difference is just that wokada deiteris fork has more platform support, vonovox got easy (some paid) voice effects and some other features

!give-media-perms 1h @whole pecan

[low shard]

send a screenshot of your program settings

[whole pecan]

Well I start the .bat file, tried both http and https, as well as main.exe. All it really shows is the text here

That’s the only anomaly that I get using the program

[low shard]

extra 2.7
uncheck sup1

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: https://docs.aihub.gg/realtime-voice-changer/local/deiteris-w-okada-fork/#reduce-more-delay

are you trying to use wasapi or asio? you should use server mode only for that

[whole pecan]

If you want, I can record a short video displaying the entire process, but I’ve already pretty much described everything

[low shard]

@whole pecan don't suggest help for that user, start_http.bat is apart of the outdated original wokada

oh you're using that one?

lemme guess, you got vb audio cable too?

[whole pecan]

Yes

[low shard]

your setup is the one used 2 years ago basically lol

oyou got an over year old version of original wokada with worse performance and buggy

and vb audio cable creates issues on windows

delete the zip, folder, uninstall from windows app settings, and forget every settings they said in the video

[low shard]

-realtime

[patent trellis]

💻 Local Realtime RVC

Guides for Programs that use RVC Models in Realtime for Calls/Games

• Wokada Deiteris Fork

Most suggested WebUI with the best general support for many platforms. GUIDE

• 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

• Original Wokada

Not suggested nor maintained, older versions in youtube tuts are even way worse. GUIDE

• RVC GUI Mainline Realtime

Unavailable, the guide is outdated and the program is worse compared to the ones above, and much less updated

[low shard]

you can try either vonovox or wokada deiteris fork, please check their pros and cons in the guides

[whole pecan]

thank you so much. All i got was 1 yt tutorial and what my friend found like a year ago. thats as much knowledge as i had

ill get back to you (if you dont mind) if i find any issues

[low shard]

be sure to never trust yt tuts for those things, you can always check there instead

istg there's never an updated tutorial in 2 years

[whole pecan]

good to know. i have a 3070 and sometimes i had issues with the old program delaying like 2 seconds or even 3 while playing FiveM. Would the newer forks improve upon performance compared to the older program or is this an issue i'd have to optimize for?

[low shard]

wokada deiteris fork & vonovox help with performance, but remember to play every game at 1080p 60fps cap lowest graphics settings, realtime ai is intensive

[whole pecan]

oof, i play on 1440p at 120

alright guess ill see what i can do to limit myself

@low shard do you know how to priotitize performance for the AI first, and my game second?

[low shard]

by playing on lowest graphics, 1080p 60 fps cap lol

[whole pecan]

i moreso meant somehow using a setting on windows or something but yeah thats another way

i got it working and HOLY CRAP its so much better than what i used before

https://discordapp.com/channels/1159260121998827560/1159290139609137264/1400076603811434536

[whole pecan]

follow this

are you using an Nvidia gpu?

on windows?

use vonovox

its an Okada fork

its better yes

[low shard]

Yep

That's outdated, are you trying to do e girl trolling/catfishing?

[whole pecan]

unrelated but do you guys ban catfishers or support it or? Just want to understand this server's opinion on that

[low shard]

It's literally illegal and leads to blackmail, I'd be more concerned that anyone supported It

[whole pecan]

ok was just wondering

[low shard]

@reef nexus that is outdated info about an outdated program, don't suggest it

[whole pecan]

I love you Nick

[low shard]

You need to elaborate the rest, there are thousands of possible causes that make a program not work

[low shard]

do you may need help with the settings btw?

[whole pecan]

I don’t think so. I haven’t looked into the app too much but if I do I’ll get back to you <3

Bro fell for the bait

[low shard]

I think long lol

[low shard]

I mean you could also try https://voyages.weights.com free tier, AI is expensive, you can't expect for unlimited free AI usage tho since it's running on a remote good server that costs up
What's your pc gpu?

[worldly terrace]

hi i need help, when i try to install okada, it doesnt show up when i run the exe file, and when i paste in http://127.0.0.1:18888/ into my browser it says i cant connect? Im using a 4070tis and installed the download nvidia on windows file in the guide.

[cunning stratus]

how do i find a link to create a rvc model on google collab

[low shard]

please also elaborate:

• the tutorial link
• what you want to do:
  • tts
  • ai covers
  • e girl trolling/catfishing
  • roleplay in vc
  • roleplay in games
• a screenshot of the issue

[low shard]

google colab is a cloud (remote good pc) platform with limited free time, it shouldn't be ur first option, and you shouldnt trust yt tuts
what's your pc gpu and operating system first?

[worldly terrace]

the one in #1159513888199540817 is the tut i used
i want to troll my friends
and idk what to screenshot because it just doesnt load, no error message, just doesnt load

[low shard]

i want to troll my friends
e girl trolling or like spongebob?

[worldly terrace]

also im unable to show screenshots i dont have the perms

[worldly terrace]

spongebob

lmao

[low shard]

!give-media-perms 1h @worldly terrace

can you show what happens when you try to open it?

[worldly terrace]

this is for the website one

[low shard]

you clicked the MMVCServerSIO?

[worldly terrace]

yea

[low shard]

you're talking about wokada deiteris fork b2332 im guesssing

show a screenshot of the CMD

[worldly terrace]

what

[worldly terrace]

what cmd

sorry im new im kinda slow

[low shard]

the terminal, the "black window with lines of code"

it opens when you open the program

did you close that?

[simple ore]

of text

[worldly terrace]

oh i dont get that

[simple ore]

they did 🙂

[worldly terrace]

it just closes as soon as it open

[low shard]

you shouldnt close it

[worldly terrace]

i dont

it did by itself

[low shard]

please show a screnrecording of you trying to open it

[worldly terrace]

ok

[simple ore]

open cmd.exe in the folder with voice changer

manually run it from command line so it does not close

then you'll see the problem

[worldly terrace]

which one is cmd .exe

[simple ore]

click the path, then type cmd.exe and press enter

just an example

[worldly terrace]

it says this folder is empty

[simple ore]

screenshot

[simple ore]

why you're searching

instead of typing cmd.exe in this space

[worldly terrace]

ahh ok

ok i did it now what

[simple ore]

with cmd open, type mm, tab, (it will add the rest of the name), enter

[worldly terrace]

done

do i take a screenshot of it?

[simple ore]

yes

[hallow thistle]

Yes, taking a screenshot is important.

[simple ore]

if it stopped and you see the command line prompt again

[worldly terrace]

hope this doesnt leak my ip address

[low shard]

weird? seems like a broken installation, could you please retry reinstalling but with anti virus on if you have any?

[worldly terrace]

dont have any anti virus on

ill try reintalling

[low shard]

it wouldn't leak your ip address, even the local one to open the application is a Local one lol (meaning everyone has the same ip and not conntected to the internet outside)

[worldly terrace]

reinstalled it same problem

[normal drift]

Well, I already shared info about my specs before, my 4GB RAM laptop doesn't even have a GPU, just "Intel UHD Graphics"

[low shard]

that fast? you downloaded the zip, extracted it with either winrar or 7zip, then clicked the .exe and it downloaded all internal files?

[worldly terrace]

yup

pretty fast wifi

[low shard]

yeah your cooked, maybe try Voyages

[worldly terrace]

lel

ookla says 300megabits/s is my wifi speed

but anyways i still have the same problem, so is it js broken for me?

[low shard]

@simple ore you ever seen this issue before?

[low shard]

try updating your windows, gpu drivers, and reinstalling meanwhile, I'm also asking other staffers if they ever seen this issue before, bc it's the first time

[simple ore]

did you unzip using windows?

try unzipping into C:\voice_changer\

the path may be too long if you have it in C:\users\users.... \desktop\

[worldly terrace]

alright thanks

[simple ore]

also using winrar or winzip or 7-zip is better than windows, it is just shitty at working with multiple files

[low shard]

did it work?

i mean u could also try vonovox which has similar quality and performance, since you're on windows with an nvidia gpu, tho it's weird

[viral mason]

I feel like all computers should come with both winrar and 7-zip installed

[low shard]

nah, microsoft edge

[swift fable]

@low shard

[viral mason]

yuck

[vapid drift]

I'm trying to get an LLM to take a number of reports from labcorp in pdf format and convert all the results into a csv. I'm not sure why it is not using all results. could it be that the default context window is too small for them all?

[timid dune]

@low shard

[viral mason]

there are too many freaks here for okada

[low shard]

?

@shy current we dont allow selling services here

[low shard]

what?

[vapid drift]

increasing num_ctx in openwebui fixed it

[swift fable]

im looking to do voice lines for cutscenes

what would b the best option foir that

[timid dune]

what's the updated version of the MMVCServerSIO_win_onnxgpu-cuda_v.1.5.3.18a? i have the year old version

[low shard]

what's your pc gpu? operating system? do you mean like use models on pre-recorded audios?

[swift fable]

windows 10 5070
on models

[timid dune]

5070 on windows 10 😭

[low shard]

that's outdated, delete zip folder and uninstall from windows app settings vb audio cable,

what's your pc gpu, operating system? what do you want to do?:

• AI Covers
• TTS
• Roleplay in VC
• Roleplay in Games

[low shard]

@timid dune I need to know because there are different programs for different things, RVC doesn't mean realtime voice changer lol, it means Retrieval-based-Voice-Conversion

[timid dune]

3060, windows 10 and just roleplay with friends

[low shard]

alright, delete everything you had before

-realtime

[patent trellis]

💻 Local Realtime RVC

Guides for Programs that use RVC Models in Realtime for Calls/Games

• Wokada Deiteris Fork

Most suggested WebUI with the best general support for many platforms. GUIDE

• 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

• Original Wokada

Not suggested nor maintained, older versions in youtube tuts are even way worse. GUIDE

• RVC GUI Mainline Realtime

Unavailable, the guide is outdated and the program is worse compared to the ones above, and much less updated

[low shard]

in your caseread either wokada deiteris fork or vonovox, they have both pros and cons

[low shard]

so, using models on pre-recorded audios, right?

[timid dune]

what do u recommend?

[low shard]

they both have similar quality and performance, the major difference is the UI and vonovox got voice effects (but some are paid)

no need for drama here, catfishing isn't allowed ofc

[sharp scarab]

Anyone have a working link for the Morrigan RVC model? All five versions I found are broken (Save interaction fails, Mega links dead). Would really appreciate a reupload

[timid dune]

i downloaded the

[timid dune]

"download nvidia on windows" version for

https://docs.aihub.gg/realtime-voice-changer/local/deiteris-w-okada-fork/

[low shard]

You can search rvc ai voice models at:

• https://discord.com/channels/1159260121998827560/1175430844685484042
• In https://discord.com/channels/1159260121998827560/1163592055830880266 , Do /find with @earnest musk
• 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
• Ask a free request in https://discord.com/channels/1159260121998827560/1159289738314919936
• Be aware that we don't allow any paid comms

[earnest musk]

:wave: @low shard, How can I help?

Available Commands:
• @weights find <query> or /find <query> - Search for RVC Voice Models

[low shard]

alr

[timid dune]

do i extract

and do the same thing

as the old version

[low shard]

no it's not the same, ecxtract it, then read the rest of the guide

you got vac lite and uninstalled vb audio cable from windows app settings right?

[timid dune]

ya

[idle osprey]

why u need vac lite

[timid dune]

yea idk what vac lite is

[idle osprey]

vac lite just what soundboarders use

[timid dune]

i uninstalled vb audio cable

tho

[idle osprey]

that is vac lite but not lite

i think vac lite give you less errors

[low shard]

vac lite is better

many users with vb audio cable reported issues on windows, such as crackling and randomly stopping to work

[low shard]

it's written

[idle osprey]

why not ur headphone as output device

why d o you need to use a differnet ovice in games or something bro

[low shard]

A VAC (Virtual Audio Cable) makes a fake audio device, used to re-route the audio of different programs

In Wokada context, it's used to get the output of wokada as the input in other programs

Putting the output to your headphones, would mean you only can hear it lmao

did you use a youtube tutorial?

those are all old

[idle osprey]

u talking to me

[low shard]

yeah

[idle osprey]

no i install it myself

[low shard]

do you may want me to check your settings? you can share a screenshot of the entire program, I feel like you're using the original wokada with vb audio cable

[idle osprey]

s

ur suposed to use this for fun not in games

wait u can troll bro?

[low shard]

you do need a Virtual Audio Cable to make the realtime voice changer in any other programs such as discord calls or games, without it, only you can hear urself

i dont know what you're talking about?

[idle osprey]

why should i use it in discord calls

[timid dune]

nick u italian?

[low shard]

if you're looking to only hear yourself, then you don't have to

[low shard]

yeah ?

[idle osprey]

ok is my settings correct tell me

[low shard]

!give-media-perms 1h @idle osprey

[low shard]

you can send them now

[timid dune]

instead of app

[idle osprey]

yes

[low shard]

yes https://docs.aihub.gg/realtime-voice-changer/local/deiteris-w-okada-fork/#why-does-it-run-in-a-browser-and-not-its-own-window

[low shard]

can you share a screenshot of ther entire program without cropping out anything? and advanced settings too?

[idle osprey]

ok

wait give me seconds

[low shard]

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?:
  • AI Covers
  • TTS
  • E Girl trolling/catfishing
  • Roleplay in VC
  • Roleplay in Games
• what tutorial link are you using / a screenshot of the program

[idle osprey]

o7

[timid dune]

rip

[low shard]

crossfade lenght: 0.15
force fp32 mode: on
disable jit compilation: on

[low shard]

you just need to install the VAC Lite from the guide and set line 1 as output, then if you want to use it in like discord set the discord input to line 1

[idle osprey]

no need

[low shard]

this way nobody, not even yourself will hear you because there's no output, you sure ?

did you already click start? need some help?

[idle osprey]

i put my headphones then

[low shard]

you will be able to hear urself, but won't work on anything else

are you trying to maybe use it for pre-recorded audios instead?

[idle osprey]

yes

no probably

its a cool program

[low shard]

because like, there's a program for that, this is meant for realtime voice changing in calls

[idle osprey]

i no imporstinato

imperstaion

imperstation

Just no

ok so these settings will make my model sound better?

[timid dune]

i keep blue screening :(

[idle osprey]

it ur pc or graphics cardd

[timid dune]

i have a 3060 tho

[idle osprey]

oh

turn off background apps

and get razer cortex

[low shard]

it will help slightly for performance and stability/quality

[low shard]

what did u do?

update your windows, gpu drivers, be sure your gpu is fine

[idle osprey]

does it capture screaming

or models have to be trained for that

[low shard]

it's an RVC limitation, don't expect models to scream or laugh realistically

it's like this since 2023

[idle osprey]

so if it does that

somehow

my pc would fry

[low shard]

no it just sounds bad

[idle osprey]

what it would sound good

nevermind

[timid dune]

how do i adjust it wont let me

[low shard]

click stop first, then you can change the settings

[timid dune]

o

[idle osprey]

when i switch between models it switches fast

[timid dune]

like

[idle osprey]

is that onmrla

[timid dune]

nvm

[idle osprey]

@low shard whats the best chunkextra settings

[low shard]

https://docs.aihub.gg/realtime-voice-changer/local/deiteris-w-okada-fork/#known-working-settings-for-chunk-and-extra

[timid dune]

@low shard

is crepe tiny or crepe full better

[low shard]

none, rmvpe for best quality and robustness, either fcpe if you want to sacrifice some quality for less delay

forget every info off yt tuts

want to share a screenshot of ur full program and advanced settings? I can help

[timid dune]

chatgpt that said to 😭

[low shard]

chatgpt doesn't know about RVC or W-okada 😭

[timid dune]

ohh yeah rmpve sounds wayy better

[low shard]

want me to check all ur settings ?

[timid dune]

no its fine thanks

@low shard also when i speak sometimes like the last word is cut out

how do i fix that

[low shard]

it's related to bad settings, please show a screenshot of ur full program so i can see the issue

[delicate cradle]

I thought f0-ers don't change quality? All the f0 does is get the pitch. Isn't the difference between RMVPE and FCPE that one is more robust and the other is faster?

[analog obsidian]

yep they don't change the quality

they only track pitch, nothing else

[delicate cradle]

Then why did Nick say they do? Misconception?

[nocturne patrol]

can anyone help me

[analog obsidian]

misconception yes lol
fcpe is just less accurate

[low shard]

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?:
  • AI Covers
  • TTS
  • e girl trolling/catfishing
  • Roleplay in VC
  • Roleplay in Games
• what tutorial link are you using / a screenshot of the program

[nocturne patrol]

i don’t think my virtual audio cable is working i have a nivdia RTX 1070 🙁

[delicate cradle]

Thanks for the confirmation 😃

[nocturne patrol]

i like testing and roleplaying alot

[low shard]

Sorry I didn't mean quality, I meant robustness and performance

[low shard]

can you share all the info i asked?

[nocturne patrol]

some of the r models aren’t compatible with my voice that’s what i mean by testing

yes i roleplay and test model

only in vc though i’m in a bunch of rp servers

[nocturne patrol]

yes i just did

i’m not using a tutorial i think it’s my audio cable, whenever i try to talk with the voice changer on it doesn’t work but when i use my actual mircophone it starts to work, i tried everything

[low shard]

which operating system? can you share a screenshot of the whole program settings?

[nocturne patrol]

in my case i tried to restart the app i restarted my computer and i make sure my cables were in the correct spots

[low shard]

!give-media-perms 1h @nocturne patrol

[nocturne patrol]

yes i can

@low shard

[low shard]

set extra to 2.0

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: https://docs.aihub.gg/realtime-voice-changer/local/deiteris-w-okada-fork/#reduce-more-delay

[nocturne patrol]

do you think i set the chunk to a appropriate ms

im not really good with the advanced ways

it still doesnt work even after setting extra to 2.0

[low shard]

you need to set it a bit higher than the perf value

[low shard]

still getting cutoff at the end of ur phrase?

have u tried other models?

[nocturne patrol]

yes i tried one other model the same thing occured

[low shard]

it would be best you try the ones i suggested

can you show a full screenshot of everything? the top too and advanced settings?

[low shard]

idk who wrote it but there are some wrong info in the docs

[nocturne patrol]

no i just can’t talk

with the voice changer

[low shard]

did you set line 1 as input in discord or whatever and then click start?

[nocturne patrol]

i’m not experienced with this type of stuff can you help me through it

i’m not experienced with this type of stuff can you help me through it

[nocturne patrol]

yes

[low shard]

you just need to set them as i said lol

[low shard]

did you also do https://docs.aihub.gg/realtime-voice-changer/local/deiteris-w-okada-fork/#virtual-audio-cable

[nocturne patrol]

ohh

[nocturne patrol]

okay i’ll try

[low shard]

did u do that specific step i sent

not doing it can fuck up ur whole audio system

uninstall vb audio cable, get vac lite, then do as i said

[timid dune]

oh

i thought vb cable

[low shard]

I need to check the full program and advanced settings too

[timid dune]

and vac lite were just the same thing

[low shard]

no, vb audio cable brings issues on windows

your settings are wrong

please show a full screenshot of the entire program and advanced settings 😭

[timid dune]

OML the entire program and settings isnt an issue anymore

i just need to output on roblox

[low shard]

your settings are also wrong there, you shouldn't use sup1, and i need to check also the settings at the top

and you also should put extra to 2.7

there are other settings too, but i can't see them if you don't show me them 😭

[timid dune]

first or second

[low shard]

none

https://docs.aihub.gg/realtime-voice-changer/local/deiteris-w-okada-fork/#virtual-audio-cable read the guide, get it from there

[low shard]

bad settings are apart of the problem btw

[timid dune]

ok i uninstalled vb do i have to restart or can i do that after

[nocturne patrol]

it didn't work i turned on force fp32 and i disabled JIT compilation

bro u gotta double click it and choose model pth

i dont mean to be like a mod i need help w my stuff aswell

[low shard]

I feel like you're using an old program and came from yt tuts

[low shard]

you can but shouldn't have to

[nocturne patrol]

i dont get why its not working

[low shard]

what's the issue now?

[nocturne patrol]

i turned on fp32 and d disabled the JIT compilation and it still does not work

[timid dune]

ok is this right now

[low shard]

please elaborate everything I asked

[low shard]

what doesn't work? elaborate

[nocturne patrol]

i cant talk with the voice changer in discord settings

[low shard]

yes, but you didn't show the whole settings, some settings might be wrong as I pointed out

[low shard]

show a screenshot of the wokada and discord settings again

[nocturne patrol]

also doesnt work in the actual app when i put output to speakers

alright

[low shard]

be also sure you give it microphone perms in the browser

[nocturne patrol]

i did but heres the settings

[low shard]

i feel like you missed this step, can u check?

[nocturne patrol]

i have the thing installed already

want me to reinstall it

[low shard]

it's not related to installing it, it's after you install it

[nocturne patrol]

okay so what do i do i put it back to my actual mircophone and my headphones?

ik it says usual device but im using the voice changer more than my actual mircophone tbh

[low shard]

what are you trying to do roleplay or e girl trolling? can you also show a screenshot?

[nocturne patrol]

its roleplaying

[nocturne patrol]

yes

[timid dune]

also if i download models how do i find the right settings for them

cuz i downloaded some model but it didnt like

[low shard]

show a screenshot of the audio device settings

[timid dune]

automatically set it

[low shard]

force fp32 mode: on
disable jit compilation: on

are u sure u did this tep?

[timid dune]

yes

i did it like 2 mins ago

[low shard]

uninstall vb audio cable from windows app settings, then restart

[low shard]

can i see a screenshot?

[timid dune]

ok

line 1 just says ready

[nocturne patrol]

okay

[low shard]

can you try restarting and see if it works?

[nocturne patrol]

the one im actually using right?

[low shard]

vb audio cable is bad, you need to use vac lite, so uninstall vb audio cable

[nocturne patrol]

okay

[timid dune]

@low shard

ok so i restarted

now just go into roblox

and use line 1

right

as inout

input

[low shard]

yes

[nocturne patrol]

i deleted it

what do i do now?

[timid dune]

@low shard

why ping so high

[nocturne patrol]

@low shard

[low shard]

restart ur pc, and retry now

[low shard]

set chunk higher than perf

set chunk to like 100

[nocturne patrol]

wdym retry i deleted it i couldnt uninstall

ill just reinstall nvm

[low shard]

retry using the program

[timid dune]

thx Nick

NICK

[low shard]

is it all solved now?

[timid dune]

i guess

nick u better be getting paid to do ts

[nocturne patrol]

i cant use pictures anymore

[low shard]

alr then

[nocturne patrol]

wdym retry it

i redownloaded it and i have to set it up again and i forgot how

@low shard

[low shard]

forgot what? it's all written in the guide

[nocturne patrol]

i forgot how to set up the audio cable

i dont know where the guide is

[low shard]

https://docs.aihub.gg/realtime-voice-changer/local/deiteris-w-okada-fork/#virtual-audio-cable

[nocturne patrol]

okay i installed it

it doesnt tell me what to do next

@low shard

[low shard]

did you read the whole guide?

[nocturne patrol]

yes and i dont understand what they mean

do i keep my audio devices as is or do i change it to the audio cable

[low shard]

you need to set the default audio device to your usual ones

[nocturne patrol]

what abt my playback and recording

[low shard]

yeah, both should be ur usual devices

[nocturne patrol]

okay

[lusty ice]

i have virtual audio cable for ai voice but discord wouldnt detect the audio no matter what

can someone help

[nocturne patrol]

okay how to i put the audio cable on discord now

[low shard]

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?:
  • AI Covers
  • TTS
  • E girl trolling/catfishing
  • Roleplay in VC
  • Roleplay in Games
• what tutorial link are you using / a screenshot of the program

[nocturne patrol]

okay it works now

thanks nick

[low shard]

great, is it solved?

[nocturne patrol]

yes thank you

[low shard]

yw

[hazy eagle]

hey which should i install on my nvidia driver

studio or gaming?

[low shard]

for what u gonna do?

[fair hull]

were do i download :

[hazy eagle]

i play league of legends and gameloop(emulator) and voice chat on discord and i use deiteris w okada fork

[fair hull]

uhhh were do i download the stuff

[low shard]

This is a General AI Server, AI has many fields, so we can't know your issue

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?:
  • AI Covers
  • TTS
  • E Girl Trolling/catfishing
  • Roleplay in VC
  • Roleplay in Games
• what tutorial link are you using / a screenshot of the program

[low shard]

i mean u can just use the gaming one

[fair hull]

NVIDIA GEFORCE RTX 2050 AMD RADEON TM GRAPHICS

roleplay in games

[hazy eagle]

do you guys have recommended nvidia settings for this?

[low shard]

https://docs.aihub.gg/realtime-voice-changer/local/deiteris-w-okada-fork/#known-working-settings-for-chunk-and-extra

[low shard]

so, like spongebob in games right? or e girl trolling?

[fair hull]

in games

[low shard]

yeah, e girl in games or characters like spongebob?

[fair hull]

in game rp

well

im playing hl2rp and am using combine voice changers

[low shard]

great then

[low shard]

-realtime

[patent trellis]

💻 Local Realtime RVC

Guides for Programs that use RVC Models in Realtime for Calls/Games

• Wokada Deiteris Fork

Most suggested WebUI with the best general support for many platforms. GUIDE

• 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

• Original Wokada

Not suggested nor maintained, older versions in youtube tuts are even way worse. GUIDE

• RVC GUI Mainline Realtime

Unavailable, the guide is outdated and the program is worse compared to the ones above, and much less updated

[low shard]

you can use either vonovox or wokada deiteris fork

please read their cons and pros

[fair hull]

which is the best

[low shard]

both have similar quality and performance, please read their pros and cons

[fair hull]

am gonna go with W-Okada Deiteris Fork

okay so i downloaded this uh voice-changer-master what do i do with it now

and now i downloaded vcclient_win_std_2.0.78-beta

@low shard is vcclient_win_std_2.0.78-beta good?

[low shard]

no, it's original wokada, do not use yt tuts, delete everything, follow only the guide i sent

[viral mason]

imagine using original wokada in the big 25

[fair hull]

the guide is confusing me

[viral mason]

you download okada or vonovox, download vac lite, install vac lite then restart your pc, start up either voice changer u want and then find the best settings for your computer

or if you use phone you die

[pastel oak]

vac lite doesnt necessarily need pc restart

[fair hull]

send me the download link to vonovox pls

[low shard]

did you read it? what's wrong in it?

[fair hull]

its very confusing me

its legit making my braincells kill itself

[low shard]

AI is intensive and complex, it isn't a 1 click program

what part is confusing u?

[viral mason]

it's more of a just in case thing

[fair hull]

all

[pastel oak]

he didnt open the guide, he said he opened it then started talking about og wokada

[fair hull]

i do have vb downloaded

[low shard]

please, read it carefully and let me know after what u didn't understand, i can't understand if u just say everything

[viral mason]

loser left

[fair hull]

yeah this guide is so confusing

[whole pecan]

Just helped someone with the voice changer entirely by myself

You can officially label me as a professional voice changer support guy

[low shard]

do you need help?

[low shard]

which part can i help you with?

[fair hull]

every

[low shard]

you got an nvidia rtx 2050 and are on wqindows 11, have you tried getting VAC Lite first?

[fair hull]

no

were i get that

[low shard]

from https://docs.aihub.gg/realtime-voice-changer/local/deiteris-w-okada-fork/#virtual-audio-cable

[fair hull]

alr what i do after now?

[low shard]

did u already download it, extract it, run setup64.exe, click yes and set your usual audio devices?

[fair hull]

yes

i just need to know what i need to download for the voicechangers

[low shard]

you sure you set your usual devices?

[fair hull]

yep

[low shard]

now download and extract https://docs.aihub.gg/realtime-voice-changer/local/deiteris-w-okada-fork/#download-nvidia-on-windows

[fair hull]

wait

i have to download nvidia?

[low shard]

that's the wokada deiteris fork nvidia windows version

[violet jolt]

Hi - I started using the w-okada voice changer with vb cable and while sound works fine everywhere it is not working on instagram audio message. Has anyone had this issue and any ideas to make it work?

[whole pecan]

if your browser wont allow you to set a custom microphone, i dont think it will work

btw, i understand the voice changer is AI based, but i saw a troll vide on youtube and his voice changer sounded perfectly

does that have to do with the voice model im using?

(thats not the purpose im using it for dw)

also is there any way to monitor the voice changer while using it on discord or something like that?

[vapid gust]

how do i voice isolate

now

[whole pecan]

using trial and error, yes

that was the reason

[vapid gust]

uvr5 huggingface not work

what do i do

[low shard]

vb audio cable is bad

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?:
  • AI Covers
  • TTS
  • E Girl Trolling/catfishing
  • Roleplay in VC
  • Roleplay in Games
• what tutorial link are you using / a screenshot of the program

[low shard]

yes, check #📰│dev-updates

[low shard]

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?:
  • AI Covers
  • TTS
  • E Girl Trolling/catfishing
  • Roleplay in VC
  • Roleplay in Games
• what tutorial link are you using / a screenshot of the program

[subtle cedar]

-Colab

[patent trellis]

📒 Google Colab Notebooks

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.

• **Applio**

by IA Hispano
Google Colab

• **RVC Mainline**

by Hina
Google Colab

• **UVR5 NO UI**

by Eddy
Google Colab

• **UVR5 UI**

by Eddy
Google Colab

• **Wokada Deiteris Fork**

by Deiteris & Hina
Google Colab

• **Hina's Modified Original Wokada**

Google Colab

• **RVC-AI-Cover-Maker-WebUI**

by Shiro & Eddy
Google Colab

• **FaceFusion UI**

by Nick088
Google Colab

• **FaceFusion NO UI**

by Nick088
Google Colab

• **Music Source Separation Training (Inference)**

by Jarredou & Makidanye
Google Colab

[subtle cedar]

so no more easyGUI again ?😭

Also no more RVC Disconnected?

I think these current Colabs are hard 😕 and I will train models on Weights instead since another easiest way to train voice models 'Astra Labs' is gonna shut down soon

also I will train on Replay too when I have a laptop

[latent kettle]

@simple ore can we use applio on a rental GPU if yes how ?

[simple ore]

on colab or where?

[brittle wing]

on a rental gpu like vast.ai

a cloud gpu i think it's called more specifically

[simple ore]

@analog obsidian knows

should be pretty straightforward

[brittle wing]

aight bet

[simple ore]

I dont know what they provide.. a docker container or vps

[brittle wing]

yeah that's my same question

[analog obsidian]

yea applio works with cloud gpu
so far i tested rtx a5000, 5090, 4090, 3090

a40 works too

[brittle wing]

im tryna rent a 4090 but i don't know how vast.ai works

i think its too good to be true lol

its this website

[simple ore]

ask them in that chat "I want to train a pytorch model using a rented GPU. I'll need to install a python application and upload my training set. Is there a documentation explaining how can I do that?"

[brittle wing]

bet

[placid holly]

I Have Question:
i test some setting for my Delay, while testing and listening with "OBS & Discord" it took 0.8s for the voice out (By watch the Audacity time/manually)
but then i tried using Monitor in W-Okada to hear the Voice, it take 0.4s for the voice out (still use Audacity)

now my Question is, if i talk in game/discord, what is the delay it actually use or other people hear?

[rose sequoia]

My computer doesnt have an gpu i just checked that as im just noticing that my pc is old i dont know why it doesnt have an gpu it only has an cpu but im trying to RVC with a goku voice but i cant launch it

My processor is Intel(R) Core(TM) i7-3770 CPU @ 3.40GHz 3.40 GHz

<@&1159293204038955078>

[placid holly]

not a helper, but that spec not able to run it to be honest
well it better use the cloud version

[rose sequoia]

can you assist me through out that way?

first time using rvc

[rose sequoia]

@placid holly

?

[placid holly]

sorry i can't help, dont have experience on cloud one
better wait for the Helper

[rose sequoia]

Oh ok thank you

[dire crystal]

How can I be generating a video in #🌇│ai-videos ?

(I'm Brazilian and I'm using Google Translate)

[slate zodiac]

is there a way to stop the ai voice from cracking so much?

[whole pecan]

Can someone help? Im using the vonovox fork and i want to monitor my voice while still using the voice changer

basically have 2 outputs

currently i only have 1 input and 1 output

[serene radish]

guys what cable should i use bc vb cable is not working

[viral mason]

Idk exactly what you're trying to do but I could probably help u tomorrow bc I'm in bed ready to snooze

[whole pecan]

its alright i just used a discord alt

[worldly terrace]

no, it didnt idk why its not working, is it because my cpu? Its a 7800x3d which i think is pretty good but idk maybe because of that?

[dry kite]

how to install on phone

[rancid pine]

Which local RVC is the best and an all-rounder?

[whole pecan]

It does

I used an alt to listen to myself

[quasi condor]

u know there's an option on w okada called passthrough

or monitor so u could hear yourself

did u even read the guide for the voice changer?

Oh jeez

youtube tutorials for w okada are outdated

type -realtime on bot commands and click the first guide

[whole pecan]

I’m using a fork

[quasi condor]

ah

[whole pecan]

As I’ve described

[quasi condor]

what fork of the voice changer are u using o- o

[whole pecan]

Vonovox

[quasi condor]

oh o - o

vonovox

that's what i said not vb cable 😔

[quasi condor]

turn off monitor

[pastel oak]

Maybe "playback device" is activated in sound settings. Go to your sound settings, Recording tab, search for the vb cable / Line 1, right click Properties and then see if hearing yourself/feedback/playback (whatever it may be called in your language) is activated or not

[pastel oak]

I believe there is no monitor function. You can refer to my message above that I replied to mengy._ , if you activate that button you can hear yourself

[whole pecan]

oh peak

idk which is easier lol, discord or that

im prolly ognna use discord, naviating to that prolly will be more difficult

[dapper cobalt]

The voice isnt working on dc it doesnt detect any input what do i do?

[pastel oak]

Screenshot your voice changer and discord input/output you selected

[dapper cobalt]

i got no image perms

@pastel oak DMs

[pastel oak]

Youre using an outdated version + the VB Cable you have doesnt work on your pc

Delete voice changer + uninstall vb cable

download this virtual cable:
https://docs.aihub.gg/realtime-voice-changer/local/deiteris-w-okada-fork/#virtual-audio-cable

download this voice changer
https://docs.aihub.gg/realtime-voice-changer/local/deiteris-w-okada-fork/#download-nvidia-on-windows

[dapper cobalt]

oh alr thanks

[hard gust]

Hey! What's the best zero-shot voice cloning model? not a TTS model, a voice to voice

[low shard]

there's cloud (remote good pc)
RVC = Retrieval-based-Voice-Conversion, the best Few Shots 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. There also updated forks with extra features like Applio.

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)

which do you need? what do you want to do?

[low shard]

you don't, it's only for sharing them

[low shard]

This is a General AI Server, AI has many fields, so we can't know your issue

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?:
  • AI Covers
  • TTS
  • E Girl Trolling/catfishing
  • Roleplay in VC
  • Roleplay in Games
• what tutorial link are you using / a screenshot of the program

[low shard]

vb audio cable is bad

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?:
  • AI Covers
  • TTS
  • E Girl Trolling/catfishing
  • Roleplay in VC
  • Roleplay in Games
• what tutorial link are you using / a screenshot of the program

[low shard]

try vonovox instead

[low shard]

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?:
  • AI Covers
  • TTS
  • E Girl Trolling/catfishing
  • Roleplay in VC
  • Roleplay in Games
• 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?:
  • AI Covers
  • TTS
  • E Girl Trolling/catfishing
  • Roleplay in VC
  • Roleplay in Games
• what tutorial link are you using / a screenshot of the program

[low shard]

that's STS, https://github.com/Plachtaa/seed-vc

[pastel oak]

F0 rmvpe
Chunk 200
Extra 2.7

[low shard]

you also got wokada deiteris fork b2332?

dont use the wokada off youtube

do you want me to check your settings maybe?

[low shard]

install what?

RVC = Retrieval-based-Voice-Conversion, the best Few Shots 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. There also updated forks with extra features like Applio.

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)

[rancid pine]

Well, what are the options for AI covers?

And their pros and cons, I mean

[low shard]

realtime voice changing with vb audio cable and wokada, and ai covers are 2 different programs