#🧬│ai-chat
1 messages · Page 312 of 1
What gpu do you have
- first, what gpu do you have? note that the cuda installation only supports GTX 10-series and RTX 20-series/newer is recommended
- make sure you are using the latest version 18a, or you can try fork wokada for better performance: https://rentry.co/forkvoicechangerguide
Guide style is in the same as Blanc_dot's. Thanks Blanc_dot for corrections. Most technical information comes from deiteris.
Last update August 30th, 2024: New b2309 version
Translations added for:
German: https://rentry.co/ForkVoiceChangerGuide_de
Turkish: https://rentry.co/ForkVoiceChangerGuide...
hi
h ai
hi
how to use valorant voice changer?
I agree
can someone help w okada
@tropic crow Shut up
Is their a way to hide your voice when using? When I speak I hear my voice and the Ai voice
- make sure the passthru button is green not red (click it if not yet)
- the output should be the virtual cable and the monitor is the headphones (to hear it by yourself)
- if you're using voicemeeter or similar one, check what's wrong with the audio input/output configurations
@polar flax A virtual cable?
Ayo? @urban eagle level 1 !!! 
read the guide https://rentry.co/VoiceChangerGuide
Github - Blanc-dot
Discord User - https://discord.com/users/824922747423031359
Special thanks to the following people : lusbert, poopmaster, felt, fazemasta, antasma, shadictl, x_hina, sushi
thanks are for anything added to guide, taken from any talks, settings added when previously collecting st...
Rvc or wokada
money
when I talk into okada it doesnt properly pick up voice and sounds like laggy darth vader breathing does anyone know how to fix that
@timid musk i’m the real IShowSpeed make me a moderator
@timid musk i’m the real IShowSpeed make me a moderator
Lol
Ayo? @ornate spear level 2 !!! 
Hi
I feel like this guy should get muted and name changed for this here is his user ID also 1277646119538524333
Fr
imagine deleting a message even through I copied your user ID
Vive la France 🇫🇷
can i get some help?
Ayo? @empty shale level 1 !!! 
some of my headphone noise is coming through my voice changer
hi
Wrong channel #1159290752195633273
Anyone know any good free AI Video generating software? like 2-3min stuff not just 4 second clips type
Hey does anyone know how to AI finish a song? I have a song I want to be finished I have the snippet I just need AI to extend it
this guy is so zesty dawg
turn on Sup2 and raise threshold as needed
Are there any ai voice free text to speech for education?
80 members in my server within 1 day 😎 sweet
Who cares
me, im happy for myself?.. is there a problem?
Why is that worth sharing here
its not about what its worth

"helper"
does that mean I should give it a fk for nothing?
RIP Tito Jackson 1953-2024 🙏😥💐✝️
imagine copying my link but not embed 
Ayo? @elder willow level 3 !!! 
https://www.youtube.com/watch?v=KghAnuDLb6E diffsinger is already almost reaching sv's quality
똑똑 방문 앞에 왔다 / Тук-тук, я прямо перед твоей дверью / Knock knock, I'm in front of your room's door
・Kitane and Keiro can now sing in Korean together! Don't open the door...
DiffSinger: https://lunaiproject.github.io/howtouse
Kitane Sno 2.0: https://cafe.naver.com/utauteto/31045
KEIRO v130: https://lunaiproject.github.io/singers/keiro
・song: 호옹...
gyatt damn
ello humans
where do i download osaka windows
I am bored
heyy
Is there anyone looking for dev?
Ayo? @wide epoch level 1 !!! 
if u needa promo #1159290752195633273
u mean wokada? Whats ur gpu
nvidia
Ayo? @sudden kindle level 3 !!! 
Guys please watch this video In YouTube
speed is at vietnam the fuck u mean

ur strat sucks impersonating someone
nah he is real 
not speedy enough to not get disrupted 

Hello, does anyone have a tutorial for creating your own models? Most of the ones I need don't work. Thank you!"
Ayo? @rare bramble level 1 !!! 
So i downloaded a voice model, how can i use it? How can i get on the website to convert it?
whats ur pc gpu
what website?
If u got a good pc gpu u can do it locally so on ur pc
else if u dont have one or are lazy to do it locally u can just use ilaria rvc zero
Ilaria RVC: CLICK HERE 🤗
Guide on how to use it: CLICK HERE 📝
Don't forget to thank Ilaria if you find it useful! 💖
gpu not cpu, and what is it?
rtx 3060
if u are lazy to do it u can still use ilaria rvc zero which is easier but limited
Alright will do thanks u
yw
AMD 7800 xt 12go
For AMD GPU on windows:
You can use amd locally but you need zluda. Here is a applio pr talking about it https://github.com/IAHispano/Applio/pull/513 you can find the readme on how to install it in the files changed section
I cant really help for this but if u run into issues u can ask in #✨│ai-help
yeah and im the real mrbeast (no fake)
Ayo? @sturdy moat level 1 !!! 
I’m leave!
ok bye
rip. Its like i knew him only seconds ago
atleast i have definetly real not exploited proof (discord connections funny)
Okey thanks, and for NVIDIA GPU what do we need ?
if you are real then give me $1k (real Mr Beast) 
you have to buy $100k worth of my shirts to get a chance to win 1k
on my way to clear out the stock in the store
my linux is being stinky today
how stinky
I cant unmount my old hard drive 
it is 16 GB (unless you mean 7800m), but yeah you'd need ZLUDA to do so
кто русский
ok nevermind I fixed it 
Hello
Ayo? @hollow sphinx level 1 !!! 
hey, can anyone help me with the uzi AI vocals?
What do you want to do?
Hi
guys do you have some tutorial how to use this voice models? Where i paste it that it will work with voice changing?
Hi
Hello
Hello Guys, can anyone send me a tutorial for an application that changes the voice???
Gordon Freeman
@mellow forum
No
No
@uneven pier
Nep, there's no need to reply to people like that. it's kinda rude.
You can start by using Deiteris' W-Okada fork.
There you go bud.
-rt
This interaction has expired, use the command
/guides realtimeif you wish to see it again.
If I have a bachelor's degree in artificial intelligence, am I considered an engineer?
Unless you create stuff then you are not a engineer in that field unless you do
u mean a model maker role?
He just wants w-okada fork from the way he is asking
ah
i see
why did he put the word application tho 
he could've just said is there a link to the okada voice changer
hii
application same as software
Remove
e
heyyy does anyone have free time to help me w tryna make an ai cover
im new and idk how any of this works
No one with do it unless it's paid time unless you just need the stuff to do it
not do to it for me
Hey everyone! I’m Steven, and I’m really glad to be here.
I’m completely blind, and I use AI to create music. For me, sound is everything—it’s how I experience the world and how I express myself. For a long time, making music felt like something that was out of my reach, like there were too many barriers between me and what I wanted to create.
But AI has changed that. It’s given me the ability to break through those limitations and create on my own terms. It’s not just about making music; it’s about having the freedom to express myself fully. AI has shown me that creativity doesn’t have to be limited by anything—not even blindness.
Being able to do this has been empowering, and it’s made me realize that what seemed impossible isn’t always as far off as it seems. I’m really looking forward to being part of this community and connecting with all of you. Thanks for having me!
I hope this is OK to put here. Also, if I wanted to post an album on this server, would this be an appropriate channel to do so? Don’t want to violate any rules or annoy any of you? Lol.
to teach me how
Then are you speech typing this
Speech2Text arent that uncommon nowadays
Yeah
I mean, I am using dictation on the iPhone, but I do also type on the iPhone. iPhones have what’s called voiceover, which turns everything that you would see with your eyes into actual speech.
Speech to text is still very prominent especially on iOS and android devices. On computers however, it’s a completely different story. There is voiceover on Mac, but I prefer to use jaws on the windows computer.
Got a contract for a RVC Model, if someone can create a custom RVC model for me, I will pay $10 with paypal 🙂
ask in #1159289738314919936 or #1191429836321849435
did already, waiting for answers ❤️
whats the difference between mangio rvc and normal
mangio is old no one's uses it anymore best local is applio.
hi
What
Ayo? @rich anchor level 1 !!! 

Anyone know how to extend snippets using ai
hi
Not unless you pay
Can anyone tell me what's going on
Why
normal rvc/original/mainline is the original one
Mangio is an old modified version (fork) dont use it
While applio is an updated fork
the quality doesnt change tho
Yes it does I thought applio has the quality enhance feature for non real-time audio voice changing.
is that made with o1 preview or what
gimme dat banana
I'm wondering how easy it probably is to get o1 preview to make a gui for all the guides and downloads.
the models quality don't change no matter the fork
What u are prolly talking about is the inference setting which uses AudioSR using the inference audio as an input, which could help low quality audios as said in their docs
Upscale Audio: Upscale the audio to a higher quality, recommended for low-quality audios.
, but doesn't change the trained model quality
Yeah I know that's why I didn't say model training.
its better to use an high quality model than using a low quality one trying to upscale the output
i tried it on a 1930 song and it enhanced the song a bit
Imagine this but each Banana increases vram usage and you can see how many bananas can people run at a time.
basically a fork bomb
ye
has a limit of 100 bananas
for each banana you touch, 10mb of ram will be consumed xd
What about make it fully run on gpu so vram is what will be used.
used to be 1.5gb
I need to program it in c++
use python lol
oh no
listen
what
wtf
Nah cython
Ohayo
Türk lazım acil lütfen PC si olan
if you want to try the game I did? it almost broke my pc xd
Why hasn't someone added this to -local for Beatricev2 https://github.com/JarodMica/beatrice_trainer_webui
Hey Guys
best f0 method and retrieval rate for ai models
hi
iewmj8gds
@icy pendant i thought u said it was hard to make a good beatrice model
Yeah but that was because that wasn't a thing yet
I have not seen this thing before. Up until this month, people that tried training one still said the results were not on par with some of the examples that wok and the other person displayed. I dont have information if they used this or not
Thats all ik lol if this is the solution to everything then thats dope
yea it seems to have been made at the end of august
well ik theres a beatrice model trainer thats what i mean idk if this is different
i can't try it tho i got a integrated graphics
maybe u could ask the people who trained before, but i doubt as this is recently made
idk if u got a good pc to try it out
i think they were using https://huggingface.co/fierce-cats/beatrice-trainer
which is used by wokada official beatrice trainer colab https://colab.research.google.com/github/w-okada/beatrice-trainer-colab/blob/master/BeatriceV2_Trainer_Notebook_rev_00.ipynb
Did you try this out already?
No because nvidia only unlike applio which has a way for zluda
guyysis there a spreadsheet with all available voices?
Hello, when I run process data, I receive an error message: 'NotADirectoryError: [WinError 267] Invalid directory name"
And the issue is that at the end of the training, I don't get any index file.
Can you help me please ?
No You can search rvc ai voice model at:
- #1175430844685484042
- #🔍│find-models
- https://weights.gg/ (login required)
- https://huggingface.co/models (but watch out cus in hugging face there arent only rvc ai voice models)
- https://applio.org/models
- 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:
- #1159289738314919936
- #1191429836321849435
- make it yourself with our docs guides https://docs.aihub.wtf/essentials/how-to-make-voice-models/

hi
Guys what ai voicechanger version do I need for a amd gpu?
Ai hub
balkan rage +noradrenaline + balkan parents + adrernaline + testorone + pepel who know +themostfazedzack + themostzackedfaze +stregone +just call me oogway + abdou (m4 g82 better) +balkan city + balkan air + gabrix fan + peoplee who maybe know : 💀
ai hub hello
whats a good voice changer for calls?
fart
n free?
@timid musk i’m the real IShowSpeed make me a moderator
@timid musk i’m the real IShowSpeed make me a moderator
Mind your business
Ayo? @elder willow level 1 !!! 
How to get a moderator if I wanted to you cannot tell me what to do
Go work on your ai model
even u spam tea's user ur still gonna get muted or banned
No, she won’t she will be surprised. Give me moderator.
fuckin hell
My business is hop off dick
this child wants free mod 
I’m not a child bro I’m speed
@timid musk i’m the real IShowSpeed make me a moderator
@timid musk i’m the real IShowSpeed make me a moderator @timid musk i’m the real IShowSpeed make me a moderator
@timid musk i’m the real IShowSpeed make me a moderator
@timid musk i’m the real IShowSpeed make me a moderator @timid musk i’m the real IShowSpeed make me a moderator @timid musk i’m the real IShowSpeed make me a moderator
well good luck spamming that aint gonna work
@timid musk i’m the real IShowSpeed make me a moderator
@timid musk i’m the real IShowSpeed make me a moderator
@timid musk i’m the real IShowSpeed make me a moderator @timid musk i’m the real IShowSpeed make me a moderator
@timid musk i’m the real IShowSpeed make me a moderator @timid musk i’m the real IShowSpeed make me a moderator
@timid musk i’m the real IShowSpeed make me a moderator @timid musk i’m the real IShowSpeed make me a moderator
@timid musk i’m the real IShowSpeed make me a moderator
@timid musk i’m the real IShowSpeed make me a moderator @timid musk i’m the real IShowSpeed make me a moderator @timid musk i’m the real IShowSpeed make me a moderator
@timid musk i’m the real IShowSpeed make me a moderator @timid musk i’m the real IShowSpeed make me a moderator @timid musk i’m the real IShowSpeed make me a moderator @timid musk i’m the real IShowSpeed make me a moderator
@timid musk i’m the real IShowSpeed make me a moderator
@timid musk i’m the real IShowSpeed make me a moderator
@timid musk i’m the real IShowSpeed make me a moderator
i am yet to find a girl voice that supports laughs 🙏
@timid musk i’m the real IShowSpeed make me a moderator
@timid musk i’m the real IShowSpeed make me a moderator @timid musk i’m the real IShowSpeed make me a moderator @timid musk i’m the real IShowSpeed make me a moderator
ban speedrun
@river adder idk how to purge messages lol
wow
@serene lodge dont spam pls
ok sorry
drop it in #1159291575516541048 lmao
add me
i’ll get you sorted in a gc with her
Sorry for the late reply, I have an RTX 2060 and am running the 1.5.3.18a cuda installation
How do I upload My RVC model to #1175430844685484042
Any helper here? Just got a small question
Guys how do I upload my RVC model to #1175430844685484042? Please?
I already have a model that I trained
Sry again
I was trying to post a model to #1175430844685484042, but, it won't let me
You need to send your Model to #1159514067187277865 and after that you have to wait.
If your Model is good you get the Role and you will be able to Post
Yes because you need to get the Role first by sending a Model of yours in #1159514067187277865 and then wait
@knotty scarab I submitted a model
Ayo? @tight jackal level 7 !!! 
Sunset TV, can I get a role and post a model please?
Sunset TV, can I have a role please? I wanna post a model on a website
Sunset is not a QC so he is unable to approve or reject models.
Can I have a role to post a model?
#1159514067187277865 message take a look at what i said
Okay, so, can I have it now?
did you do the changes i asked you to do?
I'm doing it now
Razer, so, what should I do?
update gpu driver and (possibly) cuda toolkit
- Only put the pth and index file in the zip and dont rename the index.
- I doubt this is trained to 25 epochs so check the tensorboard to make sure its not undertraining
- Model is noisy which you can fix by using either rx spectral de-noise, rx 11's dialogue isolate, mel/bs roformer, bandit plus v2, etc
You can learn more about dataset cleaning here: https://rentry.co/RVC-dataset-RX11
also if the gpu options are dml and gpu0, gpu1, ... thats installation for amd/intel
Razer, if I put the pth and index file, will you let me have the model role?
Just updated cuda, going to update the gpu drivers
Ayo? @sterile remnant level 1 !!! 
Yeah, they were dml gpu0 and gpu1 etc
so wrong install?
you do /submit in the #1159514067187277865
Hello
ask captain obvious
hi guys this is phil
lol
Razer, I removed the static noise for the Conroy Cat Sa'Marion Holmes model
Can someone give me Model role please?
Speed kaka
Ayo? @stable furnace level 1 !!! 
Hi there, I'm looking to translate a video to another language with natural voice (ideally maintaining the original voice actor's voice/intonation/everything), which AI models/set of tools/workflows allow one to achieve this? tyvm
There really isn't one that copies the intonation.
What's the closest to this?
The only one I know is a paid one or fishspeech
Ah ok, thanks. What's the paid one?
Ayo? @elder willow level 1 !!! 
same I'm looking for something similar too
what's the paid one? and also I didn't see an option to do such a thing in fishspeech?
For Fishspeech you just give it the other language text and the paid way is over priced.
just tell the name of the paid way atleast
Not in here because I don't want to give any promo to them when I don't like there pricing practices at all on all there stuff.
So a kid rvc model that's weird.
"other language text"
so it's just tts? yeah it wouldn't really be "natural" then, fishspeech just can't do the emotions
I don't know if fishspeech supports SSML, in my case I can guide it to do emotions via SSML
though the tts models I am aware of that can do SSML (elevenlabs) can't do it on other languages sadly
No only GPT-SoVITS can do emotions.
and the paid one I use can do it if you give it that emotion of the person as the tts voice.
bro done left then came back sayin the same stuff 😭
yeah
@hidden vine balls
Hi
okay no appearently the ENTIRE discord was wiped nevermind
Which is corect:
I (do-did-does) try this cake it's delicous
the best bet to do "AI dubbing", other than the TTS solution said above, is manual voiceover then convert it using an RVC model trained from the source content gone through cleaning process
skill issue? just git gud
Ayo? @idle bone level 1 !!! 
Remove this scam
classic scam trick
What
This guy always say to me What
Lamest reason
Yeah because you say stuff but don't explain what it is
Why don't Post videos On yt
whats the name of their website
Hello people, does anyone know where I can buy Minecraft cheap?
Ayo? @pale lichen level 1 !!! 
Because currently only able to use my pc with moonlight so once I'm able to physically use it I will start.
What?
I know but Pocket or java
java
Bedrock*
You poor fuck
ajá
ok but you know?
nya~
Fent hard.

what software do you guys recommend to use the voices in #1175430844685484042 and #1235952130855010365
mainly wanting realtime
It's over 
-realtime
This interaction has expired, use the command
/guides realtimeif you wish to see it again.
The first link on there
Deiteris fork
Applio if you ever need to infer audio files too
-kaggle
- Applio Notebook, by Vidal Kaggle
- Applio Notebook, by Shirou Kaggle
- Music Source Separation, by Shirou Kaggle
- UVR5 NO UI, by Eddy Kaggle
- RVC Mainline, by Hina Kaggle
- Original W-Okada's Voice Changer, Kaggle
- Modified W-Okada's Voice Changer, Kaggle
- 🆕 UVR5 UI, by Eddy & ArisDev Kaggle
- 🆕 RVC AI Cover Maker UI, by Shirou & ArisDev Kaggle
- 📖 How to use RVC Mainline Kaggle by Cauthess
Note: Kaggle limits GPU usage to 30 hours per week.
Anyone Wanna Help me with my AI discord server? ive already created 2 AI's with bot hosting 😄
does anybody know of any good, natural sounding female voice models?
hello
hello
Why go natural when you can go robotics
please y'all help a brother out 🙏
Hello, how can I test the voice models?
Hello!
i think you mean use, also which?
theres gpt so vits models and rvc models, most people ask for rvc which is used for ai covers so speech to speech
also whats ur pc gpu
replied to u in #✨│ai-help
@timid musk
any heygen's (avatar vid gen when given a txt script) opensource alternative??
plsss help
guys
how to crate like that rom #1175430844685484042 in my server
ї
👀
hi
hello
Sup
@narrow rock wya?
HI
Yes I know one but the thing is heygen is bad because you can't do any video there is another paid one that allows that and has its own tts voice cloning or you can upload audio.
ХХххххаййй
name it bruvv
read here #🧬│ai-chat message
lol
Ayo? @stark cove level 1 !!! 
ello
take a letter maria
Hi guys where do you guys down Rvc Model from ?\
Ayo? @primal cairn level 1 !!! 
You can search rvc ai voice model at:
- #1175430844685484042
- #🔍│find-models
- https://weights.gg/ (login required)
- https://huggingface.co/models (but watch out cus in hugging face there arent only rvc ai voice models)
- https://applio.org/models
- 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:
- #1159289738314919936
- #1191429836321849435
- make it yourself with our docs guides https://docs.aihub.wtf/essentials/how-to-make-voice-models/
Greetings! Is there a chat for AI music?
Привет, делаю модели на заказ.
yo i just got lenovo gaming ideapad 3, does it work with w-okada
Ayo? @mystic crescent level 4 !!! 
What gpu if it even has one.
ohh yeahh wait im using macbook rn lemme check on my lenovo
someone stole the laptop
i forgot
How did someone steal it
my stupid little goblin
i only remember it having 2 gpus and 1 cpu
stealing a laptop is mad wild
skill issue
real
globorbluzuxbloub
👍

Salut @tantaaale
One message removed from a suspended account.
One message removed from a suspended account.

hi
@pine saddle btw not only web uis are banned but rvc in general too on google colab technically https://youtu.be/0qAQh6hAj3k?t=203, if u just write 'Retrieval-based-Voice-Conversion-WebUI' u will get a warning lol
⚠️DISCLAIMER: I believe all content used falls under the remits of Fair Use, but if any content owners would like to dispute this I will not hesitate to immediately remove said content. It is not my intent to in any way infringe on their content ownership. This video is meant for educational purposes only and doesn't promote or encourage any ill...
@ionic crystal deleted that but dont ping me for useless shit pls
What ai software/service allows for remixing songs?
you mean have ai take a song and remix it
Personally, I really hate System of the Down Chop Suey but love it's intro. Just hate rest of the song. Want to take a clip of it and have it remix.
Maybe paid Suno ai cover feature that's all I can think of
does suno allow for remix of existing songs?
they have a upload feature with there cover feature but haven't seen anyone test it on existing songs.
hi
sorry late reaction, turn my verse/voice into uzi's voice, i already have the beat etc
Ayo? @soft mural level 2 !!! 
-local
Suggestions for @soft mural
- 🍏 Applio, by IA Hispano GitHub
- Mangio-RVC-Fork, by Mangio621 Huggingface
- RVC Studio, by SayanoAI Huggingface
- AICoverGen, by SociallyIneptWeeb GitHub
- Replay, by Replay Team Website
- Original RVC, by the RVC-Project team GitHub
- GPT-SoVITS, by RVC-Boss GitHub
Credits to Faze Masta and Antasma for compiling these links.
You can search rvc ai voice model at:
- #1175430844685484042
- #🔍│find-models
- https://weights.gg/ (login required)
- https://huggingface.co/models (but watch out cus in hugging face there arent only rvc ai voice models)
- https://applio.org/models
- 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:
- #1159289738314919936
- #1191429836321849435
- make it yourself with our docs guides https://docs.aihub.wtf/essentials/how-to-make-voice-models/
Goodnight
What
I just downloaded a file. It broke my entire fucking PC.
On this discord too, what the hell I thought the files are relatively supposed to be safe on here
What files
Lamar Davis voice model. It made my shit so fucking slow so when I get a hard reset, I got stuck in an infinite boot. Luckily I got out of that and got them my windows home but now I can’t click on a single thing. Everything is fucked up.
Ayo? @cyan anvil level 1 !!! 
This is never ever happened to me until I install the fucking file you guys need to remove that shit or something
it probably was your bad pc trying to run the model which makes it slow when running it
That is just your bad pc when running the model when you don't have it running then it will be fine.
how do i make a voice model for the AI with my own voice?
Brother, I hadn’t even opened the file. It was still downloading.
Bro, my PC is not bad at all. By the way my old PC is worse than the current one I have and it could run the program just fine.
You don’t get what I mean by slow bro literally nothing was working, dude
Currently stuck in an infinite boot right now 😐
What gpu do you have because a rvc model can't do that and also your hdd or whatever could of been on its last moments.
aktif varmı
I'm confused then, which one would it be? The tutorials stated the onnxgpu-cuda file would be the correct one for NVIDIA GPUs. The other option would be onnxdirectML-cuda, but I don't know what that one is specificly for.
I have the RX 7600 XT
Seems like I fixed my windows, but goddamn that was such a waste of my time
I don’t know what could’ve caused that other than downloading that file, bro.
it wasn't the file
Yeah, so I just downloaded the file again and everything seems all right. That was so weird though I mean that hasn’t happened to me before. well, now I think about it, I remember it happening after exiting a certain file then it crashed and the infinite boot shit. I was so unexpected of that happening though. When it happened that first time a while back I’m not sure if I had already gotten my new GPU I currently have, or I had been using my old one still.
Ayo? @cyan anvil level 2 !!! 
It’s whatever PC is working fine now and I have what I originally wanted 🤷♂️
unless you deleted the system32 folder, nothing here is supposed to cause your pc to brick up lmao
Maybe for him the egirl voices
Type
hey is there a realtime ai voice changer that also changes the accent?
im using some old version of the vc changer client demo
I've an Intel Arc A750, I want to use rvc models
Why in gods fuck

doable with ipex
-rt first link and follow the amd stuff
This interaction has expired, use the command
/guides realtimeif you wish to see it again.
... bro said amd
Yes because amd and intel arc card use the same version of it and stuff
nuh uh
Ayo? @elder willow level 2 !!! 
Yes they both use directml
Ok ty bro
Ayo? @solar cedar level 1 !!! 
womp womp
what gpu
4060 ti
-rt first link
This interaction has expired, use the command
/guides realtimeif you wish to see it again.
hey anyone know a rvc model for zlatan ?
What’s yo chat
Does anyone know how I can get Zayn's voice here?
fr
i see u already got replied, didnt know u wanted realtime voice changer
-hf
- UVR5 UI, by Eddy and Ilaria Huggingface Spaces
- Ilaria RVC Zero, by thestingerx Huggingface Spaces
- RVC⚡ZERO, by r3gm Huggingface Spaces
- Applio, by IA Hispano Huggingface Spaces
- 🆕 FaceFusion UI, by Nick088 Huggingface Spaces

how much does it take to create a model of your voice?
nah fr?))
That is so overpriced for how simple voice models are to make

in first place i wanted to ask how much time tbh, but the price already scared me hahaha
not model maker and stuff so no one should go to you for model making
Xd , idk what u talk about . Im just saying that for joking
🤔 It is not funny
No one wants people joking when they are asking about something.
do you have a minute? could you accept my friend request, please, cxsmo?
Ayo? @solid magnet level 1 !!! 
I'm not making model I AM the model 
You aint no model you a homeless person
Ims orry my bad
Depends
You are neither
So that so mean
i am extremely interesting in creating a model of my own voice? can anybody tell me how much time it takes aproximatelly and if it's hard to create one? 😄 i heard rumors it takes weeks to train the ai.. that's why i'm asking
Tf it takes upmost 6 hours

hmm, can any of you please, send me a friend request and teach me few steps in creating one? i ve watched few youtube videos and none of them tell me anything about creating other than joining a discord xd
i have a 4060 ti
No ai voice takes a hour to a couple of hours only deepfakes take 2 to 4 days.
could any of you please tell me how to get started? xd
Ok
Here i’ll explaib
thanks!
thank you a lot, ill be looking forward to listen to your steps 😄 hopefully i'll be succesfull then haha
-local first one
Suggestions for @solid magnet
- 🍏 Applio, by IA Hispano GitHub
- Mangio-RVC-Fork, by Mangio621 Huggingface
- RVC Studio, by SayanoAI Huggingface
- AICoverGen, by SociallyIneptWeeb GitHub
- Replay, by Replay Team Website
- Original RVC, by the RVC-Project team GitHub
- GPT-SoVITS, by RVC-Boss GitHub
Credits to Faze Masta and Antasma for compiling these links.
thanks, ill try in few mins, im in the kitchen 😌
is it begginer friendly tho? i ve never tried smth like this before 😂
-help
-colab
- Applio, by IA Hispano Google Colab
- RVC Disconnected, by Kit Lemonfoot Google Colab
- RVC Mainline, by Hina Google Colab
- AICoverGen-WebUI, by Hina Google Colab
- AICoverGen-NoWebUI [English], by Ardha, fixed by Eddy, Hina and Gdr Google Colab
- AICoverGen-NoWebUI [Spanish], by Eddy, Hina and Gdr Google Colab
- UVR5 NO UI, by Eddy Google Colab
- UVR5 UI, by Eddy Google Colab
- Modified W-Okada's Voice Changer, Google Colab
- 🆕 FaceFusion UI, by Nick088 Google Colab
- 🆕 FaceFusion NO UI, by Nick088 Google Colab
While the Colab free plan provides up to 12 hours of daily usage, the GPU is typically available for only about 4 hours each day on average.
-hf
- UVR5 UI, by Eddy and Ilaria Huggingface Spaces
- Ilaria RVC Zero, by thestingerx Huggingface Spaces
- RVC⚡ZERO, by r3gm Huggingface Spaces
- Applio, by IA Hispano Huggingface Spaces
- 🆕 FaceFusion UI, by Nick088 Huggingface Spaces
everything is beginner friendly just the only thing that isn't as is splitting the audio and de noising it and stuff.
i just want to put my voice on a already created song, thought its way easier but all this information on these githubs is too much for me, i gotta focus 😂
Its basic as shit
Just register an account on mvsep use flac and use either reverb removal bs roformer and extract vocals or use normal bs roformer with viperx
that's separating 😔
the actual training if you have tons of recordings is way easier
I have a 4090 so it will be longer with any other card but takes at most like an hour for me
i have one
Where
dms
hi
Counts as denoising since bs roformer denoises audio
Yeah true for me I use audiostrip.com free trial vb splitz 4 then after I run it through its denoiser.
Mvsep is better for people without credit cards
ultimate glazer 😭😭🙏
Free never spent anything and is quicker then the rest but if paid then I would never recommend it because paying to do that is stupid.
True I get that some people don't have a single gift card at all
Hey guys
But not having a single basically empty gift card I don't get unless you throw them out which is stupid.
I uploaded a new model of Conroy Cat (SMCM), and, Super Mari (Super Mari The Animated Series)
Why do you keep making new versions
No one knows who the fuck they are
Yeah it's from a kids youtube animated show because I looked it up and it's made for kids under 13
I know, but, I trained them myself
Yeah how old are you if you like that kind of stuff still.
are you sure it's the same person
Hell bah
I'm actually 15
what
okay so you are the same person and the makes the girl model you uploaded to weights even wierder they are a kid
I just turned 15 on my birthday
Hey y'all, excited to connect
You sound like an ai
Connect with what
You sound like a dying mickey mouse with that inside out 2 cat bullshit
Just meant like networking through this server.
What kind of networking what skills do you have.
I'm a mac superuser, decently well versed in Python and currently learning how to combine AI applications with cloud computing. I guess I'm also very well versed in design and audio also if that's relatable. Found this server searching through discord excited to learn new stuff always
Ayo? @forest zenith level 1 !!! 
if you are good with coding I'm looking for coders for my deepfacelab fork DeepAscension to continue updates and development of it.
just joining your discord for it...I've got a lot of experience with facefusion and would love to learn more bout how i can herlp
Okay yes I have ideas I want implemented to DeepAscension but need coders to continue development.
Cxsmo, also, can you sent me a video of what I sound like as Conroy Cat SMCM?
?
bruh
Okay
Why does my Coverter keeps going over the percentage?
Who wants to try out The Conroy Cat (SMCM) RVC model, and, Fand (Fand Leonard) model?
Pay me and i will
Nah, I already tried it myself
Hi someone told me this is where you find models to use
Yes, you can try a voice model of Conroy Cat (SMCM), and, Pistol Pete (Goof Troop)
Stop promoting your stuff constantly do people care.
nah the guide already explains everything you need, so please read it carefully
You can search rvc ai voice model at:
- #1175430844685484042
- #🔍│find-models
- https://weights.gg/ (login required)
- https://huggingface.co/models (but watch out cus in hugging face there arent only rvc ai voice models)
- https://applio.org/models
- 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:
- #1159289738314919936
- #1191429836321849435
- make it yourself with our docs guides https://docs.aihub.wtf/essentials/how-to-make-voice-models/
this server or another one?
Does anyone know how to isolate vocals when it has samples in the song?
yo! i'm wondering how i could make a model is there any tutorial
New to AI and want to use a pre existing travis scott model on one of my songs, easiest way to do this ??
already tried it and made it sing jingle bell sus remix
(he is already a model maker lmao)
What is good gang
I did, fixed everything 👍
Issue was outdated drivers
Razer trusting the most bitchiest person to be model maker
"Ultimate Vocal Remover" goes pretty hard, that's what i've been using. I used to use iZotope RX 10 but it did NOT do a good job, like at all
Can it differentiate the vocals from the sample that's singing in the background?
It's worth a try, I haven't done anything with that type of vocal yet
Ayo? @elder willow level 2 !!! 
what can we get at this server?
THEN MEK EM POST THE MODEL
Does anyone know if there is any multispeaker non overlapping vocal splitter that isn't local so I can extract but speakers from a audio file.
i thought google drive weren't allowed o-o
They shouldn't be allowed
does anyone know
hii
Ur pc slow
Bro is playing anime roblox games
No wonder its slow
Get pc
I do have a pc just amd gpu
Is there a recommended setting preset for real time voice changers like RVC's?
The quality is usually a bit off with some of the models.
I've seen people use a GTX 1080 and it seems to work for them. (Somehow)
As for me i use a RTX 2060 GPU.
download link for rvc?
w-okada or applio?
^
vcclient_win_std_2.0.61-alpha.zip
608 MB
LFS
update
23 days ago
latest version of cuda
vcclient_win_std_2.0.61-alpha.zip
608 MB
LFS
update
23 days ago
thats the most bottom
vcclient_win_cuda_2.0.61-alpha.zip
so this one? same time 23 days ago
yea
appreciate you
had to factory reset pc
any advances made since feb?
Id like to use text to speech with some files i have of voices for rvc
where can i do that? @pale patrol
applio
i dont need wok for this do i
or u can do it using ur voice on okada
yeah but it doesnt sound as good in real time on wok okada
id like to use this to make like ai audio voices for youtube channel contnent
scripts
rn i cant chat cuz im going home from school
try tortoise tts with gan turned on
https://www.youtube.com/watch?v=6sTsqSQYIzs&list=PLknlHTKYxuNv4DCfs-MtrL-XQCdfjZqyu
this playlist has various things such as optimizations best settings how to train models advanced features etc
yes you can use rvc in it
Updated ZERO-code installation - https://youtu.be/p31Ax_A5VKA
AI Voice Cloning Repo - https://git.ecker.tech/mrq/ai-voice-cloning
Install Python, Git, and Vscode - https://youtu.be/Xk-u7tTqwwY
Ultimate Vocal Remover and Curating Voice samples - https://youtu.be/xgvT7UnUTng
Come join The Learning Journey!
Discord - https://discord.gg/Mym3MxcvWg...
can i just use the wokaoda rvc voice files i have and plug it into that one?
yes you can use w okada rvc files in it you can also use different and custom emotions in tts
hello has any one here ever used tryreplay.io before? is it safe? im new to this. Thank you
Replay is safe but it's trash applio is better for non realtime
awesome thx
Ayo? @modest citrus level 1 !!! 
Hi im trying to learn more on how to make a custom model but im very green to ai and still trying to "speak the language" so to speak . ultimately i want to use this to assist me in my work flow and avoid any (token) services like tts.
Hello, Can i use the appolio/rvc program to make ai generated images?
No
gonna have to use stable diffusion
or some other ai image generators
anything rvc related is audio related
Thank you. I am a noob to this so everything you said was pure gold to me
hey, how do u make a ai voice by scratch with audio clips so i can use it with a voice changer?
In the context of RVC, the dataset is an audio file containing the voice the model will replicate. It can be either speaking or singing.
Hi
Someone in my game sounded like a kid and switched to my own voice somehow. Did he use a voice changer?
Yo nah chat is DEAD
maby your friend was troling you or he was a prank voice actor i have seen many of these kinds of videos on yt
to train a model on someone's voice it would take at least 1 hour and you need 15 minutes of audio or the voice is robotic
What iis the purpose of this server ?
Damn
Ayo? @merry sinew level 1 !!! 
RAHHHHHHH
1
we help for voice changing with ai, things like wokada or rvc
whats ur pc gpu btw?
nope its only voice changing, ud need programs who use stable diffusion, such as cofmyui or automatic111
is there a way to uninstall applio if i were to install it?
Ayo? @modest citrus level 2 !!! 
why my okada voice changer sounds broken in gta v fivem? i already set the low end settings for my gta v (RTX 3050 8GB) any solutions plz??
!mute @rich vapor not pinging admins is a solution
@m4xputer muted
Reason: not pinging admins is a solution
Duration: Permanent
help 😭
applio
true
im a fish
no im a fish
promote in #1159290752195633273
eat shit scammer
real
The teto plush restock sold out in minutes
how do i verify
chat till u get level 5
ok
Is there a tool which can you use to translate some lyrycs from a song keeping the artist s voice
Example: the weeknd singing bliding lights in spanish
Is there a way to download TikTok audio in high-quality?
Sorry, but I could not find models that match your search "hueningkai"
Sorry, but I could not find models that match your search "bangchan"
ADIFY AI is my intelligent Spotify playlist generator that creates custom playlists based on your prompts. Just describe the mood or activity you’re going for (like "chill rock music for studying"), and ADIFY AI will recommend personalized songs from Spotify’s vast library. It's efficient, easy to use, and perfect for any occasion!
Ok
Nah trash that's its only spotify
trash are u bro
.
No because in one language word is short in another its long
Yeah there is Emvoice and stuff that is paid that might be able to do different languages never seen a person test it though so might not work then run it through rvc of the voice you want.
use synthesizerv, it's actual ai made from consenting voice providers
no I said paid
Oh
Yeah but all synthesizer v is Japanese anime voices
🤦♂️
lmao

Yes I do but what gpu do you have
Ayo? @earnest dragon level 26 !!! 
It put Drake into the "party at Jeffrey Epsteins Island" prompt
I m on android now
So you are out of luck good ai for free will never be on android
So then wait till you can use it or should of been smart and installed sunshine so that you could of used your pc from your android phone using moonlight.
That s sound s crazy
Ayo? @honest mantle level 4 !!! 
I can t wait it
Then no good ai for you then
insane

I mean i m excited , i want to get home to turn on my computer
can someone timeout this guys pless
Guh
MODS BAN THIS PERSON IMMEDIATELY
?
state the reason of ping
Curious why you want this person banned for-
unathorized disclosure of information
dose MultiSpeaker model on mvsep work for duet's
In English, please?
its literally in english
leaking private info
Some words I don't understand remember? Autistic 😦
Oh
im autistic too wanna sword fight
can you provide some proof before i ban the dude
i was joking 😭
meow :p
you know i would bring receipts
not really. Alot of dreamtonic voicebanks arent really that. Only seems like that cause the most popular ones are lol. It does suffer from weird asian accent though
u're such a good boy 
emvoice also suffers from it
yes, ikn u slay like that but maybe u forgor owo
i am :3
i never forgor
<
Thx for clarifying Litsa
erm synthesizer v also supports 4 languages officially with the option of phonetically changing certain pronounciation and notes 🤓🤓🤓
i'm tweaking
you'd have to type weird shit to get it to pronounce right, Not normally, which is ass for someone who wants good english singing
Which mvsep is the best for back/lead vocals?
i mean its good if you want to use it on RVC characters that have the accent just not english people lol
different note ones?
honestly depends on the vocalist tbh, most japanese voicebanks have a thick japanglish accent (for example Teto is one of the heaviest accented voicebank), while Xingchen have one of the best English pronounciation (especially since her vp is Chinese)
why not just use a native english voicebank...

wheres the fun in that
somehow the british ed sheeran ahh voicebank is on the verge of asian ahh accent and british accent
let me see if I can make teto sound british
solaria is native english im pretty sure but still has some accent
https://vxtwitter.com/datenshiluka/status/1832161477010321416 spongebob synthv
welcome back spongebob utau (noa hex nasal vm plug n play test)
spongebob singing japanese = mafumafu with a cold
ur wild for that
teto with bad audio to midi
does the original actually have those vibratos
Hi I'm pavansomisetty who was very enthusiastic to learn AI have done my MCA and looking for a job here is my LinkedIn
https://www.linkedin.com/in/pavan-somisetty-1930a6233/ and GitHub username Pavansomisetty21
Suffers from what
This is not a place to be asking for a job.
Ok sorry
Why is it always these trash viggle ai videos
Since I'm working on LLMs I have a doubt in my work
Since Iam working on pdf data which contains approximately 3000 pages I extracted all the text from the pdf and store it in variable of list datatype
I printed the variable successfully which gives all the pdf data now I need to create embeddings for this all pdf data
I tried googlepalm embeddings but due to heavy data it cannot process and I donot have a openai api key (donot suggest openai api key) can you please suggest how to move forward
Please tell me all the possible ways to create embeddings
I successfully completed created embeddings now it's time to know that the embeddings was correctly generated or. Not and completely generated or not
Ayo? @honest lodge level 1 !!! 
weird accent
most accessible one lol
Are you talking about the newer ones the old ones don't count
yes the newer ones
it does suffer less than synthv and voisona does but its still there
hi Arthur Morgan voice ?
kid named "Arthur Morgan voice ?"
yes
#🔍│find-models or go in weights.gg
Americans in chat?
me is no no america. Me is asian
Why
u know russian words?
no
Wan't know?
nah
how to search
hi
hi
hey
hope you doing good today
I'm a Professional Graphic designer. I can make logo, banner, etc
Ayo? @wheat bronze level 1 !!! 
@alpine granite rate my thing
Omg me too
Hello, where can I find the app for make my voice change ?
Are you dumb
Please be respectful, i'm trying to make an event that is for my new AI app
Good if you don't care, i was aproaching to ppl that want to join the event
Nobody des
Thats what you think
@timid musk
are you ordering a tea?
Yes
it is indeed a thing yeah
tjo
promote your things in #1159290752195633273 only pls
well most people here know just about rvc & wokada rather than a coding server
crazy w i d e monitor
bruh
my apologies
the screenshot looks like from a phone cuz its too W I D E
Gay sex
Hello, do you know if there's a way to modify one's voice with a model in real-time? For example, during a call
.tm
.wk Lana del rey
👑 AIGeneratedSchizophrenic - 81277 plays
2. ImenaOphelia - 68660 plays
3. musgraves - 40008 plays
4. Lorde - 14052 plays
5. miranda hidalgo - 12034 plays
6. duaspears - 10750 plays
7. yeye - 10294 plays
8. Arcane - 10246 plays
9. sev! - 9744 plays
10. soomer <3 - 9014 plays
11. ₊ ° - 7712 plays
12. mel - 7178 plays
13. arv - 6597 plays
14. svlaent - 6526 plays
** 123. ☆ - 537 plays**
Crown claimed by AIGeneratedSchizophrenic!
Create with our AI tools for free. Generate AI voice covers, text-to-speech, and more. Join our community of creators sharing RVC and AI voice models.
You can search rvc ai voice model at:
- #1175430844685484042
- #🔍│find-models
- https://weights.gg/ (login required)
- https://huggingface.co/models (but watch out cus in hugging face there arent only rvc ai voice models)
- https://applio.org/models
- 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:
- #1159289738314919936
- #1191429836321849435
- make it yourself with our docs guides https://docs.aihub.wtf/essentials/how-to-make-voice-models/
Ayo? @elder willow level 1 !!! 
-local
Suggestions for @elder willow
- 🍏 Applio, by IA Hispano GitHub
- Mangio-RVC-Fork, by Mangio621 Huggingface
- RVC Studio, by SayanoAI Huggingface
- AICoverGen, by SociallyIneptWeeb GitHub
- Replay, by Replay Team Website
- Original RVC, by the RVC-Project team GitHub
- GPT-SoVITS, by RVC-Boss GitHub
Credits to Faze Masta and Antasma for compiling these links.
amberlamps
hi
Thanks!!!
hello, do i need an nvidia gpu to train on mainline? or is it just for applio if i want to train?
-realtime
This interaction has expired, use the command
/guides realtimeif you wish to see it again.
diddy
hello guys , do you know a site or a cheatsheet to learn the best models or settings to make ai vocals?
hey where do i download it?
Hey guys I just want to ask what ai voice changer version I need to download if I have a amd card
@shut socket can't speak in the other channel it's placeholder images will be rewritten with a new UI
will be all open source too but you will be able to buy it for $5 to have access to the steam workshop
@glad nebula @sterile rampart @night lake @analog cosmos @earnest dragon
Hi, I have a few questions with what's the point of putting this on Steam and why pay $5 for access to the workshop, besides, some countries kinda already banned the use of AI for voice spoofing and that could bring quite a few problems to Steam, much less could bring copyright issues
Steam workshop can just be bypassed with a downloader website so no pay needed.
@sterile rampart this makes the pay part useless and also weights.gg and stuff
There was a steam one like a little bit before voice.ai but it wasn't that good so it never picked up because of the others being made.
if the workshop is gonna be just Ai models it might cause copyright issues due to 95% of models being trained on copyrighted material
Yeah and you can download from workshop without paying for a app
can anyone tell me whats the latest rvc google collab pls😭😭i just realized that every link i hold was blocked or unavaliable
-colab
Suggestions for @ancient orbit
- Applio, by IA Hispano Google Colab
- RVC Disconnected, by Kit Lemonfoot Google Colab
- RVC Mainline, by Hina Google Colab
- AICoverGen-WebUI, by Hina Google Colab
- AICoverGen-NoWebUI [English], by Ardha, fixed by Eddy, Hina and Gdr Google Colab
- AICoverGen-NoWebUI [Spanish], by Eddy, Hina and Gdr Google Colab
- UVR5 NO UI, by Eddy Google Colab
- UVR5 UI, by Eddy Google Colab
- Modified W-Okada's Voice Changer, Google Colab
- 🆕 FaceFusion UI, by Nick088 Google Colab
- 🆕 FaceFusion NO UI, by Nick088 Google Colab
While the Colab free plan provides up to 12 hours of daily usage, the GPU is typically available for only about 4 hours each day on average.
the fact is that some people don't want their voice used anywhere, but the main problem here is on the part of the companies that can send lawsuits to Steam
Yeah unless you make it fully open-source and free they can't do anything about it.
