#🧬│ai-chat
1 messages · Page 260 of 1
Uhm...Might I ask something? I have a clip of a character from Ace Attorney, which is Rayfa. Unfortunately, her only lines are the Divination Seance she makes and thats roughly 23 seconds. Do you think it would be possible to get a model out of it, even if trained with the lowest epochs?
Lower/higher epochs does not mean better
-overtrain
You can detect if a model is overtraining if the TensorBoard graph starts to rise and never comes back down. An overtrained model will sound robotic, muffled, and won't be able to articulate words well.
Check these resources to learn more about this topic
- Epochs & TensorBoard from
AI HUB Docs - TensorBoard from 🍏 Applio Docs
does it support index or pth?
you didn't even read the private messages, I sent you Google drive and an example of the models that I trained, I need to open them somehow so that they read the text.
I'm sorry, I couldn't think of anything to say.
I see. Then I guess a more appropriate question would be if anything good could come out of training 🤔
Ayo? @tulip cedar level 4 !!! 
Maybe?
oki, thank you! I will try~
try to open them and test them in some program, because I do not know too many of them.
I'm sorry, I couldn't think of anything to say.
Should I send it here?
is vocal fry good or bad in a dataset?

check link and model type
Just recreated kanye's voice perfectly in udio ai 💯💯
ocasional vocal fry is good, if there's a lot of them then rvc will add vocal fry in every word no matter what
can anyone help me get an voicechanger with a girl voice pls?
how about harsh s and p
sometimes when you talk to a mic, maybe you release some wind or something from your mouth when saying P and S, and it creates harsh sounds
simpler words:
rvc will learn everything is in your dataset, so i hope that makes things more clear when clearing datasets xD
hard S and hard P (or any harsh sound) is bad
ha
and im looking for saori hayami (shinobu's, yumeko, yor etc's VA)
which character's "saori hayami" do i go for
who sounds the best
model quality depends in the person who train them
hmm yeah im aware
Ayo? @tall vigil level 1 !!! 
so for people who've tested various ones or atleast found a good one, do you have any suggestions?
s
just try every one
<<In a survey of 2,700 AI researchers who had published at top AI conferences, a majority said there was an at least 5% chance that superintelligent AI will destroy humanity”>> ummm
anxiety
hi
need a turkish valorant jett and neon
😭😭
Barbekü festivaliniz kutlu olsun
@poopmaster
I mean.
Nuclear physicists would say there's an at least 5% chance humanity is going to be destroyed in a nuclear holocaust 🤷♀️
Hi
? he left time ago
bruh no 😭
I would never get whipped out
Hello hello AI people.
haii
I was looking for an AI model of that awful TikTok valley girl voice but nothing came up. Has anyone come across one?
happy father's day
someone make a rimuru tempest model and my life is yours
You can search rvc ai voice model:
- #1175430844685484042
- #🔍│find-models
- https://weights.gg/
- 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/
if there isnt one, you can:
- #1159289738314919936
- #1191429836321849435
- make it yourself with our docs guides https://docs.aihub.wtf/
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.
At the forefront of innovation as an open-source ecosystem that hosts cutting-edge AI voice cloning technologies.
Last update: Mar 10, 2024
You can search rvc ai voice model:
- #1175430844685484042
- #🔍│find-models
- https://weights.gg/
- 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/
if there isnt one, you can:
- #1159289738314919936
- #1191429836321849435
- make it yourself with our docs guides https://docs.aihub.wtf/
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.
At the forefront of innovation as an open-source ecosystem that hosts cutting-edge AI voice cloning technologies.
Last update: Mar 10, 2024
isn't that the 19 march
the search rvc?
- the other older copypastas that i made for searching models that i forgot tho
i remember i made other ones js idk the keywordd
i do it like daily atp
same
i used to share the sites without the 'search rvc' before so thts prolly why
idk why people come here like 'make a super mario model'
like theres request modle
wdym with other places
i join and left that place like 2 times
should i join it
does anyone here use hina's rvc? it doesnt work for me anymore
ask help in help channels and be specific

yo does anyone know why my skibidi toilet voice dontr work no more
!howtoask
How To Troubleshoot 
- Don't simply mention your issue, like "
my rvc is not working". - Describe the step you are on, what you're trying to do, the RVC you're using, a screenshot, etc.
- The more context, the better.
- 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.
- 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.
Hi
Hello
Hi
Who needs ps5 valorant codes?
Brazil
hold on can someone link me some good models
the ones ive used so far have been pretty bad
-rt
This interaction has expired, use the command
/guides realtimeif you wish to see it again.
@rustic gazelle
STOPPPpPPP
There is also a ai hub Brazil server
You can search rvc ai voice model:
- #1175430844685484042
- #🔍│find-models
- https://weights.gg/
- 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/
if there isnt one, you can:
- #1159289738314919936
- #1191429836321849435
- make it yourself with our docs guides https://docs.aihub.wtf/
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.
At the forefront of innovation as an open-source ecosystem that hosts cutting-edge AI voice cloning technologies.
Last update: Mar 10, 2024
can someone help me? it says JSONDecodeError when trying to do step 2: download the model
hey i am having problems with voice.ai. when i use my 3rd party voice for live it just crashes. can anyone hellp
tryreplay?
ye
you are using an outdated colab, either use:
- Ilaria RVC Zero which is an huggingface space running for free on zero gpu, so A100 which is 11 times faster than a T4, if you want only inference (use the models, make ai covers)
- Use other google colabs (using colab free daily limit T4 gpu) that you can find in our docs
Also for issues next time use help channels
Have the audio file of your song ready, & let's extract the vocals from it with an audio isolation software.
whats that (js curios)
We dont offer help with voice.ai we use free wokada here
-rt
This interaction has expired, use the command
/guides realtimeif you wish to see it again.
https://github.com/tryreplay
here was an opensource tryreplay, but they made it private, there was something useful
Replay & Weights.gg. Replay has 4 repositories available. Follow their code on GitHub.
oh u meant that replay 😭
There was something useful for the community but of course now it's private 
didn't know much abt their github page, but so they privated their whole replay program source code?
yep, I predicted it 1 year ago, idk.
sadly most of the chat went to the other dc. but I had already said it
Does anybody know any online rvc site?
anyone know a good software to use that can actually convert metal screams/growls?
how do I find rvc on huggingface, cuz the thing im using needs a hugging face link
Ayo? @west rover level 2 !!! 
- Ilaria RVC Zero which is an huggingface space running for free on zero gpu, so A100 which is 11 times faster than a T4, if you want only inference (use the models, make ai covers)
- Use other google colabs for inference and training (using colab free daily limit T4 gpu) that you can find in our docs
Have the audio file of your song ready, & let's extract the vocals from it with an audio isolation software.
basically all models uploaded in #1175430844685484042 are uploaded on huggingface, where are u getting the models
idk if its the model or the software (replay) but it's not converting my screams properly (using chester bennington)
ok I found a link, when I use ilaria it says failed to unzip
damn you ilaria
Um, excuse me?, I have a question
I don’t see that the model for the character I wanna make a voice model of is available on this server, what do I do to get the voice model?, I have a file I downloaded of the voice lines of this character and I don’t know what to do with it
Im trying to make a voice cover of this character singing “sway” by Michael buble
when i upload a model to ilaria is it only me who sees it or everyone else using the site as well
Who cares about AI researchers idea about probability lol.
Them saying "Yea there's about a 5% chance a super AI will destroy humanity" reads like a scientist saying "Yea there's about a 7% chance scientific advancements will go far enough to exterminate the human race on accident"
everyone, but you can duplicate the space for private use
We're gonna blow ourselves up either way
can I delete a model after uploading?
every model gets deleted after every restart
ok, and is music I upload private
music and audio yes
okok and approximately when is every restart
They have some semblance of credibility in the field as far as AI goes, but for example if probability is gonna be read out under Bayesian probability, I don't see what they information they could even have for likelihood, their priors & evidence lol
when i want really tbh
if you want to convert and ask me to restart ill do it
IF no one is using it
We will be our own undoing, I will not let Humanity's destiny of destroying itself be cucked by some Mommy Milkers having robot

wait could u restart gang 🙏
(whenever it's convinient)
restarted
Thanks
Ok
Ayo? @abstract ridge level 63 !!! 
uhh how do I pick which version for my specs
What’s your GPU and what are you trying to install?
4080 super and I got a ryzen cpu
Ayo? @grave epoch level 3 !!! 
the RVC
just RVC?
yep
Download the one for NVidia GPUs
which one lol
im clueless there is so many links
Where are you right now?
there is ONNX and Pytorch and directtml cuda and so many stuff
the hugging face download page
That’s the voice changer not RVC
(But it uses RVC so eh doesn’t matter)
Download the highest number that doesn’t have DirectML
make sure it has Cuda
look ill send you a pic and justt tell me which one it is
@cinder swan a
tf
i feel like this is one of those n word attemps idk why
and what does F0 do? like which one should I pick
Pick FCPE or RMVPE
F0 is pitch method
zamn
and index?
Acts as accent
Most people don’t use it on the real time voice chnager
A good chunk of models have their accents baked into the pth
Random question, where do you go to submit models youve made?
Thank you! I've already found it as I'm doing this. Found the tutorial as well. Thank you!
In terms of not uploading instrumentals behind vocals and such in your samples to show off the model, does this count when it's playing a song in the public domain already?
ye. don't wanna risk the server getting taken down again
Even for a 90 year old song? XD
Ok thank you!
I would assume though that if I upload it as instead as youtube video, the responsiblity would fall on me right?
Is that a way to get around it?
I say that because it's kinda important for me to be able to compare the original clips to the sample I give
Mostly just because I kinda really want the instrumentals behind it since I'm proud of it XD
I also would like to upload a link to the original video I took the audio from
guys i have a question!
Im trying to use rvc to a recorded voice. I was wondering how you do it? I remember some guy did it with a website
Also is this out of date or anything? Ive seen people use weights.gg recently instead of hugginface https://rentry.org/fdg_guide_new
hmm.. i guess you can upload it as a video w the instrumental on YouTube after getting the role. in your submission you need to have vocals only though, or the qcs/mods will delete your message
Alright that would be perfect. Thank you!
Ayo? @vast quiver level 2 !!! 
I'd be able to still link it in the description right?
Ayo? @wise zodiac level 1 !!! 
yea if you want
-guides
Suggestions for @mossy compass
- Full AI Voice Model Training Guide (local) by Christopher Villanueva
- Model training with Mainline RVC by Raven (ravencutie21)
- AICoverGen Colab Guide by Eddy (Spanish Helper)
- Create a model with RVC disconnected (colab) by Angetyde
why does my voice sound choppy? when im using the voice changer?
Hey how do i deepfake images perfectly?
Anyone knows the software or anything to do so..
Send a screenshot of your settings in #🔍│help-w-okada
okay
wym by deepfake? Make completely new images or modify one? Also a deepfake will never be perfect
in that channel?
Yes
i cant send it
Ayo? @elder willow level 1 !!! 
I want to swap face with someone.
Yeah it should be a good one.
Do you know anything about it?
i sent it
instrumentals would mask the voice quality to assess in #1159514067187277865
Yea you're right. I'm going to upload some bare vocals and I'm already working on it.
it's easy, just upload the converted sample which is untouched (no reverb, effects and shit)
I'm aware I'm doing that.
Are we allowed to have two demos?
Facefusion for swapping faces
Sever isn’t really about face deepfakes so don’t expect much support here
But there is guides for it in #1159513888199540817
Done. Got no idea whatll happen now
How to i fix tensorboard in the easygui no dataset available
I train locally so I have no idea.
If you can I'd use a good GPU and just train with that. It's absolutely worth it if you have the knowhow to use it
How do you do that
is it okay if i use crepe?
or only rmvpe?
RMVPE is better then crepe
okay tysm
And faster
what about the monitor?
Set that as your headphones or speakers
okay
Have a GPU that's Nvidia and capable of using CUDA cores.
Is there any way to ask about help when your model's rejected?
They give you feedback
Yea I've gotten it but I'd just like to know on more technical terms what an explination is
Or for someone to explain the t echnical terms to me
I understanding the trianing process and everything just I'm not sure what the issue is and would love to know
@storm meadow can you help me out pleass
Ayo? @prime plover level 1 !!! 
They should tell you how to fix a problem
Or at least that’s what the QCs are told to do
With what?
Yes they told me exactly how to fix it, and I know what to do, but I'd just like to know what the issue means
Or why its important enough to be rejected for
I promise you its not to be rude i just genuinly would love to know
i run the easygui and whenever i click public url tensorboard says no dataset available
Hi all
I created an animated film using free open source AI - Tooncrafter + tutorial for beginners https://youtu.be/bik3pSa7Ny8
What was the issue?
I don’t use tensorboard sorry
ask in #1192011222023950368 and wait for someone who can help you
"waste of rvc zero."
"Reason: the model has some noise and artifacting. please de-noise your dataset using rx's spectral de-noise, then retrain."
Ayo? @vast quiver level 3 !!! 
I'd love to make my datasets as best as possible. I've been making them on my own for a few years for my own little projects and never really thought to upload any until now so I'm doing that with some models. Some of these are quite old.
according to them the audio isn’t clean enough
But since it’s rvc zero I would say wait until another QC
Yea and I honestly think that's not a problem.
Also try clearer audio for your vocals make sure they are wav
The original audio is crisp and exact to what my one is
Ive made sure of that all already
I worked with Talknet 1 before it was thrown out so im used to screwing with settings XD
Wait till it’s someone else who isn’t rvc zero
Whats that mean
Is there anywheres i can show you that the dataset is as clean as possible
I can garontee that "cleaning" the already cleaned audio is going to make it worse
I have RX9 and I can clean it up as it's saying but it'll make the thing sound worse
Its not a bad model I dont think
talking about the guy named “waste of rvc zero”
Not the best qc imo
Oh thats a person? XD
Whats a qc
Quality Control
Oh
So just not good person for it?
Do I resubmit the same model?
the newest is RX 11 and has some new modules and improvements
Ok.
I'm taking audio that is litterally nothing but a guy and a ukelele for 30 minutes. I can garontee its the cleanest possible https://youtu.be/iATTi8-YiC0?si=QF1-TcYBN0vhPiNG&t=71
I've thought of going to it but I don't really ever need it. I might get it though
do you use tensorboard or easy gui
Any of the "spectral noise" of the model is litterally just how his voice is. It's his somewhat hoarse resonance that I think the reviewer picked up as being "noise"
When it's delliberate. I've made sure that's preserved in the thing
Is this because it'll flip to another reviewer
There’s no schedule
It’s whoever wants to do it does it
it honestly depends on who's online rn
hi
is it possible to recreate instrumentals using ai ( with referencing ) like mp3 or mp4
idk any websites or tools
Oki.
I just garontee this model is exactly as I've made it delliberately. I've spent months on this thing to make it happy for me XD
If they based it on the demo, I would KINDA understand if they rejected it because it sounded like model artifacts when it was really just not the cleanest inference audio for the demo
Ayo? @vast quiver level 4 !!! 
Ребят,а тут есть модель лосяша из Смешариков? Найти не могу.
Guys, is there a model of the elk from Smeshariki? I can't find it.
why
does the v2 app works with v1 model?
Hello I am Guillem
Hello to all
Haloo
Hey
what does a .index file even do, for some reason when I made one of my models I couldn't find a .index file but the .pyh file still worked fine as an ai voice model :/
It in simple terms adds to the subtle inflictions and timbre of the model by adding samples of the real dataset into the mix of the AI.
The base model I think already does this to some point but the index file lets you control how much is added
So can't I just replace it with the default model
hello rookies
Greetings
hello how can i create model of AI voice
how powerful is your computer is the first question
specifically the vram
and gpu brand
What is "test" for the new RVC
Guys, I cannot make a tulu ai cover, there is gradio.live, I add a link from there, I say download the model, it either gives an error or says to complete it, how can I solve this?
use this instead
Best selling ai singing voice
How much is the digital one? Is it cheaper or the same price?
uhh @quartz roost help me out here
Of course, when it comes to SV, who do we got a call
Ayo? @dapper drum level 24 !!! 
iirc the jp demo version is free but rest paid
true !
Yo @elder willow did you try to do AI training?
hi i made a model and want to test it
Ayo? @south gale level 1 !!! 
Where i can do that?
hello fellas
Hello
How is it going y'all
I remember once I used ai image generator
its logo was like a wizard
there's a free lite voicebank w only 1 pitch for free :p
Ayo? @tidal jetty level 1 !!! 
isnt that leonardo.ai
thank you my friend
Glad I could help :)
Ayo? @elder willow level 2 !!! 
what program
Ayo? @sour idol level 1 !!! 
w okada
I downloaded one version and it didn’t lag, but when I downloaded the new version it started to freeze, and I forgot the previous version
https://rentry.co/VoiceChangerGuide has the downloads for the NVIDIA version
EOL - No further Updates
Github - Blanc-dot
Discord - Blanc_dot
Despite being end of life, most if not all information has not really changed, so should be very accurate until actual new stuff comes out.
Other Links
Antasma's Local Error Fixes
Antasma's Colab guide
Sushi's useful Links - You need...
ehhh, #1159290752195633273
https://docs.aihub.wtf/ has everything you need to know
Last update: Mar 10, 2024
okay
hey guys
does anyone here has messi and mr beast ai model
You can search rvc ai voice model:
- #1175430844685484042
- #🔍│find-models
- https://weights.gg/
- 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/
if there isnt one, you can:
- #1159289738314919936
- #1191429836321849435
- make it yourself with our docs guides https://docs.aihub.wtf/
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.
At the forefront of innovation as an open-source ecosystem that hosts cutting-edge AI voice cloning technologies.
Last update: Mar 10, 2024
all sites 🔥
any colab links?
-colab
Suggestions for @tough palm
- Applio, by IA Hispano Google Colab
- RVC Disconnected, by Kit Lemonfoot Google Colab
- RVC Mainline, by Hina Google Colab
- AICoverGen-WebUI, modded by Hina Google Colab
- AICoverGen-NoWebUI [English], by Ardha, fixed by Eddy, Hina and Gdr Google Colab
- AICoverGen-NoWebUI [Spanish], credits to Eddy, Hina and Gdr for translating and fixing Google Colab
- Ilaria RVC, by thestingerx Google Colab
- EasyGUI, by rejects Google Colab
- UVR5 NO UI for Google Colab, by Eddy Google Colab
hello
ello
F
:'c
banned
in Minecraft
develop rvc v4 🔥
real
fading away -- im on data couldn't see shit in gifs search
Yo guys whoever typed in chat first is gay
@tired flume
@tired flume @tired flume
@tired flume @tired flume @tired flume
@tired flume @tired flume @tired flume @tired flume
I know where u are you..
You typed first after you sat that rule. Technically its you that is gay
I’m immune
So you typed first so now ur dating James Charles
Stinky boy
Onion boy

Sorry man. I don't see "I'm immune" in this statement
Bro how long does it take for you to type
Ayo? @exotic nexus level 1 !!! 
Bro takes ages
My phone is glitching
Types on its own
I smell 🧢
My screen is broken and it sometimes closes my app. Sometimes types twice
why the fuck would you spam ping this much?
F
I just wanted to talk and why would you curse at me
Jeff bezoz wants some attention
Your not Jeff
Who wants 20 dollars cash app

you can have an AI Hub coin if you want to
1 AI Hub coin = 0 $
deal?
wait yall friends?
chi-
Sounds like a good deal
CHICKY COIN VS AI HUB COIN
How many can i get
chicken coins
skill issue
u just dont have that chicky coin mindset ngl
as many as you want 
Send them to me.
I want yes
I mean I said there were worth 0$
Have a good week chat ^^

I'm rich now. What do i do

Sadly i can't buy them with ai hub coins
how many ai hub coins when does the
hey
yo i need someone to help me with the CNNs
ai bub
hi
hi
us bro us
wait what happend to the tune option in the rvc voice client?
Ayo? @steep quarry level 1 !!! 
You also need someone to create those?
has there been a update?
I can't go to the ai voice site anymore
Could I maybe get some help and explonation how to get there the right way?
Hi chat
oh I got it
HI CHAT
hi alot of things changed in the ai voice web where do I need to put the link for the voice now? it became alot harder I don't quite understand it
I can't show a pic sadly
can a d & g file mimick the dataset? i'm trying to get high notes to work on a model and the d & g files i'm using for a model have high notes in it
for Ilaria RVC you don’t
Hello
AYO
Trying to make models or covers?
covers
hello
https://huggingface.co/spaces/TheStinger/Ilaria_RVC use this instead
Hi
I have a question for yall, in your opinion, do you think this server the BEST voice changer? (If you know what I mean..)
Realtime?
Or covers
Realtime.
GPU?
1 Second.
how do i get illaria's voice changer?
Ayo? @elder willow level 2 !!! 
i already did the kofi thingy it showed it in my gmail but i cant find the link somehow
hey, can someone send me a good working collab?
Covers or making models
Use a hf space with ZeroGPU if you are gonna make covers
👋
yoo
I wanna make automated AI shorts, Is there any tool that is free and can let me download the videos?
covers
https://huggingface.co/spaces/TheStinger/Ilaria_RVC use this instead
what's the current best UVR mode for vocals and instrumental isolation?
thanks bro, i'll try
can someone tell me plz
Download videos as in
Like automated shorts or like background videos
automated shorts
Ayo? @waxen quarry level 1 !!! 
can someone help
bcuz most of the websites which make automated shorts ask for their subscription when you try to download em
my shi wont work
!howtoask
How To Troubleshoot 
- Don't simply mention your issue, like "
my rvc is not working". - Describe the step you are on, what you're trying to do, the RVC you're using, a screenshot, etc.
- The more context, the better.
- 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.
- 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.
You can probably find a alternative on GitHub for shorts automation
Or see if you can download the file they won’t allow you to download via inspect element
can you send a trusted one
This might work maybe?
Dunno I just found it
ohk
there is a colab version linked on that github tho
You might need api keys for it tho
baana
how do you tell me how??
I wanna download it through inspect element
someone plz tell how
Depends how the website handles videos
But you can probably click the video frame and find the link attached to it
is 15 min dataset any different from 40 minutes?
15 minutes for a RVC dataset should work
40 is a bit overkill
they use all the text and effects as different media so we cannot download it 😭
I was using smartshort.co
Screen record it
What’s stopping you
If it has a watermark inspect element the watermark and remove it
Delete it
Ayo? @waxen quarry level 2 !!! 
Inspect element
Click the mouse button top right
The click the timeline
Then delete it
Or alternatively you can just crop out the timeline in a video eidtor
(Also if anyone asks you to send you anything from the networks tab on any website they are probably trying to get your account)
why am i hearing noises in my mic when running the voice changer
what do you mean by send you
it’s not related but if someone says “send me this from inspect” don’t do it
They are most likely scamming you
Make sure you know what your actually doing in there
-colab
- Applio, by IA Hispano Google Colab
- RVC Disconnected, by Kit Lemonfoot Google Colab
- RVC Mainline, by Hina Google Colab
- AICoverGen-WebUI, modded by Hina Google Colab
- AICoverGen-NoWebUI [English], by Ardha, fixed by Eddy, Hina and Gdr Google Colab
- AICoverGen-NoWebUI [Spanish], credits to Eddy, Hina and Gdr for translating and fixing Google Colab
- Ilaria RVC, by thestingerx Google Colab
- EasyGUI, by rejects Google Colab
- UVR5 NO UI for Google Colab, by Eddy Google Colab
.wk
👑 dranix - 2067 plays
2. yucc - 1079 plays
3. homo - 859 plays
4. josh - 833 plays
5. wilq - 592 plays
6. yeresin - 394 plays
7. H.K_HighKickin☪_ (GLOsama) - 334 plays
8. fantuh - 287 plays
9. angelito - 285 plays
10. luminal - 277 plays
11. epilogue - 261 plays
12. phigglebottom - 175 plays
13. inhale - 165 plays
** 14.** gilbert - 133 plays
Crown claimed by dranix!
can u guys send for me the voice changer link???
Ayo? @thin crescent level 3 !!! 
how do i fix delay
Hi fellas, i don't suppose anyone is able to gimme a link to an arxiv paper on RVC? I've tried looking for the original paper but can't seem to find anything. Help would be GREATLY appreciated.
Edit: I've tried training and cloning with the webui already, but would lvoe to read the actual paper
-rt
This interaction has expired, use the command
/guides realtimeif you wish to see it again.
ask in #1192011222023950368 or #🔍│help-w-okada
hi
Ayo? @cerulean pine level 2 !!! 
how can i get model master
hello ?
anyone help me? How can I create my own voice model ?
I practically don't know English, I'm using Google Translate 😦
Ayo? @torn rapids level 1 !!! 
-guides
Suggestions for @torn rapids
- Full AI Voice Model Training Guide (local) by Christopher Villanueva
- Model training with Mainline RVC by Raven (ravencutie21)
- AICoverGen Colab Guide by Eddy (Spanish Helper)
- Create a model with RVC disconnected (colab) by Angetyde
hey everyone
I was wondering if someone could help answer a question or two for me... i am completely new to all of this and i am a bit lost
There isn't a paper on how RVC works, sadly
Ask away
How do i fix gradio download model error??
What was the model link?
@gray tiger Please help, why do I hear myself when I connect my Skype? My virtual cable is vb-cable. Please help me. What i am doing wrong?
it seems like you have a loop
make sure the output in your pc is set to the speaker
But its not working fine. Can I send you my Sound settings?
can someone do model with xraxenikk?
thx
One message removed from a suspended account.
Vote Booster: Vote now for a 10% boost. https://arcane.bot/vote
✨ Tip: Use /card to modify your rank card
close
yo uh just a general question does this work for windows 11 im using it and it keeps saying Looks like there's a bit of a problem. and i have to initialize with out reloading anyfixes
Ayo? @main vector level 1 !!! 
don’t see why it wouldn’t
real, not fake
why evfery time i try to change the voice it just sends me to the weird initalize page
purple
.
!
@orchid slate@latent hedge Where do I get a model in VTube Studio?
@latent hedge I do not have any type of electronic payment
No one told me that when i have a second discord account. I would have to remember 10 other different aspects of that e person
Can you make a model for Sargon of Akkad, Hamu Rabi, or Qalqamish @latent hedge
Ayo? @grave bobcat level 2 !!! 
And that i can't stay on that account otherwise i will forget my main. And lose 10 aspects of my main... I'm getting ripped apart
@hollow crescent Don't curse
@hollow crescent Don't curse me
Who can make a model for me Sargon of Akkad?
Satoru Gojo, I can't wait to have your feet facin' my ceilin' With my tongue deep in yo' uuas while I kiss all on yo' dieck 😣
this is the first thing i see in this server
does anyone have any fast training rvc?
Hi
how to get perms to upload models
yo wassup everyone can you guys DM me the most realistic female voices that youve found? Thank you! 😇 ill return the favor and give you the ones ive found!
Hi
whats the difference between one-click training and using train model?
one click training ain’t good
how does it work
haven’t heard one click training in forever wtf
basically it’s the easy way out of doing all the training steps
you just click and you don’t gotta do anything else, that’s what the intended purpose was
no. It just clicks 3 buttons for you
eh hem
\
Hi, guys may i please ask a question: i know w-okada is the tool for realtime voice changing but which tool is used when you want it to be not realtime?
hi
what do you do if cuda out of memory?
what gpu
RTX3060 6G
strange, did you install everything?
can someone tell me what ai this is https://www.tiktok.com/@luxoper_/video/7360772978205805856
Ayo? @rotund warren level 1 !!! 
^^
can you ban Анальный пират real fast he's showing porn on webcam
here is discord id 716962410656694322
@wooden jolt
Solo estoy aquí para pasarmela bien y crear cosas para que la gente se dvierta tanto como yo lo hago
Is there an AI for changing song genre/remixing?
preferably with a UI
of some sort
hi @wooden jolt can you ban @peak dome for being singaporean
WHAT?
done
Ayo? @lethal flax level 3 !!! 
thank you
so, basically, racism?
We hate all races equally here /nsrs
Is there an AI for changing song genre/remixing? preferably with an AI
An ai that remixes?
idk of one
yes, that or changes style, while keeping chord progression and vocal speed
-colab
- Applio, by IA Hispano Google Colab
- RVC Disconnected, by Kit Lemonfoot Google Colab
- RVC Mainline, by Hina Google Colab
- AICoverGen-WebUI, modded by Hina Google Colab
- AICoverGen-NoWebUI [English], by Ardha, fixed by Eddy, Hina and Gdr Google Colab
- AICoverGen-NoWebUI [Spanish], credits to Eddy, Hina and Gdr for translating and fixing Google Colab
- Ilaria RVC, by thestingerx Google Colab
- EasyGUI, by rejects Google Colab
- UVR5 NO UI for Google Colab, by Eddy Google Colab
wassup
Looking for an AI to remix/change genre of song
How do I make it only detect my voice and nothing else
there isnt, although suno ai is a thing, just that you can create songs of any genre
with prompts
How do I make it less laggy
Ayo? @elder willow level 1 !!! 
💀
erm
.
where tf is the pitch at in the voice changer
It's labelled 'tune' in w-okada
Idk what exactly you're using
Im using this thinga mabob
oh i dont have image perms
Hey can anyone convert my script to celebrity voices like messi and mbappe
DM me if you can i will give you credits in the video
mabob? lol
damn that's a shame, thanks for the heads up dude. I'll look around the code in the repo and try to see what's being done under the hood then
Ayo? @thick blaze level 1 !!! 
a
What to do if “trail” sounds from time to time in the microphone
hi
hi
в
.
hi
Where do I send ai music?
Ayo? @tight totem level 1 !!! 
Hi
Sahil
-realtime
This interaction has expired, use the command
/guides realtimeif you wish to see it again.
Ayo? @ruby vessel level 5 !!! 
hello
Hello
Hello
Hellonu ula hamsi tuttum sesni
😞🥶😢😞🥵😞😭
3133331331312333133131333131313131321111333
31313131313131313131331313311413131313133323113213131
Include Illaria Zero in the -hf command.
napim
Ayo? @frigid thunder level 1 !!! 
Bok
Is anybody interested in AI dubs in Slavic languages?
It's meant to be a huggingface space brah
use -hf or smth
Alrighty, let us know how that goes!
hey im new to this, is this rlly just a 1-2 process?
ello
Ye
Separate the vocals and inst(remove reverb, separate back vocals) and then convert
Question, anyone here using gtx for training?
Hi guys 🤗
Hi
@finite void, I have found 1 results that match your search!
I ever used 1660 super for training on the old rvc 0717 beta and mangio before, with batch size between 3 or 4
that iirc
Trying to piece together what gtx tend to use or fallback to
oh yea, thx!
Seems like 117 is the go to and only if failed ( some 40xx cases I suppose ), it's 118
Can someone send me Fabrizio Romano AI voice?
it is 118 on latest mainline rvc, and it's what I ever used for training with RTX 4070 pc
Hmmm, not sure why the bump
already 2 4090 users required 117 compared to 118
Guess some setups are funky or some weird shit, honestly hard to figure it out why one system prefers 117 over 118 despite having same hardware, oof
lol
hey, do you have any online RVC programs to train? begginer friendly if possible
Ayo? @solemn wren level 2 !!! 
idk which channel this belongs in or if im even in the right server but how do people do those deepfake video things where they make a character/human move or dance from a photo
does sb know what UVR model is best for vocal/instrumental isolation for now?
Hello
Hi I am Usagyuun Bot
Can I make the voices I created somehow read a text I give them?
Hi there
how to train rvc?
Yes its called text to speech, tts, RVC isn't natively made for TTS, but some forks such as ilaria rvc mainline & applio have built in tts (using Microsoft Edge TTS to make a generated tts audio, which i suggest you to choose a tts model that is the same gender and language of the rvc model you wanna use, and then convert it with rvc)
NOTE: RVC isn't as good as GPT So Vits for tts, but gpt so vits can't use rvc models (and viceversa), and its only limited to: english, chinese & japanese
If you wanna do tts locally (if you got a good pc):
- You can find Ilaria RVC Mainline in #📰│dev-updates message
- While Applio in our docs
If you don't got a good pc you can do it online:
-
Ilaria RVC Zero (Running on A100 GPU, free fasted rvc on cloud) and the guide
-
Use Applio Colab (with google colab T4 free daily limit gpu)
-
if you don't wanna use edge tts, you could try another tts ai in https://discord.com/channels/1159260121998827560/1212368971127590922 and use the output as an input in rvc
Last update: Apr 01, 2024
Table Of Contents Introduction Model Loader (Download & Upload) Inference (use RVC AI Voice Models) Settings (Inference) Ilaria TTS Introduction Ilaria RVC Zero, is an RVC (Retrieval-based Voice Conversion) Fork made by Ilaria & mikus, running only on Hugging Face Spaces, it’s called this way...
Last update: Apr 01, 2024
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.
do you have any websites to train?
how many minutes and how many epochs does it take for a perfect voice clone
10/300
In the guide its said there is a cloud way, you can try:
Last update: Apr 01, 2024
Last update: Mar 8, 2024
hi i think
It's suggested 10 minutes, about the epochs, there isnt a perfect amount, u need to use the tensorboard https://docs.aihub.wtf/rvc/resources/epochs--tensorboard/
Last update: Feb 10, 2024
Not 300 epochs, it depends
Hello?
Ayo? @strong oracle level 1 !!! 
We dont use kits, its greedy, we use rvc v2 https://docs.aihub.wtf/essentials/how-to-make-ai-cover/
Have the audio file of your song ready, & let's extract the vocals from it with an audio isolation software.
Ohky? Do i find RM model here?
how many epochs do I need for a 10-minute dataset?
RM ?
There isnt a perfect amount, read the guide about the tensorboard
tensorboard on linux?
Yeah
can someone hop on vc and help me train a model please?
Cuz I searched for it on Apollo but I didn't get it
How's life
I dont know much of local as i do it on cloud tbh, u could try by the guide but im not sure, could try asking in help channels
You can search rvc ai voice model:
- #1175430844685484042
- #🔍│find-models
- https://weights.gg/
- 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/
if there isnt one, you can:
- #1159289738314919936
- #1191429836321849435
- make it yourself with our docs guides https://docs.aihub.wtf/
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.
At the forefront of innovation as an open-source ecosystem that hosts cutting-edge AI voice cloning technologies.
Last update: Mar 10, 2024
??
you can try searching the models in those sites
i have an AMD gpu and apparently the directML version of the voice changer works pretty damn bad on my pc
suppose 1 fps but in terms of audio if that makes sense
I have an RX 6600
yall have any ideas what to do?
For directml, models require export to ONNX
But you can use modified version that's much more optimized and doesn't require export to ONNX with directml
https://github.com/deiteris/voice-changer
リアルタイムボイスチェンジャー Realtime Voice Changer. Contribute to deiteris/voice-changer development by creating an account on GitHub.
can someone hop on vc and help me train a model please?
Ayo? @solemn wren level 3 !!! 
there's no comparative downside to the modified version i suppose, is there?
thanks for the info and link tho man
Basically, no. It's mostly the same since it's based off the original, just performance improvements are added and some UI parts may be a bit different
does it work as well as its nvidia counterpart? (the original version basically)
Well, unfortunately no. Nvidia still performs better in general
There're few videos in readme, you can see that even gtx 1650 laptop performs about the same as rx 6600m
Well, rx 6600m has seen a lot of improvement still 😄 It barely managed to get 200-250ms latency, had huge CPU usage and consumed more vram (around 2.1GB) in wokada version
guys please i need help with training a model can someone join the voice channel and explain to me how to train a voice and then post it on hugging face?
Hi
Hi
Does anyone speak Chinese?
How do you use ai voice models for text to speech? Because all the tutorials I can find are either just teaching you how to make an ai voice model or use one for a song cover. But I want to use one I downloaded for text to speech
It has an index and pth file
Ayo? @tough palm level 2 !!! 
Use a TTS tool to generate an audio, then you can just convert with RVC
https://huggingface.co/spaces/TheStinger/Ilaria_RVC this is pretty decent, since it has built in TTS
hello i put the url link and i get an error
probably an outdated colab, use the thing i sent above if you just wanna do covers
alr ill try
https://docs.google.com/document/d/1YbXcLFPaGjhOdG5NFkK3QrucCEpHZBwFUxkeMO8aB18/edit guide for it as well
Table Of Contents Introduction Model Loader (Download & Upload) Inference (use RVC AI Voice Models) Settings (Inference) Ilaria TTS Introduction Ilaria RVC Zero, is an RVC (Retrieval-based Voice Conversion) Fork made by Ilaria & mikus, running only on Hugging Face Spaces, it’s called this way...
thank you
You're welcome :)
im getting horrendously high amounts of delay
on RX 6600
cpu is ryzen 5 5600x btw
23k ms delay
peaked 34k ms

UPDATE : looks like the default models in w-okada dont have this issue
the delay is normal
Hi!
Are you looking for help? you can ask in help channels
also we have #1159600809332453437
Ayo? @elder willow level 1 !!! 
Google Colab gives T4 GPU with around 4 hours daily limit, just login and you will have the gpu, about workarounds check #1213586188091523075
Kaggle gives around 30 hours weekly of P100 and T4x2 GPU, but you need phone number
-kaggle
- 🍏 Applio RVC by IA Hispano
- ✨ RVC Mainline by Hina
any idea why a voice suddenly changed and got worse? same settings and model but it sounds like I've chainsmoked for the past 20 years straight now
Ayo? @daring ibex level 1 !!! 
hi
- 🆕 Ilaria RVC Zero, by thestingerx Huggingface Spaces
- 🆕 RVC⚡ZERO, by r3gm Huggingface Spaces
- Applio, by IA Hispano Huggingface Spaces
- AICoverGen, by r3gm Huggingface Spaces
- Advanced RVC Inference, by r3gm Huggingface Spaces
- RVC v2 Huggingface version, by Clebersla Huggingface Spaces
do i really need to install python and pytorch for this? https://huggingface.co/wok000/vcclient000/blob/main/MMVCServerSIO_win_onnxdirectML-cuda_v.1.5.3.18a.zip
🎙️ Realtime Voice Changer (Local)
Are there any software out there better than VB-Audio that's less complicating? Even if its premium
For RVC online check:
- Ilaria RVC Zero which is an huggingface space running for free on zero gpu, so A100 which is 11 times faster than a T4, if you want only inference (use the models, make ai covers)
- Use other google colabs for inference and training (using colab free daily limit T4 gpu) that you can find in our docs
Also don't promo out of #1159290752195633273 , i will delete your message for that
Have the audio file of your song ready, & let's extract the vocals from it with an audio isolation software.
I personally still use the astra labs bot since it's easy but the wait time sucks sometimes
VAC-Lite
Hello ! I don't know if it's good place to ask but i want to make Turkish cover of an Korean song,i splitted vocab and music already and translated the vocab,but how can i make a voice sing it in Turkish ?
deepfaking
https://youtu.be/es9JXZxmDkk?si=Up-A3382yQ-53lHT ong this shi is just brainrot
hello
It should be. 😏
the ai just straight up refuses to recognize small audios
how do i fix that
(infering btw)
i'm getting old
cope with it :3
WrOnG, Its a LoLi, ShOtA AnD FuRrY CoMmUnItY
Skittles are good
funny how society changes overtime, if you said that 2 years ago. you would be in the FBI black list and banned
HOW CAN I COVER THIS SONG WITH MAMOI VOICE
Then why u mad?
SORRY MOMOI
Ayo? @elder willow level 1 !!! 
What’s your reasoning
What did they do to you
Explain.
And did it ever hurt you or do anything to you?
No.
ga
You can disagree with something without being hurt by it
No since I don’t eat moldy food
With that being said, it is not necessary to be hateful
It's sad, I hope you're doing good
Seek positivity friend
what
hey
I AHTE STUPID GAME HACKS ESPECIALLY THE ONES FROM VISONMARKET
Do you believe in this gender thing theory ?
Let people be happy
You belive that people can have "genders" other than male & female ?
Ayo? @elder willow level 1 !!! 
Yes, I am just asking a question
Oh ok then why do you need to precise your gender in this way "he/him" ?
gender is not self defiant, otherwise its mental issues
that's my opinion.
(i've been waiting 2 years to say this sentence)
Let people have opinions
It’s not required
I agree
I think society fell into madness a few years ago
I don't know what happened but we became overly laxist
Like "let people be happy !!!"
yeah I partially agree but people should not harass people who believe so
"it's okay to feel like an helicopter !!!!"
"it's okay to feel like you're a sponge (;"
"it's okay to be fat (-:"
No, they're just sick
as long as they don't spash it everywhere and waste govement taxes on useless flags all over the city, then i'm with you
https://youtube.com/shorts/eXf8rUqEiPA?feature=share check this out
And it's sad that we encourage sickness today
🤑
Of course, no one harassed anyone here
@elder willow:
Oh ok then him
Not me, I don't like the LGBT community but I don't care about their life
Hahahaha
btw 2 years ago. this happened alot. and it was also tough in school (parents were mad, cuz they introduce sexual stuff to 7 yolds). they had the right to be mad.
It shouldn’t be forced on anyone
Yes then it shouldn't be presented to kids
I think that is completely wrong
Inviting queers to talk to kids
If you say the same thing about sex, yes
i got banned on a discord server 2 years ago for speaking up like this
never got to this reply
Sex also shouldn't be presented to kids at an early age
I think the problem with LGBT is just the over-popularity
We don't need to shout our sexual orientation on the streets
No one says "HEY I AM HETERO"
it shouldn’t be hidden but it shouldn’t be forced onto anyone/thing
Ayo? @elder willow level 2 !!! 
Yes, true
Pride is fucking weird, I'm sorry but...I've seen people disguised as dogs with plastick dicks on their head
Ayo? @elder willow level 2 !!! 
It is just degeneracy
we do not claim that as one of our people
I think real homosexuals don't like LGBT
Look at every pride
In a lot of cases yeah
Because it’s always forced onto things and people
I think homosexuality shouldn't be "advertised"
By forcing onto things trying to make it “normal” you are making it not normal
It is overly advertised, in series, in movies
i also have the right to not talk to you, or to treat you differently,
if i cross paths with you.
for me (my personal opinion) its the same way i treat some a overly emo annoying kid.
On TV, in school
It's even a danger for humanity in general, more homosexuals = less kids
Same thing with any minority
Overpopulation:
Give me another example ?
race
Overpopulation is fake
But what is the problem with advertising race ?
Does it have any danger in any way ?
I mean, it's not like race is a way to live
But what is the problem with advertising gay ?
Advertising LGBT *
For a large number of people in a society where everyone is sad
Influences people to join a community just for the sake of feeling good
That's the case with LGBT, you see 10000 kids on TikTok with a thousand colors on their face
Claiming they're LGBT at 12
That’s called forcing
It's just because they feel in a group, it's called group effect
But it is what is happening, it is propaganda
When a 14 yo opens TikTok she sees hundred of people her age talking about LGBT
Which is bad, with other minorities such as race or also makes people left out since they are not apart of it
"Act only according to that maxim whereby you can at the same time will that it should become a universal law." -- Kant
Of course she will be tempted to join them, they're easily influenced
And overpopulation is fake @storm meadow
There is a huge fertility crisis in the USA, in France, Japan
I like how you said Japan
And all over the world basically lol, look the stats
Yeah, I just came back from Japan 2 days ago
except for china
Yes
It's an exception, but bro, they make the 1/4 of earth's population
How dare you say earth is overpopulated lmao
Even Musk said it, it's completely wrong
Earth isn't overpopulated lmao
Never said it was
Fertility rates will see 'dramatic decline' with 97% of countries unable to sustain populations
And you know, even for governments, fertility is important
Less fertility = less workers = less money
Less fertility = less soldiers = weak army
That's why you don't see LGBT in Russia or in China
