#🧬│ai-chat
1 messages · Page 306 of 1
average person knows 0 about this shit
So just find an uncensored version online
so are you never going to use a software just because it doesn't have protection against that even though all you do is sfw no
Again, people will uncensor it and publish it online
report the uncensored version that someone made of ur program 
yeah you can stop it and also gitlab
Stable diffusion is a massive corp
They couldn't take down those models
So goodluck
yeah and civitai is big and has that stuff and no one is stopping it.
ofc i do sfw, i used deepfakes just with ai covers
but trash one image
i just personally dislike the use of ai being used for nsfw in general, when it can have a better use
im not gonna train 10k images just for a 2 min video😭
and deepface lab is mostly local only
its banned on colab and prolly kaggle too as they are both owned by Google
not just for a 2 minute video you do it for unlimited use and also real-time.
with '2 min video' i dont mean that dfl is limited, i mean that im gonna use that deepfake only for just making a youtube video
Yeah local only but that's fine
not everyone has a good pc
then cloud vms like tensordock.
why would i wanna pay for deepfaking when i can do it for free

but the thing is your brain can only think of one video to use it on for me I find a bunch of I things for using it on and stuff and realtime ome.tv middleman with them is fun.
your brain can only think of one video
Im not making a youtube channel dedicated only for deepfaking lol
because quality only is there when you pay something or have good enough hardware.
also have u seen facefusion next
nah i pirate shit
yeah and facefusion dev has shown me other stuff and he agrees one image is not as good as dfm one image Res does not equal DFM Res with is higher at the same Res.
Ayo? @earnest dragon level 19 !!! 
what have i done...
Wat da fck
yeah but you can't pirate hardware and stuff and even a ARC a750 used for under 180 usd can do deepfakes fine.
bro actually revived ai hub for a bit
Is it cement?
nah the infamous pink slime that changed color over time
im just saying that im not personally gonna train 10k images when im not gonna use that model that much
can someone help me figure out where i should request for someone to make a "kk slider" cover of sabrina carpenters song "taste"
yea fr
i got a 10th gen i3 🔥
ai hub
idk much of dfl, but i just cant do things locally
i dont know if theres a channel for that, here there are guides for you to do it yourself and channel to request models
RiP 😔 I used to use 9anime now it went poof
rip animekisa frrr
rip
hey
Nah av1 blu-ray remux video are the goat netflix has lower bitrate.
but no difference
yes there is imaging 500mb bitrate vs 140 bitrate 4k video
on anime
Yo hold on
and also h.266 is coming out
Wait this is wrong server
yeah neflix is not lossless video they have compression and lower bitrate to save money were they can.
Dinner rides voo voo
wifi speed limit:
imagine downloading 500mb/s
cant be me
no it isn't it has been tested that netflix is not lossless because no streaming service except for one is lossless and I have 1gb upload and download.
no that's the bitrate not internet speed
you makje everyone depressive
Just saying the truth that netlfix and youtube and twitch and most of then are not lossless but youtube does a better job then netlfix with video because bitrate and stuff can be higher.
ok
So true way to get good bitrate is to find a streaming service that does direct non streaming service copy with the highest bitrate as the content they show I know one but can't talk about it here.
Shut up n....
whoa whoa whoa, chill..
whats the realm invite code i want to join
boyk1sser
ok thank you im joining the realm
Ayo? @stray wing level 1 !!! 
Cyberbullying is wrong because it inflicts emotional and psychological harm, undermining a person's self-esteem and mental well-being, often leading to long-term negative effects such as anxiety, depression, or isolation, and can create a hostile online environment where individuals feel unsafe, unvalued, and disrespected, perpetuating harm across communities.
ok
I disagree with you because your perspective overlooks key evidence and fails to consider the broader context, which is essential for a balanced understanding. While I respect your opinion, the facts and reasoning I've encountered suggest a different conclusion, leading me to challenge your viewpoint based on logical grounds.
ok
Saying "ok" repeatedly is often useless because it adds no meaningful contribution to the conversation, lacks depth or engagement, and can create a sense of disinterest or indifference. Over time, it can diminish the quality of communication, leading to unproductive interactions and a failure to address underlying issues.
ok
Saying "ok" over and over is completely useless because it shows you’re not actually listening or caring about what I’m saying, and it’s frustrating to have a conversation where you give zero real feedback or effort. It’s like talking to a wall, and it gets us nowhere!
He has problems
I agree that saying "ok" repeatedly can be frustrating and unproductive in conversations. It shows a lack of engagement and effort, making the other person feel unheard. Meaningful dialogue requires more than just acknowledging words—it involves active listening, thoughtful responses, and contributing to a conversation that moves things forward.
keys
Anyone know of a good music spectrum visualizer free program? Like specterr.
spek
The word "specter" is more appropriate than "spek" because "specter" originates from Latin, meaning ghost or apparition, and it conveys a sense of mystery or foreboding. "Spek" is a non-standard spelling that lacks historical or linguistic significance, making "specter" the correct, meaningful choice in formal usage.
IT'S "SPECTER," NOT "SPEK," BECAUSE "SPECTER" ACTUALLY MEANS SOMETHING! IT COMES FROM LATIN, MEANING GHOST OR APPARITION, AND IT HAS REAL HISTORY AND MEANING BEHIND IT. "SPEK" ISN'T EVEN A REAL WORD—IT'S JUST WRONG! WHY IS THIS SO HARD TO UNDERSTAND? LISTEN!
THANK YOU, TOOK YOU LONG ENOUGH! I’VE BEEN SAYING THIS FOR AGES, AND IT’S ABOUT TIME YOU FINALLY GOT IT. IT SHOULDN’T HAVE BEEN THIS HARD, BUT HERE WE ARE. AT LEAST NOW WE CAN MOVE FORWARD, SO THANKS FOR FINALLY LISTENING AND DOING WHAT NEEDED TO BE DONE!
I’m sorry for overreacting earlier. My frustration got the best of me, and I realize I didn’t handle the situation as calmly as I should have. I value our communication and should have expressed myself more thoughtfully. I appreciate your patience, and I’ll work on responding better next time.
Yo
I TAKE BACK MY APOLOGY, LOOK WHAT YOU’VE DONE! YOU CALLED ME "MRS. PRESIDENT" AND NOW I’M EVEN MORE INFURIATED! HOW DID YOU MESS THIS UP SO BADLY? I’M THE PRESIDENT BUT NOT A WOMAN, AND THIS ISN’T SOME JOKE! YOU’VE MADE THINGS WORSE, AND NOW I CAN’T EVEN DEAL WITH THIS ANYMORE!
Ayo? @stray wing level 2 !!! 
My bad
💀



























































































































Oh my middle son
Shit
Moonwalks run away
Yo
skibidi toilet

We’re so back baebae
hi
Hello greetings salutations what’s cookin’ good lookin’ 👋
Ayo? @viscid agate level 1 !!! 
Thoughts on your deepfake with Kamala Harris 💭🤔
#33339 😭
agreed

yay
Hi
KAKYOINN! 
i will pay some one who can make a AI cover for a song message me
may i ask what request for the song and ai voice you're looking for? i dont have experience, just askin
why do i have a robotic voice for no reason on every voice i have
lil tecca and the song is called thanksgiving it’s unreleased there is a LQ snippet of the entire song i have the beat tho
just need the AI vocals
have no idea what any of those things are but i bet its sick, good luck to ya 💙 👍
Ayo
I can help
message me
Ayo? @gray dust level 1 !!! 
I wish there was a website version of Falltalk instead of just the file version.
what i like them
Ayo? @elder willow level 1 !!! 
Which model is good for code development? (specifically web-oriented languages such as HTML5, CSS, Javascript, etc.)
i have this ai im training to walk in unity and idk it just doesnt do very well so should i give it FEET?
-realtime
This interaction has expired, use the command
/guides realtimeif you wish to see it again.
🦎🦎🦎
Is the applio colab broken right now
.
guys any way to use rvc on mac pls?
I’m in the middle of trying to install, got it to start locally. Followed the instructions from the video on the applionsite but none of the features on the local applio work. Just get an error
Tried PC too but when I try to run it I get the “do not recognized python.exe I’m stuck
Wonder if there is a working hugging da
it must be because whenever you refresh in the gui, it just says connection timed out
Ayo? @polar mesa level 2 !!! 
So what’s that mean? And the fix?
Ayo? @elder willow level 1 !!! 
@thick spire, I have found 1 results that match your search!
What?
i got no clue, so im waiting till someone finds a fix for it
How long has it been down for you?
at least an hour
@polar mesa Thanks, maybe I’m worrying for nothing then. I just installed it and everything was timing out lol
unless you want some manual works for better quality
Pregunta alguien tiene el link de applio con la versión de entrenamiento con los modelos titanium ?
Ayo? @lavish jewel level 2 !!! 
Hello guys, i want to ask about the tortoise tts, what is the updated github for this? is it from neonbjb or 152334H?
Ayo? @honest sage level 1 !!! 
Just use fishspeech instead
What do i have to type in the ngrok_token box ?
can it use RVC as a model for the speech?
do you mean to make a rvc model or use a rvc model ontop
#📰│dev-updates message
For this one
It wants a token but idk what to type there
And Applio is Down
if you have ngrok account and stuff you would but putnits token in there and stuff.
Ohh
Are there other alternates for Applio
I dont want to create a account xD
I just want to test my trained model
-hf second link
Suggestions for @knotty scarab
- 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
Ayo? @knotty scarab level 5 !!! 
i want to develop something where i can use RVC for text to speech, i have a project that needs to do that by code
not by using GUI
Can anyone help me make a voice model?
Ayo? @slender nacelle level 1 !!! 
anyone know a good place where I can get 3rd party models for UVR? Im trying to find BanditV2 and BS Roformer-Viper-X but I cant seem to find much
Ayo? @tropic linden level 2 !!! 
Hello, new to the server! Once I have downloaded from HuggingFace, how do I use that voicemodel? Just looking for a point in the right direction to learn
kat
Hi folks!
Hello balleater
Ayo? @ionic crystal level 25 !!! 
Does anyone know a remote job for AI Engineer position which is or allows work as you learn principle and require minimal or do not require experience?
Ayo? @faint walrus level 1 !!! 
hello how do i remove the background music so i only have the vocals
@gray dust check your messages, I am a model master. Don't take any requests from unknown users.
hello how do i remove the background music so i only have the vocals
what program you guys use to make voice models?
sorry im new here and i wanted to having fun with my own model but dont know where to start
Guide
thanks
this place have made my life more hell and i dont care
Impossible
Has anyone successfully installed and ran the new SF3D? I'm trying to get it to work but can't seem to figure it out
Can someone make me an AI cover with own voice please?
No
Idk what that is
Ayo? @earnest rain level 2 !!! 
Still dunno it
what is your use for it
It makes 3D models the same way midjourney or dalle makes 2d images
can fish speech using the RVC model for the speech?
I'm not sure of the hardware requirements, but you can try the demo hf space
English
why does my voice sound when i talk with the IA how do i fix it
Hi. Is there a YouTube link for this AI voice tutor? Which can be used in DC
so my mic Is breaking up bad when i play a game or try to use discord, is there anyway to fix this? i have two gpus the voice changer is hooked up to a 1080TI
while i play games on my 4080
I was just using the voice changer with a headset microphone, if I bought a Blue Yeti microphone could it be that the AI voice would sound better?
boh good that you for share
@valid palm ohh cool that is good bubby
That was a question and not a statement
I will start YouTube channel about ai tech today i try to found freelancer man that can help me
okay
You can post in there I bet
We generally don't recommend youtube videos, they're outdated. Are you looking for realtime voice changing, or do you just want to convert a vocal .mp3?
İs there a video chat
I mean we have voice channels and you can turn on your camera in there
Nah i wanna show a vid i took
Oh, you get image/video upload perms at the next chat level I think
What?
Vote Booster: Vote now for a 10% boost. https://arcane.bot/vote
荷兰咯 (hello)
ку
/train
Is there a ai that can give 2d stuff like animes shaders like shadows or something else
i really need angry birds voice rn
already exist
all voices they have is AAAAA
shit takes forever
Hi everyone, do you know how to convert text to speech?
Ayo? @novel nymph level 18 !!! 
Your mom shit
hi there ! Noob here, have a Q regarding image generation, where should i ask ? Thanks !
dead ahhh server
Where can i find the beatzforge PTH G and D files ?
Please what is that mdx model?
iihihhihhhihhii
on god?
on skibidi
german or russia
yo guys how can i stop background noise?
I've been using w-okada for the longest time and it's been amazing as a voice changer, I am wondering, do any commercially available voice changers compete at all?
the architecture
As in the model architecture?
😭 I thought you were responding to me, sorry
Just trying out the voice testing today for the first time. Having a lot more fun with it than I expected to. ^-^
wokada is the best, espcially the newest fork that optimizes performance
men, is the earth flat
does a voice changer exist where i input these voice model and they turn my voice into any character i want
I don't know about this new fork, is there a name I can look up?
Ayo? @drifting pewter level 1 !!! 
This interaction has expired, use the command
/guides realtimeif you wish to see it again.
1st link
Thanks! This is going to be painful to figure out on dockerizing, hoping it's largely the same as the original T^T
edit: For anyone wondering, code is roughly the same for server stuff. Figuring out how to work around CORs should also not be too bad
and if you don't mind an additional question, would fine-tuning my own model be any good? I have access to A100s, and I see that a lot of models only use ~10 minutes of training data. Is this some kind of limit, or just no point in using any more?
its because for making a model you dont need hours of data, 5-30 mins are enough, because pretrains help users to not have to train 50 hours just for a model
pretrains require tons of hours instead
That makes sense, I saw that Titan had a lot into it. If you don't mind sharing, are there any specific tips you have in preparing these 5-30 mins data?
clean the dataset as much as possible and have high quality audio
Right, so these 5-30 minutes should ideally be filtered through manually to remove any unnatural sounds/background noises/empty sound?
Sorry for so many questions on this - I am new to this whole thing and wanted to give it a go! It's really helpful to hear you share on this
there is also uvr that helps removing instrumentals echo and noises
That makes sense! So in essence, for these 5-30 minutes audio, I should use uvr to remove any echos and noises that would not be human voice, and manually curate through to remove any odd noises myself
can anyone help me in rvc
Ayo? @mossy jewel level 1 !!! 
Would there be any other tools you would suggest for data preparation or cleaning?
Hello
U can't leave or I'll ban u again 
some use izotope rx11 but its paid, i personally dont use it tbh
didn't people pirate it
Yeah that's why I said it's not paid app
oh yeah lol
https://www.izotope.com/en/shop/rx-11-advanced/ for sure many people paid 1k here lol
Yeah like for Rx 10
everyone is rich here frfr
Where can I find mel roformer on uvr?
I'm Rich
smh
Vote Booster: Vote now for a 10% boost. https://arcane.bot/vote
i need to level up to get my roles back
Yeah u'll lvl up
Appreciate the insights into this! Last-ish question, I see that Titan is the most popular thing by far when I go through the model catalogue as the pretrained model, would you also generally suggest using that?
did you decide not to leave?
i can give you your roles back
hi
how
guys whats epochs
we can share AI Images from any sources on #1159290752195633273?
How do you make Applio more expressive? I noticed breathing and moaning, yelling and crying all sound broken and glitchy. For singing, this thigs is great!
why do u want rvc to cry and moan?
anyways to answer that, rvc was meant with natural speech in mind
ok, is there a tool that can use rvc files (index and pth files) to do other stuff for more expressiveness then?
Ayo? @upbeat forge level 1 !!! 
usually long datasets are able to be more expressive but still has their limitations, index only forces the model to increase their accent over the original audio in the inference
index for realtime is always bad because usually make models to have worse pronunciation
tldr; rvc can only be realistic with natural speech/singing
can’t do expressions well
hello
is this only for tts or is this for inference too?
if there is a way to use it on inference, is there a settings I should use?
currently trying it out with crepe hop lenght of 1
it's been 620 seconds so far
you can do both
Ayo? @ionic pumice level 72 !!! 
for crepe length, i think it only matters if you use crepe/mangio crepe(?)
how would I go on about making it sounds good then? so far, before trying out crepe (still waiting for it to finish) I tried the default and it sounded really glitchy
Wait, are you using applio’s tts?
inferece right now on applio
Crepe is less pitch accurate than rmvpe, also setting the hop length too low may cause issues
64 or 32 is fine
Tho if your model is a rmvpe one, is going to be better if you select rmvpe
Oh so converting an audio to another audio
You can’t make an unrealistic model to sound realistic, you can only do that if you train a big dataset
biggest struggle is the breathing noises, some songs have heavy breath in between or moaning of sort
Those are the ones I'm trying to patch with
basically do two render of the songs, one as usual, and the second as breathing/moaning focused
combined them in audacity and good to go
Youre using mangio rvc which is extremely outdated
You can use mainline or applio for training
I recommend mainline because is more stable and less buggy, and for some people training is faster
- How to use RVC Mainline Colab by Cauthess
- Full AI Voice Model Training Guide (local) by Christopher Villanueva
- AICoverGen Colab Guide by Eddy (Spanish Helper)
- Create a model with RVC disconnected (colab) by Angetyde
Rvc cant do porn
U can get more realistic breaths, but not porn breaths, again, rvc is meant for natural speech, it can do realistic speech breathing but not the other type of breathing

who said anything about just porn?
Besides, to get more realistic breathings u need more audio data
i'm doing s3rl song Hentai next and need it to sound right
feel free to look that up, i'm not posting the link to youtube on here
I noticed rvc cant do breathing well if its too loud and prolonged
But it should be able to do good short breathings
If ur model can’t do short breaths then is a model issue
-docs
Suggestions for @sleek wadi
- How to use RVC Mainline Colab by Cauthess
- Full AI Voice Model Training Guide (local) by Christopher Villanueva
- AICoverGen Colab Guide by Eddy (Spanish Helper)
- Create a model with RVC disconnected (colab) by Angetyde
Use ai hub docs
Hey 👋 if I bless you with sum money 💴
what r u gonna use the money for?
if u dont mind me
Be honest!!! Dm I need to bless 3 people
oh hey i like some of s3rl's songs
Btw doing that is bannable in this server, read rule 1

my wifi wont wifi-ing

how can we get it for free
Thw wrong hole
x
Does anyone know a TTS model that sings instead of talk? Like Suno.AI but no instrumentals
Impossible
Hi
you could use emvoice but that is a monthly subscription but then after you can add rvc on top
hi
ew emvoice
use synthv
cevio
vocaloid6
diffsinger
Vocaloid6
who wants to make me a model
Ayo? @median silo level 1 !!! 
y
z
what
js use okada a this point
Ayo? @amber light level 56 !!! 
Whats that lmao
hello all. I'm a hobbyist who has spent the last year developing an open-source model for generating SNES music (demos here: https://www.g-diffuser.com/dualdiffusion/). looking for a community to share results and resources
thank you
emvoice is the only one that isn't Asian or animal voices that has full vocal range and stuff
emvoice is melodyne'd vocals
yeah but the newer voices are better then the competitors in quality and range.
a realtime ai voice changer, whats uc pg gpu?
#1191429836321849435 or #1159289738314919936 or make it urself
hi people, vivo here
yeah but the quality is a lot better then is others
whatever knocks your your boat ig
you should have it generate files also so that it can be used in famistudio
like all of the others don't have the range and fine tweaking or just are mostly Japanese or anime sounding.
it is trained on and generates raw audio, it doesn't use or have access to any midi / metadata
d
So it doesn't work with the best chiptune daw and also I thought all music from those games is in a format that is compatible with famistudio.
wasn't me xd
i was waiting for your answer
and someone just gave you the roles
@river adder was it you?
heyy, I just got curious, what is a epoch?
🤔
ye
oight
UwU
whats the best natural tts for voice acting a text convo
Ayo? @shadow pumice level 1 !!! 
Last update: Feb 10, 2024
with rvc models?

There are different Text To Speech (TTS) AIs:
GPT So Vits: RVC isn't as good as GPT So Vits for tts, as rvc is for speech to speech, but gpt so vits can't use rvc models (and viceversa), and its only limited to: english, chinese & japanese, if you wanna check gpt so vits instead, read https://docs.aihub.wtf/tts/gpt-sovits/
Freemium 11labs: A easy way to do TTS is https://elevenlabs.io/, you can't use RVC model on this but its a mostly premium easy way for good quality TTS
RVC is natively for Speech To Speech, but 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)
If you wanna do tts locally with RVC Voice Models (if you got a good pc):
If you don't got a good pc you can do tts with RVC Voice Models on cloud:
-
Ilaria RVC Zero (Running on A100 GPU, free fasted rvc on cloud) and the guide
-
Use Applio UI Colab (with google colab T4 free daily limit gpu)
-
if you don't wanna use edge tts, you could try another tts ai from our tts index and use the output as an input in rvc
Ok
@signal flint
edge
I love edging
Hello everyone! Is there a voice to voice converter from RVC on some collab document?
Ayo? @soft hemlock level 2 !!! 

what🫥
any help me?
you mean, realtime voice changing on google colab for calls?
ask in help channels
I have a problem with the Voice Changer and the sounds from my PC are also played on it.
Does anyone have the architecture of the following model 4x_DigitalFrames_2.5.pth??
hey
Hiya im new, nice to meet you all
is this the claude ai server
say ur pc gpu and what voice changer u are using in #🔍│help-w-okada
i isad
I feel like this should include fishspeech
no
what program do you guys use that's free for the voice changers
no, i mean changing voice from recording to recording, not online
Hi
where can i get models for real time voice changer
Ayo? @elder willow level 1 !!! 
-hf second link
Suggestions for @soft hemlock
- 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
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.
Does anyone have the architecture of the following model 4x_DigitalFrames_2.5.pth??
do they have one
pick me girl ?
Can I be banned
why?
hi
no
why
hi
im new here
i got a bit of a question
why is "ai art" called art? if u just tell a bot to draw it for you?
Hello
why wont my thing launch just stuck on this cmd
Ayo? @gaunt crow level 1 !!! 
i am french
but do you transleate my message please
Comment on fait pour avoire des voix mode
cuz its ai generated art....
First question is do you got a life.
can someone buy me a game for free its cost 8 bucks so if you can buy me it please
Someone should ban this guy cause all he does is beg and beg for a game
Ok
Ayo? @dreamy anvil level 1 !!! 
Gn
.
Any good free online RVC voice to voice?
-hf Ilaria rvc
Suggestions for @deft ether
- 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
Anyone know any good tails (Colleen) Ai Voices?
.,
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/
anyone know why my audio lowers when i load up the ai voice changer application?

Hey is it possible to add in more model voices? Cause I like to have some more voices to work with, like the characters from the Friday Flareon comic, Firday the flareon herself, Aron the Vaporeon, Valance (Val) the blind Espeon and Rin the glaceon, I'd like all the eeveelutions if possible, Jolteon, Flareon, Espeon, Umbreon, Leafeon and Glaceon, there's only Vaporeon, Sylveon and Eevee himself
can you save on google collab so you dont have to redownload everything in the collab over again when cooldown is over
are you asking for people to make models? u can #1159289738314919936 or #1191429836321849435
maybe someone in #🔍│help-ai-art knows
google colab doesn't have persisten storage
unless there was a google colab that saves the whole rvc in google colab, which i dont remember if there was one, and tbh rvc is not small so i dont think it would be worth it
I mean i did but theres like only one good one, the rest are wierd fanmade projects and different language voices
i mean u can use the good one, else u could ask in #1159289738314919936 / #1191429836321849435 or make it urself
there is the flux lora way but that is not for beginners and need to train it on a bunch of images that are similar you want it to extend like.
you can make them yourselfeon, read the guideon: https://docs.aihub.wtf/essentials/how-to-make-voice-models/
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.
YUOGHKBJNKHKIHJGYT
For?
the rvc
MMVCServerSIO right?
i downloaded it from mediafire
and from a youtuber
why would you use a link from a youtuber and which youtuber.
a trusted youtuber called aswproject
Ayo? @vagrant cairn level 1 !!! 
So why u are even asking
real and true
i meant like is it supposed to be 4 GB
What’s the landscape like for getting tracks to Apple Music/Spotify these days?
Still a legal gray area?
trust any link from the hewsnn youtube channel
Ngl I want to wear long feminine socks
they’re good for the winter
How to find model
real
yeah but they're a bit hard to get in and out
From what Ive heard
but his links are not up to date and stuff and he is not reccomending the fork of w-okada which is better
Nah unless they link to the source and not there own link then it will not be up to date No self Promo
but the hewssn youtube channel is awesome
Ayo? @unkempt rivet level 1 !!! 
No Self Promo
i literally don’t care the channel is abandoned and i gain nothing from it
i’m just trolling
that was a joke 
as in i don’t care about the channel
Yeah I get it but still was promo
does anyone know a model with a voice similar to this: https://www.instagram.com/p/C-VjJqMAl4V/ like an old timey tv,, nostalic
p
Hello
hi 🙂
if someone could help me in #🔍│help-w-okada that would be much appreciated <3
a friend of mine is trying to set up their stuff but it seems to not be working so any help would be awesome
it's kinda hard to do restoration on such the lofi effect and some other strange distortions to produce decent quality audio, so no
he is not asking to restore it he is asking to sound like it.
it's easy to do except the transatlantic accent.
voice datasets shouldn't have reverb, distortions, or any other effects, including that "vintage feel" effect nor even the real vintage source
yeah you add that on top after
those are not yours those are hoodem and not good quality
i love ai
but i dont at the same time idk lol
ai voice changers fear me cuz... i can do mario, donald duck, mickey, toad, and tons of other voices for no reason
quick question, in the voice-models channel i cant find any beatrice models instead of rvc, any idea how I could get my hands on some premade beatrice models or if i have to train them myself, thanks
-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
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.
-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
- 📖 How to use RVC Mainline Kaggle by Cauthess
Note: Kaggle limits GPU usage to 30 hours per week.
Hi everyone! I’m new to this platform and was wondering if anyone could assist me with creating a short deepfake video for my wedding. Is this something that can be done here, or should I check other Discord groups for help?
Yeah because people don't train them or know about the Beatricev2 trainer
righttt i see
For Deepfakes my discord is better for that sort of thing this is mainly just for voice this server.
mhm owner of deepface live huh?
No the owner of the DeepAscension Fork of deepfacelab.
oh right what do you do
what
Thanks for the response! Would you mind inviting me to or sharing the link for this Discord group? I'd really appreciate it!
bio
are there any Beatrice v2 models here? (voice changer)
hi guys
Hi lil ballsack
AI tools on the right hands can create wonders
Don’t download from mediafire
Unofficial source, you don’t know what they added or changed in there
Might be outdated too
-rt
This interaction has expired, use the command
/guides realtimeif you wish to see it again.
2nd link if you have mid-high end nvidia
1st list to use the fork if you have a AMD card
Yes it should be around 4 or so gb, ai takes lots of storage
Hi, i have colap pro, do you guys have colap link for the voice modelling ?
Hey guys, I like to catch up with random people with a 15-minute call I do every Sunday, would you like to hop on tomorrow at 9am ist?
😉
-colab
Suggestions for @amber stream
- 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
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.
Rvc gpu when
can someone give me a tutorial on how to make a ai voice model
Does anyone have the architecture of the model 4x_DigitalFrames_2.5.pth
What
Hell no
@narrow flicker how old is u
Chat, what's the best LLM for coding?
hi does anyone know how to do tts except astralabs
Gm good day
Türk var mı
if one administrator see it can i share the link ?
Ayo? @quartz crag level 1 !!! 
Unnecessary ping but ok
Mind sharing this on #1159290752195633273 if you haven't already? This channel isn't the right place sadly
install michaeljacksonrvc.exe
is bitcoin miner
Hello, I am looking to get the voice models of French celebrities, can you help me!!! Thank you
What
Woow how should Benedict Cumberbatchin's voice model be?
Check weights.gg or search in #1175430844685484042 for the specific person you're looking for
Can you share your settings? Make a post in #1192011222023950368
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/
Does anyone have the architecture of the following ESRGAN model 4x_DigitalFrames_2.5.pth??
Hi i am new
Someone has losyash and kopatych from smeshariki?
hi
true, just added that
There are different Text To Speech (TTS) AIs:
GPT So Vits: RVC isn't as good as GPT So Vits for tts, but gpt so vits (few shot tts, which means needs just a lil training for models) can't use rvc models (and viceversa), and its only limited to: english, chinese & japanese, if you wanna check gpt so vits instead, read https://docs.aihub.wtf/tts/gpt-sovits/
Freemium 11labs: A easy way to do TTS is https://elevenlabs.io/, you can't use RVC model on this but its a mostly premium easy way for good quality TTS
FishSpeech: FishSpeech is a 0 shot (no explicit training needed) TTS, if you got a good pc you can use it locally else use their site
With RVC Models:
RVC is natively for Speech To Speech, but 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)
If you wanna do tts locally with RVC Voice Models (if you got a good pc):
If you don't got a good pc you can do tts with RVC Voice Models on cloud:
-
Ilaria RVC Zero (Running on A100 GPU, free fasted rvc on cloud) and the guide
-
Use Applio UI Colab (with google colab T4 free daily limit gpu)
-
if you don't wanna use edge tts, you could try another tts ai from our tts index and use the output as an input in rvc
promo only in #1159290752195633273
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/
wow this is a whole guide, thankss
your welcome, i try to tell everything that can be useful
Hello, I reinstalled my windows and lost mai voice converter
Does somebody have one?
Please
Is Mel karaoke good for extracting backing vocals? Or can I do this where I use the Mel karaoke for lead, but then use something like bve2 for extracting back vocals
mai voice converter ? Do you mean RVC?
Michael Jackson is cooking 🔥
j found this artist
why?
😎
i thought it was a music chat
For the funnies
I'm kidding dude
Yes
I had a local one but don t remember how it was called
Well, either the Original RVC (Mainline) Or Applio whcih is an RVC fork with some extra features (both got same quality)
whats your pc gpu btw?
Rtx 3070 ti
Thank you
your welcome
promo only in #1159290752195633273
nope, applio tts got some options more like applio tts, and different ui, just same quality
Both.
how do I create a model, can you help me please!
Read these two to prepare your datasets for training:
https://docs.aihub.wtf/rvc/resources/vocal-isolation/
https://docs.aihub.wtf/rvc/resources/datasets/
Use this for the training part:
https://docs.aihub.wtf/rvc/cloud/rvc-disconnected/
This is to read the model training graphs:
https://docs.aihub.wtf/rvc/resources/epochs--tensorboard/
Just take your time and understand each part of the process, it's not that easy but you'll get used to it.
Last update: Feb 29, 2024
Last update: Mar 8, 2024
Last update: Mar 8, 2024
Last update: Feb 10, 2024
if I send you a voice that can be heard for 3 minutes, I can make a model, please, I'm not good at it
Ayo? @shadow drift level 1 !!! 
plz
i already pinged u in #✨│ai-help btw
u can make it urself, else ask in #1159289738314919936 or #1191429836321849435
Ayo? @ocean mulch level 1 !!! 
promo only in #1159290752195633273 or else it will get deleted
Me and michael jackson
No one will for this scam in 2024 unless they are really dumb.
hey everyoner
Hi
I Have Made So Many Weights Models It’s Unreal
I Would Upload Them Here, If Possible.
If you can download them and upload them to a huggingface repository, you can get the model maker role and post to #1175430844685484042
Everything that you post in that channel will be uploaded to your weights.gg as well
Oh, Of Course, Man, I Still Have The Files.
I always keep the files :)
yo guys one question
Ayo? @worldly drum level 4 !!! 
#1159514067187277865 is where youll wanna start. Theres a quality control team that will work with you
how to do a text chat like the one in voice models?
like with topics
forum or smth
not funny, cried
hi
hi
hello there
🌄
hi im looking for a paid course for mle( beginner) dm if uou have any suggestions
YOU DID !
Viggle is trash can't count that and imagine getting a post from snapchat
Hello
Hey does anybody know why my voice cuts in and out using w okada?
fallguys is now on phone 🗿
so true
!js Core.settings.put('uuid', 'ююид_12символов')
Stop self promo
Why so serious?
Just one of those self promoters
Yea ik
what
duh
No one is giving you something that's paid for free.
e
what
see i have a sound snippet here
ohh hey can anyone please join on unlimited channel i have a question
but it contains part of MJ's Beat It, can i post that
what?
(yes i will join in a moment)
Ayo? @river gust level 1 !!! 
thank you 🙂
Better join rq boy
what snippet
u can join too bro
What is it about?
It's on Nitro Awards
And i got it on Universium server
What's epochs?
search on google
aaa
Bro this voice changer stuff is hard 😭
Promo only in #1159290752195633273 , everywhere else u sent It Will get deleted lol
Start
Last update: Feb 10, 2024
Thete are written guides here
I'm having trouble with virual audio cable itself
why don't we have a channel for sound clips smh
what about it
npc ahh
boutta shit myself tho
@covert lake i have question
Howto download freevoicevramonline?
I need 1tbvram
Ayo? @cobalt lichen level 1 !!! 
Nah put it in virustotal and stuff and it told me it was for Rickrolling
@timid muskban his balls
How long does it usually take to set up the voice changer inside discord
It's taken me 3 weeks and my dumbass still can't figure it out 😭
Ayo? @fringe haven level 2 !!! 
so easy
Can you help
-rt first link
This interaction has expired, use the command
/guides realtimeif you wish to see it again.
Where are the ai aimbot models? hahaha
Can I DM you abt this
@molten stone i have an idea for kaggle mainline
and is to mute imjoy's output which is very annoying.
yo
?
Can I dm you rq
why?
I can't post pictures here
o ty
just follow the first link
no
Formulário para ser namorada do grats basta clicar no link da minha bio
guys
i need
help
when i use voice changera female voice says Child
on background
I'm at the first link but it isn't telling me where to download it
yes it does it has a part for Nvidia and one for amd
no that's later read and you will see is what you should always do don't skim
Yea I've been trying to figure it out myself for 3 weeks
Anyone got like 5 bucks exra on cashapp
yeah
i dont have cash app
What is that
guys what software do you use when you actually make the ai cover song?
combining source material and ai model
yeah whats ur cashapp dumbass
Beggers in here should be banned
$voltictheamazing
shut the fuck up incel
Ayo? @sharp stream level 1 !!! 
can someone delete this or ban this guy for begging for money
And I’m not begging just asking
and you know it's always a no in discord servers.
Not always
Never said that
white boy
Nah ima do my own thing
Ayo? @trail pasture level 2 !!! 
(i am white as well)
I am and I have a job 👍
yeah thats why you are begging for 5 dollar
Then you don't need money from people because you have a job
Not necessarily I do t get paid daily
yeah you still get paid which is still money
i mean if you gotta sell your body to make money, you gotta make money i guess
selling ass to old men is gross, but u do u
Nah u know from experience I don’t do that weirdo
still want that 5 dollar fuckhead?
Yuh but not from yo weird ass
@ruby moon, I have found 5 results that match your search!
Why do you need it do you make pennies from your job or are just super inpatient
idk man maybe he just looking for attention
does anyone know a voice that gives that old 50's radio vibe like this:
https://www.youtube.com/shorts/e90rfbd_d6E
No I get paid monthly stupid
isn't that what most jobs do which is bi-weekly or monthly
use rvc disconnected and look at ai cover music on youtube's channel and then use in the software replay
Bro ur acting like I am hurting u bruh like u never asked anyone for money
is this fuckhead still speaking LOL
wdym there is no ai music cover on the channel
It was just a question all u had to say was yes or no or do what Eko did
sorry, go up your ass, take a left, then go down the hall
what the hell did i do o-o
be a bit nicer when someone tries to give you advice
Nothing I was using u as good example
not be an asshole
i am not being asshole bruh, just gonna ignore you because i dont need this rn
@signal cairn someone arguing here
No I have only asked for money to eventually have others make money and myself.
LOL fcking loser
So u still asked for money
you begged us for money, we said no, end it
but the person gets more in the long run
wait is english ur first language, i was saying that IM not trying to be an asshole to YOU
i was just messing with you i have no idea
--_--
R u stupid I didn’t beg u never really said no ur just being a dick to everyone
hey dont get lippy with me fuckhead
Ayo? @sharp stream level 2 !!! 
Ohh shiver me timbers I’m so scared shut yo bitch ass up bruh
you have nothing to say when you are asking for 5 dollars LOL
you need something to eat big dog?
you cant afford some postmates big dog?
Nah
Bro who the fuck uses postmates
bro i should have scrolled up bro has no idea about any of this shit
Ayo? @young kraken level 2 !!! 
I asked for 5 bucks all u had to say was no



AI HUB Docs