#🧬│ai-chat
1 messages · Page 155 of 1
no, sadly
i'm a lame nerd, it was just a mutual friend
i'ma boot into windows for now, brb
anyone know of a realtime tts?
Reminder : ALL voice models are free in 🎧┋voice-models and Weights.gg
If you don't see the model you want and don't want to make it yourself you can always go to 🎫┋request-model or 👑┋model-master-shop to get a model commissioned.
better discord no perms moment
oh crap, it still renders for me
dang
i actually haven't finished pikmin 4 yet.. i want to, but i also want to wait for my switch to come in
i'm super tempted to just play it in ryujinx, but i want to save the rest of it
any good mics for w-okoda? my steelseries arctic mic sounds weird on this voice changer
Ayo? @golden vector level 1 !!! 
hey what's the right version of osaka to select GPU?
For what GPU?
cuz in newer osaka versions you can't select gpu it's like
cpu gpu0 gpu1
Which GPU do you have
to select my GPU
who dare ping me
is headset mics bad for w-okoda?
what
@prime crow what GPU do you have
Nvidia
😀
@lethal swan 
@fleet ingot 
anyone who has headset mic and thinks the voice changer works well?
which do you think is the best voice model right now?
Searching for the perfect RVC e-girl voice model? 
evening!
nah 💀
evening?
hi
or afternoon or something depending on timezone
is there a voice changer that works on windows 11 with these sounds
i came from socksapollo
you came? :ayo:
bruh 💀
sata andagi reference
w-Okada
Do you have a nvidia or AMD GPU?
ye nvidia
Extract everything and run the start_http file
Refer to this guide if you need any help https://rentry.co/VoiceChangerGuide
If you can’t find your error on any of those ask in #🔍│help-w-okada
💀
Ayo? @chilly tangle level 1 !!! 
is the server bot's catchphrase "ayo"?
☠️
Boooooo
There’s no reason to put windows on the deck
Everything works for me on it with steamos/arch
almost everything he wanted to use wouldn't run
Like???
i don't remember much, but s&box was one thing
it refuses to run under proton
i can't give too many details, i don't own a steam deck
Even proton experimental and wine?
idk
Greetings and hello
i use basically steamOS (garuda with kde plasma), and everything works perfectly fine for me
it might just be a skill issue
It is
pacman wasn't even working (as in the package manager, not the literal game 'pac-man')
i use python so often that i accidentally find myself trying to use 'pip install' instead of 'sudo pacman -S'
random, but okay
i might install grapejuice
My osaka doesn'T detect my gpu what can I do to fix this ?
dang it, no embed
nvm. it ruined the joke :(
You have to use vinegar instead via flatpak
i don't even use flatpak at all
Send a screenshot in DMS
Merry Christmas
No today is Orthodox Christmas (celebrated on January 7)
Oh
google it if you want
🏳️⚧️
Your coming out!?!?!?
and Ethiopian calendar of course
hell no im not trans
It wouldn’t be Boykissing if it’s not a boy

uhm could someone help w the voice changer i cant hear myself or smt

yeah
Set monitor to your headphones/speakers
where
Under monitor:
Bigot 🤮
Wait till bro finds out about 2 thirds of the server
2/3rds of the staff 
I wonder how these people react when they see a LGBTQ person in real life
Anyways @hollow tangle could you slaughter this bigotted user?
chat
can someone help me how to do the download process
!ban 1073531520402329700 homophobe🤮
@henimartin banned
Reason: homophobe🤮
Duration: Permanent
bro had model maker too
help wtf is this

!ban 1150587132830818344 dont think you can escape
@papabilal banned
Reason: dont think you can escape
Duration: Permanent
can someone dm me i need helo uhm
It was this fucker too
illaria ate
how do i find out if there is a michael cera speaking model i cant find one
no one did a michael cera model
you can find models on voice-models.com
💣
Okay which one are you using
idk my output thing is the problem
Which voice changer are you using
uhm the realtime thing voice changer
w-okada specifically
No there's two, realtime and w-okada
they arent the same? lol
how do i fix it , its not working on my vc nor can tet it
Nope
Ayo? @manic plover level 5 !!! 
huh idk to explain it
Ayo? @turbid bronze level 2 !!! 
since i have no pic perms
Wait give me a sec
ok
DM me
someone gimme kaicenat voice model
google colab being slow for me
there isnt a mangio crepe option
gpu(dml) mine looks different to the tutorial
is it removed or
ill pay someone to make me a voice model for a rapper
if this isnt allowed please let me know
hello
RMVPE is best
RVMPE is better
ahh ic, ty ty
hey
Anime women aren't real
i need help to do the voice changer
midreal more like realmid
Can someone recommend me an existing AI model that might work well with the Ainu language?
Ello Im new here!
hi is it possible to use rvc on mac
gmorning
yi
Use the venv activation command and then jut run infer-web.py
elo
hi
how can i download voice models from kitai or wtv i wanna get the mongraal voice
Is there anyway to generate a melody or basic beats
hi
https://discord.com/channels/1159260121998827560/1175430844685484042
:right_arrow: /search https://discord.com/channels/1159260121998827560/1163592055830880266
or take a look at weights.gg
https://discord.com/channels/1159260121998827560/1191429836321849435
cant find the model you want?
you can commission one from a Model Master 👑 https://discord.com/channels/1159260121998827560/1159289738314919936
hello
Probably a niche request but does anyone have a Shadoe Haze aka The "Damn son whered you find this" voice model?
hi does anyone know which one duckus uses?
"which one" what?
duckus is a youtuber that uses ai model idk i've never watched him
gm!
can you please pin this so i have a guide to look back on
Probably not worth a pin of it's own to avoid confusing users, but I'll see to put it somewhere reachable
thanks
Hey there! Just a quick question : i see lot of models that only have singing examples but are they usable for talking too?
Not always. Depends on what information it was trained with
Thanks, and yea, make sense. I'll just try and see how it goes but that is pretty much what i thought
Ayo? @languid python level 1 !!! 
Like for Steve1989 there is only one singing example but we all know that this guy never sang in his videos 😂
Reu

Doesn't always have to be singing. Just needs to have larger vocal ranges
Hello, do you guys know how to remove electric noise when the AI Voice Model saying "esss"
I had ever made an artist/singer voice model i took from a song. the result was pretty clean and no electric sounds (when saying "esss" )
But when i took from some audio samples (2-3 songs, one of them from different album) but the result of model was bad/noisy at "esss"
Maybe use a de esser on the audio being inferred over. Could also be a sample rate issue with the creation of the model.
How large is the dataset
Maybe not good S samples for the data set
it’s common for the .index to be very large
it depends
5 min can make an okay money but what matters the most is the quality of the dataset
I meant for the question about size of the files
I can't figure out the datasize
It's just annoying to hit reply with mobile
your index file is what’s big
the actual .pth shouldn’t be a lot
I know the pth 52.7mb
nothing wrong with 500
Doesn't change the index. Your features from the dataset affect it
very much so
i seen one that’s like 1.6 gb
I've actually failed to generate an index before
It's just from what iv been told It's typically suppose to be small like a couple megabytes or so
Is there a way I can upload my model on the #1175430844685484042
You have to get the model maker role first. There is another channel for that
Does that have to be approved by a mod?
Ayo? @iron patrol level 10 !!! 
It gets approved by the qc roles.
So do you know someone I can reach out to, to talk to them about it
Use the get-model-maker channel. I have no clue how to tag the channel on mobile.
Oh so can I just upload the link there and it will be approved
You use the submit command there. Fairly certain there is a guide in the guides channel that says how to get the role. They will verify if the model is good quality before approval though.
Ok thank you
can anyone train a voice model for me!!
https://discord.com/channels/1159260121998827560/1193523852026855584
Hello everywone
hello
hello
yo
Used to use voice.ai it's not the most terrible website but it just sometimes doesn't register with vocals, with rvc you have more control and it registers better and overall quality is better. All while doing it for free
reminds me ever installed voice.ai when old AI hub & kits model sharing were a thing, but ended up uninstalling it and keep using RVC 
Ayo? @still stag level 1 !!! 
I mainly like it cause it's free and you just overall better quality voices, some website voices are just so terrible
how do i do a complete reset on RVC disconnected
runtime > disconnect and delete runtime
Hello
https://colab.research.google.com/drive/1Gj6UTf2gicndUW_tVheVhTXIIYpFTYc7?usp=sharing#scrollTo=F6zbsuNs6xZF
does this still work or is there an updated version
is there any good french model or models that can deal well with french accent
Look at the french models or any English models with thick accents
thanks
Ayo? @candid stone level 1 !!! 
Does anyone know what to do it says pipeline failed whenever I go on any voice
Did some tests and it took only 18 minutes to convert a 5 min file with Linux
Amazing
https://www.youtube.com/watch?v=0uyGj7Fel58 is this real ?
100%
If you want the best quality i can show you how
so i can make it work without harming my gpu ?
yeah you just need a good internet
i tried it but i had a lil delay
Great
Is there really no GPU in your system?
Even intel integrated graphics might be worth a shot
I have a 4th gen i5
and 16GB RAM
I’m running on a laptop not a PC
Is the number below information the current number of users registered on AI Hub?
almost 220k users 
i
--local
There are 10 sexy discord bots in your local area! 
links for local installation:
https://github.com/LykosAI/StabilityMatrix
https://github.com/comfyanonymous/ComfyUI#windows
@feral girder's guide:
https://civitai.com/articles/2982
- Applio-RVC-Fork, by IA Hispano GitHub
- Mangio-RVC-Fork, by Mangio621 Huggingface
- RVC Studio, by SayanoAI Huggingface
- AICoverGen, by SociallyIneptWeeb GitHub
- Replay, by Replay Team Website
- Original RVC, by the RVC-Project team GitHub
You can find more info on the #1159513888199540817 channel. If you can't find your answer, feel free to ask for help in #✨│ai-help. Credits to Faze Masta and Antasma for compiling these links.
which one 🧑🦯
It was 600k before
You know what has millions of users?
where can i find a latina mommy voice model
Ayo? @limber lynx level 1 !!! 
I expected there would be many users, but I didn't know it would be this many.
Where i can find a realtime voice changer for mobile
use /search command
what the tuna
escuché un cover del utau Pruno Faustino de esta misma canción y recordé que yo había hecho uno con Teto hace algún tiempo y decidí hacerle remake
MIDI/SVP
https://drive.google.com/drive/folders/1-vAxhw5Yvi4MjmEdF4wjW-GvtBGOx9Ae?usp=share_link
❤️ Discord: Zusmo-cat-0 Utau#3424
is there a issue useing amd cards when i use voice changer my res goes up to like 150000
Ayo? @rustic parcel level 2 !!! 
Mi segundo cover usando SynthV, a este le puse más empeño, poco a poco aprendiendo a usar mejor el programa
Intenté hacer lo mejor que pude el lipsync con el video pero la pista que descargué estaba pocha y no tenía el mismo tempo que la canción original 😭lo siento si se ve un poco raro por eso
Dejen comentarios lindos plz espero les guste mu...
any weezer covers
A couple but nothing really well done
-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
- RVC Disconnected, by Kit Lemonfoot Google Colab
- easyGUI, by rejects Google Colab
- Ilaria RVC, by thestingerx Hugginface Spaces
- RVC-HFv2, by r3gm Huggingface Spaces
- AICoverGen, by r3gm Huggingface Spaces
- Advanced RVC Inference, by r3gm Huggingface Spaces
- RVC v2 Huggingface version, by Clebersla Huggingface Spaces
- Applio-RVC-Fork, by IA Hispano GitHub
- Mangio-RVC-Fork, by Mangio621 Huggingface
- RVC Studio, by SayanoAI Huggingface
- AICoverGen, by SociallyIneptWeeb GitHub
- Replay, by Replay Team Website
- Original RVC, by the RVC-Project team GitHub
You can find more info on the #1159513888199540817 channel. If you can't find your answer, feel free to ask for help in #✨│ai-help. Credits to Faze Masta and Antasma for compiling these links.
Ayo? @limber lynx level 2 !!! 
-egirl
Searching for the perfect RVC e-girl voice model? 
realest thing ive seen all day
is it true that rmvpe can now do 6th octave notes?
oh hi vecken
Theres one that can do the 8th octave
how is it called?
胃が弱いからいよわです
足立レイさんが好きなので歌ってもらいました
今回MVは足立レイさんのデザインをお借りして描いております。(いよわガールズではないので把握お願いします!)
「足立レイ」は、みさいる氏による等身大美少女ロボット制作計画で開発中の等身大ヒューマノイドロボットです。その中で読み上げ音声・歌声ライブラリも開発が行われました。
彼女について知れる動画こちら↓※「いよわから来た」等のコメントはお控えいだたくようお願いします
https://youtu.be/3Ev_lJeAgYM
歌唱 足立レイ(コーラス 初音ミク)
曲・動画 いよわ
that's not an algorithm
Adachi rei has an rvc model
what
Weve been doing this before it was a trend
is rvmpe good for it now
that sounds difficult 🫢
You can write it by hand not just change existing sound
The saxophone model is fun
Car horn is the best
🫢I don't need those
You will need at least 10 minutes of clean recordings in all ranges
But it can be done with rvc
Ayo? @glossy trellis level 1 !!! 
hey, no self promo here
why?
...for obvious reasons
and its not self promo
i want to sell someting
it literally is 😭
thats called
you're promoting something you do
i just need some money
who doesn't need it
but like seriously promotion of this kind isnt allowed in this server
ok
i burnt the water
a sad day for us all
why is the water becoming blue fire did i just summon a demon or what
Ayo? @turbid mirage level 1 !!! 
when I use the voice chnger my voice takes ages to come out and when it does its really laggy. Is that because of my 1050ti?
you overcooked it
yeah, 1050ti ain't enough for W-Okada afaik
oh ok
it's more usable than other older cards tho
just make sure you're on the right version for your gpu
is it the one with the gpu dropdown
the one with the GPU dropdown is the NVIDIA version
okay
Ayo? @empty basalt level 1 !!! 
then get a real job 
Hey, quick question, How do you re-train your old AI? or like how do you grab your already trained AI and train it even more to evolve it? Also how exactly do I make sure I have the best voice model? (In terms of singing ability and stuff)
Searching for the perfect RVC e-girl voice model? 
Ignore that 😭
why is this bot here 💀💀💀
E-girl voices are in high demand?!?!?!?!?!? 💀
People are so down bad
One message removed from a suspended account.
-
If you mean making a better model, you can just train another one
-
Add lots of variations to it, singing, talking in various pitches and emotions if possible
(they are)
you get to lvl 5, you verify
Ok so, I have a ton of clips of a cartoon character talking, about 5:30, I'm working on a final clip that'll make it 10mins since I heard more mins = better quality sound
One message removed from a suspended account.
So I need to add variety basically?
So I need to grab clips of him making different emotions and such, different tones and pitches, and singing?
The samples I have are pretty varying but it's not that varying, that should impact it right? I mean the final 4min clip should have more variety
sorta, it's more about activity
if you're very active you'll level up fast
Sorry I'm probably asking dumb questions, I'm new to this lol
omggg slayyyy
ChatGPT don't know how to answer this 💀
Not that much
If you intend to use them for those types of variations then maybe
I intend to use it for AI voice covers of songs
Not necessarily!
Quality over quantity always
True
Focus on pitch variations mainly then
So your model has a higher range
try making a dataset with good vocal range then
does anybody have a jeon soyeon speaking model?
I have no idea how to make a dataset, I found some dude on YouTube with a ez dataset maker that makes em automatically and just used that 💀
😭
might not be a good thing ngl
I know 💀
But I'm a newbie so that's all I got rn
i think thats outdated, the only thing you need is a bunch of raw acapellas inside a folder, then inside a zip file
- Perfecting Audio Isolation on Low-End Rigs: A Practical Guide, by Litsa The Dancer and Faze Masta Google Docs
- Gathering and Isolating Audio, by SCRFilms Google Docs
- How to make a good model All-In-One guide, by LUSBERT
Rentry - Vocal Mixing Tutorial, by Roomie YouTube
Youtube Downloaders
Audio Separation/Isolation
So just a ton of voice lines?
if you can, yes
Already got a ton of his voice lines with variety
but you dont need to make it a folder or zip, depending on what you'll use to train ot
ez dataset maker was good when we had to cut a buch of 5-10 seconds audio clips, but you dont need to do that anymore with RVC
ez dataset maker is from sovits era
ohhhh damn that's sovits era 😭
Though in afraid that because they're just talking clips (even though they have some verity of him going somewhat higher and stuff) that singing won't turn our good
So how the heck do I make a dataset?
I already know how to isolate noise and stuff since at one point I decided to learn "bandlab"
And I got that free noise seperatee thing with mdx
Yall know what I'm talking ab 💀
a dataset for rvc is literally just audios of your character/person
ofc you need to do the obvious removing silences steps, y'know
and make sure audios r clean of reverb/echo
Yup
I've got em prepped
Just didn't know wtf to do lmao
you should be fine then lol
I'm scared my model won't be able to sing 💀💀
exporting every audio together is also a nice option
Cuz then I'd have to wait 30 mins and if it sucks then I have to figure out wtf I messed up on and retrain it
every model is able to sing, its just some are worse than others
my steve jobs model can sing
it will be able to follow the pitch, you shouldnt worry about that
and it wasn't trained on singing samples 💀
I used the bluey model under the family section in the models tab and I made it sing, was better than the bandit standalone (banditv2) but when it came to high notes it sucks
Also it sounded more robotic than smooth
oh yeah that can happen yes
Amazing model, but when singing "whistle- Josh hutscherson" don't ask it looses it during :32-:40 on the highs
if you got high pitch samples though it should be fine
That's why I decided to make my own bandit model
So I can make him sing whistle (don't. Ask)
I don't think I have high pitch samples cuz all of em were mostly screaming in pain but I have high-ish ones
It's not an octave above but it's like 8/12 of that
If it doesn't work after first model training then I'll just gather some clips of his higher pitch and hopefully it isn't booty cheeks
After this I'm making a mosquito voice model
check #1159513888199540817
Suggestion for @prime geyser
Full AI Voice Model Training Guide (Local)
Link: YouTube
Credits: Christopher Villanueva
Model training with Mainline RVC
Link: Rentry
credits: Raven (ravencutie21)
AICoverGen Colab Guide
Link: Google Docs
Credits: Eddy (Spanish Helper)
Create a model with RVC disconnected (colab)
Link: Google Docs
Credits: Angetyde
How To Make an AI Cover With Ilaria RVC
Link: Rentry
Credits: 👽 Julia (ailen2091)
use rvc disconnected
yeah
s
but i need the colab link...
-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
- RVC Disconnected, by Kit Lemonfoot Google Colab
- easyGUI, by rejects Google Colab
- Ilaria RVC, by thestingerx Hugginface Spaces
- RVC-HFv2, by r3gm Huggingface Spaces
- AICoverGen, by r3gm Huggingface Spaces
- Advanced RVC Inference, by r3gm Huggingface Spaces
- RVC v2 Huggingface version, by Clebersla Huggingface Spaces
@long flume Boi you need to leave
Hello guys! 7900XT or RTX 4080 for AI?
4080 for sure
Amd isnt the best for AI workloads

or workloads in general
it goes like this, AMD focuses on gamers and NVIDIA became stupid and is now focusing even their gamer GPUs on AI
because of Nvidia have AI optimization? It's just that the 4080 has less memory 
VRAM isnt everything, 4080 has tensor cores which are sortoff and AI accelerated compute unit
Ayo? @woven gulch level 5 !!! 
thx
how many GBs of VRAM does it have
this is why things like pytorch and container workloads only run on NVIDIA, amd only supports NCNN
that's decent
HOLD OFF TO 4080 SUPER
no, 16gb actually
I know about her, there was news about her recently. But in my country it will cost more than 4080.
Ayo? @opal oyster level 1 !!! 
you always want a good quantity of VRAM so you can test other batch sizes
hence why im getting 3060 12gb vram
I'll wait, though.
Exactly, but realistically Its gonna take significantly longer on an AMD gpu since they dont support the pytorch acceleration unlike NVIDIA, they rely on NCNN, and because the tensor RT cores are good at acclerating, even if you cap out your VRAM more than likely the NVIDIA gpu will still be faster
though this is based on prior knowledge and hands on with pytorch on image generation, enhancment, and interpolation workloads
nvidia dominates
hi
Hey guys i am new here and i was trying out voice changer for the first time but when i am starting it and stopping i am not able to check how my voice sounds, anyone up for help?
...can you elaborate on that? not sure i understood you there
For the program VOICEE CHANGER will the processor be important? Or does the GPU play a more important role?
both play important roles, though an AI accelerated GPU line an NVIDIA gpu will perform it faster and indeed will be faster than a AMD gpu + ur cpu
exactly
like i installed the rvc now i wanna test default voices provided above.
so at the bottom i selected my output and input device ,
after that at the mid section where image and other settings shows up i am trying to to speak after clicking start button and stop afterwards but i cant hear myself .
is there any ohter way?
if u click stop afterwards it'll stop
just keep it at start
@woven gulch I have an i7 9700k on board right now, I don't plan on upgrading to the next generation yet 
i have a i7 9700f
better CPU than me lmao
cpu bottleneck moment
and me, but i don't know for AI
but i am not hearing the voice after speaking
check cmd
ik, my combo (i7 w/ 3070) gets a 25+% bottleneck
please leave me alone
I need a CPU upgrade so bad, even when gaming my CPU is at 100% 24/7 and gpu at like 30%
[2024-01-07 22:17:01] connet sid : ah0rYxF_3nGyksjpAAAB
[2024-01-07 22:17:01] connet sid : M1rqwVmrrbCULOixAAAD
[Voice Changer] update configuration: gpu 1
[Voice Changer] device detection error, fallback to cpu
Invalid device id
[Voice Changer] device detection error, fallback to cpu
Invalid device id
[Voice Changer] exception! loading inferencer invalid load key, '\x08'.
Traceback (most recent call last):
File "voice_changer\RVC\pipeline\PipelineGenerator.py", line 22, in createPipeline
File "voice_changer\RVC\inferencer\InferencerManager.py", line 25, in getInferencer
File "voice_changer\RVC\inferencer\InferencerManager.py", line 37, in loadInferencer
File "voice_changer\RVC\inferencer\RVCInferencer.py", line 16, in loadModel
File "torch\serialization.py", line 815, in load
return _legacy_load(opened_file, map_location, pickle_module, **pickle_load_args)
File "torch\serialization.py", line 1033, in _legacy_load
magic_number = pickle_module.load(f, **pickle_load_args)
_pickle.UnpicklingError: invalid load key, '\x08'.
[Voice Changer] update configuration: gpu 0
this sort of error is coming
ig
Ayo? @uneven bison level 1 !!! 
might go AM5 or wait for 15th gen, 13/14th gen on LGA 1700 is a dead platform now
what GPU do you have
rtx 3050
hello
Here we go. Waiting room.
eh
here's the right one
i should go with this one?
yes
dont upgrade to 12th, 13th or 14th basically, Am5 upgrade is ok cuz itll be getting support past 2025
more than likely till 2026-2027
AMD is known for having long lasting platforms
i believe AM4 lived till 2021/2022
from 2017! so thats like 6 yearsdang
6 years of support is crazy
I was looking towards the 7700 (even higher doesn't make sense as I don't want to upgrade to water cooling). Or wait for the next AMD processors (8000 or whatever)
yo
thanks for helping
btw is there any video guide of installation and fullsetup like
there's a guide in #1159513888199540817
Im planning on getting 8000 gen for 8800X3D, Or i might wait for prices to drop and then pick up a 7800x3D to use since im going to be having an MSI 240r V2 AIO, even i9 13900k was able to stay at 61-70 degrees OVERCLOCKED on the 240r, thats amazing for a overkill cpu
it's written tho
Hello!
so the 7800x3D should stay nice and cool
hello
The 7800 is too hot. Are you water-cooled?
7800x3D*
wdym? i9 13900ks is hotter than AMD, especially since AMD chips use lower wattage, and im not overclocking it (or at least not much)
Boi you need to leave now
why do I need to install a million different things just to run applio RVC
Im planning on using an AIO (Water cooled loop) for CPU
😭
mangio is easier 🙏
apparently mangio is outdated and hasn’t been touched in a while
Ayo? @onyx condor level 1 !!! 
it's not necessarily outdated lol
nothing big has happened in 6 months months
why did i say months months 😭
u can use original rvc too
-local
- Applio-RVC-Fork, by IA Hispano GitHub
- Mangio-RVC-Fork, by Mangio621 Huggingface
- RVC Studio, by SayanoAI Huggingface
- AICoverGen, by SociallyIneptWeeb GitHub
- Replay, by Replay Team Website
- Original RVC, by the RVC-Project team GitHub
You can find more info on the #1159513888199540817 channel. If you can't find your answer, feel free to ask for help in #✨│ai-help. Credits to Faze Masta and Antasma for compiling these links.
okk i got it somehow can you help me
i just wanna use it for general purpose like use in Valorant (game)
yeah I wouldn't recommend gaming with it tbh
why so?
could make delay much worse 
ohh i see
and btw here's some input/output settings, in W-Okada they should be like this:
Input - Your mic
Output - CABLE Input/Line 1 (if you're using VAC by Muzychenko)
and in other apps:
Input - CABLE Output/Line 1
Output: Your headphones
is this w okada and mmvc oongx cpu different models?
they're literally the same old W-Okada
just different version names n stuff
omg not dragging the epoch training slider to 1000 makes it so much faster to train
same
dunno what im gonna do with my z790 tho
wasted money on it
a nas with a 13600KF lol
orrrrrr make it mine bitcoin using conainer workloads (if u get a new GPU, have ur 4080 on that rig doing container workloads, ive seen ppl make $5 a day and if ur a star chef youll get higher priority
OOPS WAIT, U DONT MINE BITCOIN WITH CONTAINER WORKLOADS LMFAO
4080 is an LHR card
Salad.io bypasses LHR (somewhat)
because container workloads arent mining
container workloads and bandwith sharing are like mining bitcoin but ur not mining anything, ur basically renting compute power and getting payed like $5 a day
then the 4080 will pay itself off
and if ya live with ur parents, no electricity bill
😁 
leeching off your parents lmao
thats how ya get free vbucks- I mean eshop and paypal gift cards
I can input multiple voicelines into the AI trainer right? I have 5 voiceline files for the character spanning ~7 mins 30 seconds
they say you need 60 minutes or more for the best. In general, the longer the better.
+ different tonality
LOL
what the flip is a singer ID/Training folder path
okk so there is no way of using voice changer while gaming like any other source?
Never mind
it should be good if its just voicelines, ive trained singers with around 20 minutes worth of audios
ive been traumatized at what vtubers say
kk
is it normal for CMD to say "the system cannot find the path specified 'C:\Users\(my name)\Downloads\RVC1006Nvidia/Logs/bandiddums/0_gt_wavs
RVC says model training started but my GPU/CPU nor being utilized lol
🥹 i just got it to play games now i regret , that i should have gone for macbook
Ayo? @uneven bison level 2 !!! 
you can
u can use Colab maybe
in #🔍│help-w-okada pins
im stuck at reducer buckets have been rebuilt in this iteration
in CMD
GPU usage is at 100% and vram is at max util
so im guessing its running
heyy
The problem with MacBooks is
Good luck playing any games on those
good luck running any games on mac
hi
can someone help me?
I want to surprise my parent's, I have minutes of vocal isolated recordings, and want to turn it into a singing voice, I want help but also do myself what I can because I don't have money to spend to make people do it for me.
I own a GPU RTX 3080 if that helps.
Ayo? @empty yoke level 1 !!! 
In #1159513888199540817 there’s lots of guides
You can use RVC to make a voice
-links
- Applio-RVC-Fork, by IA Hispano GitHub
- Mangio-RVC-Fork, by Mangio621 Huggingface
- RVC Studio, by SayanoAI Huggingface
- AICoverGen, by SociallyIneptWeeb GitHub
- Replay, by Replay Team Website
- Original RVC, by the RVC-Project team GitHub
You can find more info on the #1159513888199540817 channel. If you can't find your answer, feel free to ask for help in #✨│ai-help. Credits to Faze Masta and Antasma for compiling these links.
Download Orginal RVC or one of its forks like applios
Suggestion for @empty yoke
Full AI Voice Model Training Guide (Local)
Link: YouTube
Credits: Christopher Villanueva
Model training with Mainline RVC
Link: Rentry
credits: Raven (ravencutie21)
AICoverGen Colab Guide
Link: Google Docs
Credits: Eddy (Spanish Helper)
Create a model with RVC disconnected (colab)
Link: Google Docs
Credits: Angetyde
How To Make an AI Cover With Ilaria RVC
Link: Rentry
Credits: 👽 Julia (ailen2091)
use rvc disconnected, its free
My model is still training but CMD has been stuck on Reducer buckets have been rebuilt in this iteration and i dont see any progress
The person has a RTX 3080
oh i didnt read that
It will train faster using a local method
yeah better try local this time
now turn that on its head with team fortress 2
last update was 7 years ago
i have this problem where i cant open app
i opened it once and cant anyomore
is there a fix ?
hi
Do u know a fix ?
Friends, I need to write a little bit for me to be level 2, how are you?
Good
Ayo? @slim oxide level 1 !!! 
But I need a fix
Can you briefly explain what you mean by correction?
So I downloaded the voice changer it worked well I closed it and now I can’t open it anymore
You can find it if you search on Youtub and they can help you when they receive your message from here.
Ayo? @late ether level 1 !!! 
Thx
uninstall files before uninstalling from control panel and try uninstalling from control panel programs, restart computer and reinstall again
Don’t recommend YouTube tutorials
They are often outdated and contain misinformation
Ah
I understand, then someone help our friend.
It tells you how to solve most errors
Thank you, TIMBOVILL
I'm a new 1 level, how much more do I need to write for 2 levels?
I'm a new 1 level, how much more do I need to write for 2 levels?
Few more messages, you can check with /level
2 levels waiting for you, dear.
Where are you?
level 2 I think she threw up on me
ahahah 😄
It autodetects spam
I don't understand
I’m saying if you say the same message that won’t count
I understand you
artificial intelligence has really made our lives easier
This is amazing.
Ayo? @late ether level 2 !!! 
yessssssssss 😄
anyone has PopekMonster model (polish raper) ??
Tambovill
@wintry sinew popekmonster
Or poopmaster
😭
how to remove multispeaker form a song can some one help me
Anyone know why on the voice changer, the audio is very good but in discord its terrible
use a diff virtual cable
VAC by Muzychenko
is there a voice model for cypher from valorant
Check weights.gg
thank u
hello
hi
👋
Are there any decent music Upscalers
123
i tried this but its hit or miss, idk if it still works: https://colab.research.google.com/drive/1ILUj1JLvrP0PyMxyKTflDJ--o2Nrk8w7
hello
not really and trust me ive researched this
this is more for upscaling like...really shitty quality stuff
if you put like a bit compressed audio in it itll just make it quieter
its best to use this on like separate stems also

Ye
yoo
hi me new
Hi new
hi
why is it saying GPU: cpu gpu0 gpu1 gpu2 gpu3 ?
Ayo? @prime crow level 3 !!! 
hey chat
what is a good voice changer app?
and then it sounds really bad even with a dope ass graphics card
thats free
how do i have a voice changer work with discord?
W-Okada
i have a voice changer, and a vb cable but it doesnt change my voice
Did you set it up
Send a screenshot in DMs of Okada
who okada
is it the one on github
Yeah
Do you have NVidia or AMD GPU
I’ll send you the guide
yes RTX 3060
@storm meadow how do i find okadas dm LMFAO
but its laptop version
No I’m saying send a screenshot of Okada in my direct messages
ty
Ayo? @tepid sierra level 1 !!! 
look dms cuh
Ayo? @errant palm level 1 !!! 
is there a video tutorial? am more of a visual learner
How about I walk you through
sure
Video tutorials skip a lot of stuff
https://huggingface.co/wok000/vcclient000/resolve/main/MMVCServerSIO_win_onnxgpu-cuda_v.1.5.3.17b.zip here’s the direct download for the voice changer
uh
After your done downloading it press “extract all” using 7ZIP
can i just use
the regular windows extractor
You can
But some people had troubles with it
hi
alr done extracting
Now run the start_http bat file
check #🔍│help-w-okada
hello, introducing myself as a lurker i guess?
hi
i'll be honest just looking for ai voices for a personal DND project taking place in my own version of Sonic Forces
i can't voice act so just having an ai doing the voices for me when I talk can make it more immversive for my players
lmao why did my response on a free/paid model request get deleted
Your not a model master
yeah but it was also free
Only model masters can talk on paid requests
Doesn’t matter
That isn’t your model
That’s for training
Your model should be in the weights folder
greetings! anybody able to train my model?(10 minutes dataset) 🙂
Ayo? @spark agate level 2 !!! 
found a few voices on here that can be useful, anything that's not the main cast/generc NPCs will just be my horrible souding voice but the ones i found will be useful,
Ayo? @mystic frigate level 1 !!! 
yep
What do you guys personally use Tortoise tts
Ayo? @meager lake level 1 !!! 
do a post in #1159289738314919936
eh i use ElevenLabs for my TTS stuff
just did 🙂
You pay for it?
oop i see it thanks
nah, just use the free version
Hello
has 10k characters for free, its good enough
I have a problem where in the music the model starts struggling in the high parts and seems to break and think it has to do the low parts, how do i fix this
make sure you're using only the lead vocals
guys there is an ai V1 from ULTRAKILL
I am, Ill see what i can do
Ayo? @woven gulch level 6 !!! 
thank you guys for letting me join, think i got enough for the campagin, and no i won't be streaming it 
bye
Yeah but
any clue why only today i have 20k+ ms
nameless
hi
Hey guys 🙂 looking foward to learn a little bit more about AI in here
came to the right place
:)
I made an AI Cover of Michael Jackson
I made bandit from bluey sing Whistle by flo rida
using a model I compiled off of hundreds of bluey clips
Is there no way to promote AI Cover anymore?
idk
how do yyou uhm, download a voice from AI kits?
I use a very good app that is on the Playstore to make my covers, since the Guis no longer exist
Ayo? @vivid epoch level 1 !!! 
Buenaaas
waos
dm me putting ppl on DONT BE BROKE THIS NEW YEAR
Why do all the sample audios on Weightsgg sound like the same voice?
models with config
bump
#1159290752195633273 YouTube links only
-svc
Yeah I still use so-vits-SVC
Dataset is the audio used to train a model
where is corspe husband voice at???
Hello, I am morgan 😄
The president of Cartoon Network is against AI

Searching for the perfect RVC e-girl voice model? 

Banned.
🙀

😭
omg i can scam egirls AND eboys on valorant
Ayo? @unique gyro level 4 !!! 

i realise my actual voice sounds like a EBOY omg
Scam both with a femboy model
bro is drake

drayke
im trying to find a mommy sounding vtuber to make a dataset
Already exists
Sinder
e girl model
Searching for the perfect RVC e-girl voice model? 
im not buying it off someone
It’s free
wtf
timbovill is experienced
latina egirl model pls 
Searching for the perfect RVC e-girl voice model? 
omg bot STFU
ive been on the internet since i was like 6
wait no 4
on my moms iphone 5c back in like what 2013???
valorant players are down bad
a few people asked for my snapchat when i used my gura model lol
do people even use snap in asia
Sketchy link
uh huh
wait who was that
Dunno
WHY DO I NOT HAVE PERMISSION TO CHAT LOGS
@worn mist ai hub is giving 50 day ban
balls
i think its uhh 1 week
for automod
oh
how do the models work? how can i use them?
you use them in roblox
go to a game called adopt me and use it
hm
For real time or covers
real
Dont be you got us fr

Do you want them for covers or real time conversion like a voice changer
Always bro
b
It’s a good team cant lie
Only mid unit there is agl spirit bomb goku
Imo
Legit
does anybody know how i can make a voice model? is there a tutorial somewhere or smth
He’s a good link partner so he does go well in the team
covers
New years step up blessed me with units
how slow is the online method
yeah
Ayo? @torpid frigate level 1 !!! 
dosent it use nvidia tesla gpus
i’m on mac m1
Depends which method
You can choose
whichever is easiest i guess
but the better quality is important
so whichever u think
Online I would say
Because you don’t have to download anything
@sacred current this might still be one of my most favorite teams tho
Here’s a guide for Ilaria RVC which is hosted on HuggingFace
thanks man!
The SDBH banner was so W
that xeno vegito leader i got hits like crazy
And ssj4 vegito the one with eza DAMAGES LIKE A BITCH
Yesss
Dokkan never misses on art
Tbf
The OSTs are fireeee
It is tho
Bro goes ssj3 rose shirtless and maskless
W
I dont bother reading dokkan passives anymore fr
They too long
how do i add a pic to model submition?












