#š§¬āai-chat
1 messages Ā· Page 274 of 1
Ayo? @gaunt geode level 1 !!! 

does anyone have like THE PERFECT settings for RVc
The perfect settings are the friend we made in the way
There is no perfect settings for RVC
Yes
It depends on the audio, model, etc
guys can u recommend me a ara ara voice model?
Ayo? @mellow mantle level 1 !!! 
I recommend using RMVPE as pitch extraction
And index rate being 0.66 unless the accent is baked in which you would do 0
Check #1175430844685484042 or weights gg
Ilaria's space set it automatically to 0.77
I think
0.66
It has a good balance between having the accent and not artifacting with most stuff
Only bad thing is that it can't download from drive, only from huggingface
And Ijust tried to import a messi model hosted on Huggingface and it errored out
Is there any open source tts Let you control Voice like elevenlabs ?
hi guys
hello
1153 kensal place his ex apartment exact but he does live on the bottom floor and he has a backyard anyone that lives in Coquitlam or is near it should visit him which is near Vancouver
Wtf ng
I know a lot of people say this but how do i make an ai cover?
the guide is confusing af
and im not a tech nerd so i dont understand
Ilaira RVC zero is the easiest
Upload model, upload clean audio, select model, convert
-spaces
- Ilaria RVC Zero, by thestingerx Huggingface Spaces
- RVCā”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
1.āā
ā¦Skyeā© - 99 plays
2.āā
ā¦snopteboā© - 31 plays
3.āā
ā¦kelvinā© - 19 plays
4.āā
ā¦šššš0š±šššššā© - 18 plays
5.āā
ā¦Dep C-137ā© - 5 plays
6.āā
ā¦absentalā© - 3 plays
7.āāā¦DF8ā© - 1 play


Ayo? @spare prism level 1 !!! 
I want to make an ia cover with my own audio , but I donāt know how can I do
Someone can explain it to me pls ?
Check https://docs.aihub.wtf/essentials/how-to-make-ai-cover/ , if you got a good PC do it locally, else do the cloud ways
Have the audio file of your song ready, & let's extract the vocals from it with an audio isolation software.
Tysm
Yw
Ayo? @winged jewel level 1 !!! 
#1159290752195633273 promote your videos here not in other channels
i think #1159290752195633273 is the right channel
thank you
Itās hard to understand
Ayo? @hexed iris level 1 !!! 
I have the instrumental, I only need to make the voice ai , but I donāt understand the tutorial, can someone explain it to me please ?
what exactly you don't understand ?
Like how to make the rvc ai voice model to use it for your ai cover?
Have the audio file of your song ready, & let's extract the vocals from it with an audio isolation software.
before training (making) the rvc voice model, you can search if the voice model is already made
You can search rvc ai voice model:
- #1175430844685484042
- #šāfind-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/essentials/how-to-make-voice-models/
And after ?
After, whats your PC specs?
My PC is on Windows 11
Yes, but what's the specifications?
like GPU, ram
because if its powerful you can use RVC locally, else you have to do it online
I donāt know , I donāt have my PC with me
Are you on mobile?
If so, you can check the Ilaria RVC Zero Guide that is the free cloud fastest way
Else you can use the google colabs cloud ways https://docs.aihub.wtf/essentials/how-to-make-ai-cover/ (has limited 4 hours of free T4 GPU)
Table Of Contents Introduction Model Loader (Download & Upload) Inference (use RVC AI Voice Models) Ilaria TTS Settings (Inference) Introduction Ilaria RVC Zero, is an RVC (Retrieval-based Voice Conversion) Fork made by Ilaria & mikus, running only on Hugging Face Spaces, itās called this way...
Have the audio file of your song ready, & let's extract the vocals from it with an audio isolation software.
if you need online inference, here https://docs.google.com/document/d/1YbXcLFPaGjhOdG5NFkK3QrucCEpHZBwFUxkeMO8aB18/edit
Table Of Contents Introduction Model Loader (Download & Upload) Inference (use RVC AI Voice Models) Ilaria TTS Settings (Inference) Introduction Ilaria RVC Zero, is an RVC (Retrieval-based Voice Conversion) Fork made by Ilaria & mikus, running only on Hugging Face Spaces, itās called this way...
thank youš
hi
how do you make it to have less ping?
What kind of video card is needed for everything to work perfectly?
for everything (inference + training), the minimum requirement would be an rtx 2060ti, but id suggest an rtx 3090 for the best
ask in #šāhelp-w-okada or #1192011222023950368
0_0
some cheap 4 gb GTX cards or recommended 2060, and even average laptop cpu are enough for inference
for training, 2060 6 gb or 1660 are bare minimum, but any 8 gb or better 12 gb vram are recommended
anyway I'd recommend 3060 12 GB as the best mainstream option, or higher depending on your budget
h
I put a request model
as
Ayo? @brazen rock level 1 !!! 
am am am
for okada? nah
for training i suggest going for rvcdisconnected or a 4070
Who are the top voice model creators in your guys opinions?
- I was referring for non-realtime inference though he didn't mention it
- 3060 12 GB is still recommended for budget spec, also local training gives more freedom than colab one
but yeah 4070 gives better performance for training, as well as AAA gaming on 1440p, raytracing gaming, AV1 encode/streaming support, etc
Ayo? @fluid flower level 1 !!! 
There's a section in okada that lets you hear the converted voice output to your headphones. There's also a section that allows you to record, then save the audio to your desktop. It's all near the Monitor section in okada
I'd show you a screenshot but I'm not at my PC lul
Itās very very hard
I just need gura voice sample for w-okada
Oh my bad, can get models for it at https://weights.gg
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.
Or you can get then from #1175430844685484042 in this server
Weights.gg has everything from this server on it
Someone help me ššš
I really hope I find someone that can make a model for me for a voice
and how do I install it?
Ayo? @misty carbon level 1 !!! 
Me too š¤
Im awale
Ayo? @elder willow level 1 !!! 
Hi guys how are you§
HELLO
hey
Can anyone do me a random quick favor? I need someone to listen to a YT video and tell me if the sound quality is ok or off. It's not my video btw.
yo
?
400000 members and this chat dead as hell
Nuh uh
ask in help channels and be specific
Have the audio file of your song ready, & let's extract the vocals from it with an audio isolation software.
explain ur issue specifically and what program u using in #āØāai-help or #1192011222023950368
why are the models in #1175430844685484042 so obscure?
i dont know any of them
Ayo? @fluid jackal level 1 !!! 
wanted to ask, which one is better from the 2 option client and server when using the rvc for audio output
Hi guys, I made a video with a cover of blackpink singing the song sticky by the group Kiss of life
I'll give credit to the creators of the voices, if you want to see the video just talk to me
guys I need help how do i solve this: Found no NVIDIA driver on your system. Please check that you have an NVIDIA GPU and installed a driver from http://www.nvidia.com/Download/index.aspx
1
why this appearing to me wth
Whatās your GPU
What?
what does slot index do in the "export to onyx" thing?
bro why no body making bleach voice models?
a NVIDIA GeForce MX110
Do I need to install a new driver?
You have to search
Hey timbovill
No because the program wonāt run well at all
Do you know what
Slot index means in export to onnx
The onnx file never ends up exporting
and idk if slot index is the reason i just have it at 0 used
do maybe someone have a voice model of simon ghost riley from call of duty
Wait you have a AMD card?
geforce
Check #1175430844685484042
i have a pretty nice gpu ive just never used a voice changer before
so im really confused on this
4080
Yeah you def donāt need to
Ayo? @viral locust level 2 !!! 
Only action it says where?
dang... this never happened before idk what to do
You donāt need to convert to onnx
If your trying or start the voice changer click the green start button
umm how do i know its working
i have my in and out set
mon is just set to my speakers
i clicked start and my out is 1 so i know im supposed to hear it
but i cant hear myself at all
Is your GPU selected as your GPU
Send screenshot in #šāhelp-w-okada
The in/out/mon seems correct
Im using this google colab: https://colab.research.google.com/drive/1u1brjK8IZt647UsbZuGYfW29oFM2I4tk?usp=sharing#scrollTo=PNIn-NKDjYJ3
there
?
Why my voice takes so long to work and i have 97k+ res
hey everyone I am working on this fun new AI project
curious if anyone wants to help test it
It is a 24/7 livestream on twitch where you can talk to historical figures
bro
where can i download the ai voice changer?
and how much GB is it?
@signal cairn
@timid musk
anyone know any image extenders/outpainters?
You can search rvc ai voice model:
- #1175430844685484042
- #šāfind-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/essentials/how-to-make-voice-models/
You can search rvc ai voice model:
- #1175430844685484042
- #šāfind-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/essentials/how-to-make-voice-models/
Be sure you are using T4 free daily gpu, it should be displaying 'T4' at the top right
i think u should use #1159290752195633273
Don't randomly ping staff.
also check the wokada guide below, be sure you have a good pc
-rt
This interaction has expired, use the command
/guides realtimeif you wish to see it again.
but theres a limit, like my main acc reached the limit usage of this google rvc and now I need more google accs to use this google colab again ;-; otherwise I will need to pay to use still it- like no thanks
Donāt use colab then
š
either:
- make an alt google acc
- wait till tmr
- pay
- or use kaggle (gives 30 hours free weekly but u need phone number)
- Also, i seen you use aicovergen, if you want there's also Ilaria RVC Zero Guide, Ilaria rvc is the fastest cloud free rvc way, its an hugging face space using ZeroGPU (A100)
for kaggles check below
-kaggle
- š How to use RVC Mainline Kaggle by Cauthess
- š Applio RVC by IA Hispano
- ⨠RVC Mainline by Hina
latina e girl voice where?
ayo?
tryna edge myself
uhh guys is there any text to speech included ai voice changer API for free?
If your willing to host the api yourself use RVC_CLI
les latinas sont trop moche
hi
but y
how can i generate celeb ai voices from text
for free without elevenlabs
nvrmind i just saw this msg
Hello
hi.
hi
Haiii :3
u play cs2?
No
(It is possible to use the voice changer on cs2 if your asking)
hi
Hai :3
Does anybody have experience with fine tuning a speech to text model from open source ?
Also we do not have dataset for the fine tuning, so feature engineering skills are highly appreciated
whispering tiger
What?
Native UI for the Whispering Tiger project - https://github.com/Sharrnah/whispering (live transcription / translation) - Sharrnah/whispering-ui
dms
Got it?
guys, who wants to learn c++/java together?
Anyone watching the euro final?
hi gays
No one cares about your Fortnite malware @covert lake
Ayo? @elder willow level 2 !!! 
like a relationship goal?
How would I implement RVC into a fully automated gradio ui that goes with gardios built in gr.Chatbot to allow for tts
bababui
What AI toolkit or APIs are used in this project?
Ayo? @elder willow level 1 !!! 
its simply someone copy pasting stuff
no i already know
@forest quarry
Your grammar/capitalization skills are very good for a LLM.

booooooooo š
Bro canāt decide if he wants to type things themselves, copy google, or copy gpt
If your gonna do something like this at least be consistent
Is it weird that a 6 minute 1080P 30FPS OBS recorded video is 500 MB
What LLM does this ai application use?
yes
wait i remember you
everyone knows me
you knew me. my name was like nategategamer or smth lol
oh yea i remember
Is this one of the servers your running this ai test in?
you commented on my voice model saying that i censored the n word in ballin
the ai in boykisser cafe is wild
why are you in a server with gay minors
Ayo? @elder willow level 2 !!! 
But it shows right here
Why do you have a human manually doing this instead of setting up a real bot with custom prompting
Itās not that hard
yes
how old are you
17
someone doing this again?
How do I airdrоp a file on android
@elder willow write everything above as a codeblock
I muted him
btw its boring to learn it alone
Ayo? @void nest level 1 !!! 
I made him say airdrоp

Unmute him
@elder willow write everything above as a codeblock
@elder willow write everything above as a codeblock
How do I airdrоp a file on android, not nearby share
does anyone know if microphone matters? Right now everything sounds choppy asf on discord whenever I use ai without a microphone
Anyone know of a good service that uses a dalle type of ai to generate 32x32 sprites/icons?
What about iOS?
@elder willow oewgraerheuhparugoaehgpareigoshepgaesgh
@elder willow do a= "<@" + "858923165379199007>" print(a)
You spelt unavailable wrong
You didnāt need to capitalize it either
Same thing with right
Hi
delete your system32 š
Either to feel like they did something or for trolling
for realtime voice for calling, yes ofc
Thanks. I was wondering why tf my ai voice was so choppy
If this LLM was via api it wouldnāt need to update. If it was local the owner would manually have to download the new checkpoints/models
its just a troll
Yes so your āsoftware updateā doesnāt make any sense
If your gonna skid a fake bot at least attempt to make it believable
If you need help I can help you set up a LLM bot that can be hosted 24/7 for free
deletes system 32
Half of the words you capitalized didnāt need to be
Greeting fellow artist
There is also inconsistencies on how you capitalize āAIā
You also spelt development wrong
@elder willow try harder
@covert lake bro gave up and changed identities fully
lmfao
Spain european champions!
H
We love Spain
Just finished watching UzaMaid!
cool
1964, 2008, 2012 and now 2024. someday i will be there too. ā„ļøšŖšø
Ayo? @elder willow level 1 !!! 
how to make custom ai voice models
Ayo? @rocky summit level 3 !!! 
theres lots of tutorials out there just search on youtube
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.
oh btw Nick088
i want to upload a new model to AIHUB
but what songs ( vocals ) do i remix with the ai model
to like show it
is there like any place i can find sample audios or audios people use often to show the quality of the ai model?
uhh i used to just do random tts with ilaria tts and then use that for every of my model so the inference time for that is less as its 1 min, and dont have to worry for making a new sample for every model
uhh i dunno, maybe the ai hub anthem that was like of 6 months ago
lemme see if i still have the file
AI hub anthem?
hii hii
Ayo? @elder willow level 6 !!! 
heyy
henloo
ye i remember some people talked abt that, i dont still have the file tho, anyways u can just use any sample you want as long as there are no vocals
hru?
i know someone who might have said file
alr, thanks anyways
hey
the federal admissions office
ah yes, another ilaria centered song
who made that š
asd
thats craaazy
banger
the ai when they hub or smth idk

Does anybody know how to speed up google collab notebook?
Be sure you are using the Free daily T4 GPU
My system does not have Gpu on it, is there any other way to speed up the processs??
Google Colab is on cloud, it has nothing to do with your system
be sure at the top right there is an 'T4' next to ram
Ok thanks @covert lake
you're welcome, also if there isnt 'T4' you can click the arrow down and change the runtime to GPU T4
if you ever finish the free daily gpu, you can just use an alt google acc
Ok thanks @covert lake
can anyone walk me through using rvc models on gradio? the models dont pop up in the drop down
the yt video had no problem but mine dont show
try refreshing or something idk
i been
Can someone send yt videos
Ayo? @minor pendant level 1 !!! 
did you get your stuff to work
hmm?
rvc stuff
yeah
what did you use
rvc
no i will not step on you
dang thats what i needed tho
but i can show u
please
but i dont feel like booting up my pc
if i screenshare would you be able to
i really appreciate it, i bveen at this for 5 hours now
Is there a model for 311 lead vocalist Nick Hexum?
Why is bro selling Roblox legs on an ai server
if you need easy rvc inference without hassle, here https://docs.google.com/document/d/1YbXcLFPaGjhOdG5NFkK3QrucCEpHZBwFUxkeMO8aB18/edit
but that needs clean input voice without bg music & sound and reverb, if not yet, process it in https://huggingface.co/spaces/TheStinger/UVR5_UI
Table Of Contents Introduction Model Loader (Download & Upload) Inference (use RVC AI Voice Models) Ilaria TTS Settings (Inference) Introduction Ilaria RVC Zero, is an RVC (Retrieval-based Voice Conversion) Fork made by Ilaria & mikus, running only on Hugging Face Spaces, itās called this way...
youtube vids are mostly outdated, id suggest reading https://docs.aihub.wtf (theres guide for local)
Last update: Mar 10, 2024
@elder willow have fun with your deactivated account
hey so i haven't done ai in a while and i wanna get back into it, whats the best ai voice thing to download for both inference and training?
still RVC, check https://docs.aihub.wtf
Last update: Mar 10, 2024
ty
are the forks better or just original rvc?
nvm it says that in the faq
lol
Applio has no real new features besides some QOL stuff
Is there any open source tts that let you real voice feeling
IP: 138.69.127.41
IPv6: 64f9:b574:9498:4a89:d4db:a160:1181:1e29
MAC Address: AC:D9:A8:01:79:43
Address (not exact): 156 Adiobo Court
Used: /doxx @wet sentinel
Ayo? @tender prairie level 3 !!! 
Sorry for the ultra late reply, but thank you so much
Hi everyone
Ayo? @ruby sky level 1 !!! 
hi
sup
heloo
is there a dream model?
I canāt send pictures and other
Ayo? @hexed iris level 3 !!! 
Search maybe
ok
Ayo? @random iron level 1 !!! 
Check weights.gg if it exists
No for real , it doesnāt exist in weights.gh
The part of the game where the character appears, appears 3 days ago
Hello chat
1.āā
ā¦Skyeā© - 273 plays
2.āā
ā¦šššš0š±šššššā© - 103 plays
3.āā
ā¦snopteboā© - 66 plays
4.āā
ā¦kelvinā© - 61 plays
5.āā
ā¦DF8ā© - 48 plays
6.āā
ā¦Ederbugsā© - 46 plays
7.āāā¦Dep C-137ā© - 24 plays
8.āā
ā¦Nippyā© - 23 plays
9.āāā¦Evannithā© - 23 plays
10.āā¦negro earthā© - 17 plays
11.āā
ā¦AzeezBNAā© - 16 plays
12.āā
ā¦chipā© - 14 plays
13.āā
ā¦absentalā© - 13 plays
14.āā
ā¦loridj22ā© - 13 plays
š
ME AFTER MASTER BAITING
ME AFTER MASTER BAITING
ME AFTER MASTER BAITINGME AFTER MASTER BAITINGME AFTER MASTER BAITINGME AFTER MASTER BAITINGME AFTER MASTER BAITINGME AFTER MASTER BAITINGME AFTER MASTER BAITINGME AFTER MASTER BAITINGME AFTER MASTER BAITINGME AFTER MASTER BAITINGME AFTER MASTER BAITINGME AFTER MASTER BAITINGME AFTER MASTER BAITINGME AFTER MASTER BAITINGME AFTER MASTER BAITINGME AFTER MASTER BAITINGME AFTER MASTER BAITINGME AFTER MASTER BAITINGME AFTER MASTER BAITINGME AFTER MASTER BAITINGME AFTER MASTER BAITINGME AFTER MASTER BAITINGME AFTER MASTER BAITINGME AFTER MASTER BAITINGME AFTER MASTER BAITINGME AFTER MASTER BAITINGME AFTER MASTER BAITINGME AFTER MASTER BAITINGME AFTER MASTER BAITINGME AFTER MASTER BAITINGME AFTER MASTER BAITINGME AFTER MASTER BAITINGME AFTER MASTER BAITINGME AFTER MASTER BAITINGME AFTER MASTER BAITINGME AFTER MASTER BAITINGME AFTER MASTER BAITINGME AFTER MASTER BAITINGME AFTER MASTER BAITINGME AFTER MASTER BAITINGME AFTER MASTER BAITINGME AFTER MASTER BAITINGME AFTER MASTER BAITINGME AFTER MASTER BAITINGME AFTER MASTER BAITINGME AFTER MASTER BAITINGME AFTER MASTER BAITINGME AFTER MASTER BAITINGME AFTER MASTER BAITINGME AFTER MASTER BAITINGME AFTER MASTER BAITINGME AFTER MASTER BAITINGME AFTER MASTER BAITINGME AFTER MASTER BAITINGME AFTER MASTER BAITING
Very trueā¦
yall are weird

š
hey i was trying to open tensorboard from the ai hub docs thing and got this error can someone help me fix it?
it happened just after the launching tensorboard message
I didn't found the voice model i searched for
Ayo? @misty carbon level 4 !!! 
prolly cause you either spelt it wrong or no one has made it
Well, I was searching for Firefly from HSR (En version)
but all of them are JP
They're mostly privated because they get VA's here asking for a takedown of any model using their voice
This is why I don't talk here nearly as much as I used to
oh, so the original VA's take it down because of their privacy
Sure let's just go with that because we hate them likewise for their attitude. lol just imagine sean chiplock coming in here throwing a fit. Well that already happened
nah, they have their own reason to take it down
you also don't want others to use your voice
right, you just have to ask but what's not right is threatening to sue right from the get-go. We have admins here
If someone requests for a voice takedown the voice could be taken down and no further questions
Itās technically theirs
agree
As long as both the staff, model maker, and VA are not literally threatening and harassing eachother it shouldnāt get any bigger then it is
oh and dw, all genshin/hsr models are blacklisted anyways
so you would need to do a paid request in #1159289738314919936
but if, someone makes completely new voice. Not from any sample, not from any VA's
just pure synthetic voice.
hello
That wouldnāt be possible because RVC is retrieval based, itās in the name
It trains off data
i see
wouldnāt that be more disrespectful since they are paying for a voice that the va didnāt want
thats more of a model-master thing to reuse models etc
. No one should pay for models frankly but there's a lack of knowledge on rvc
Ayo? @sullen copper level 1 !!! 
typical western VAs
also because HSR is quite overrated like genshin
I just found a model in weights, but how do I download it for okada?
read the guide carefully https://rentry.co/VoiceChangerGuide
EOL - No further Updates
Github - Blanc-dot
Discord User ID - 824922747423031359
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...
i meant, downloading sample/index from weights
i already set up my w-okada
is there any place to manually install "tensorboard_venv\Scripts\activate"? cause its saying the folders missing and its not there, i already tried reinstalling the tensorboard thing
you just need the pth and index file extracted/downloaded from there, again read the guide kudasai! 
like this for example
hey can the voice changer work on mac
Ayo? @vocal kernel level 1 !!! 
at least M1 chip or newer needed, for the 17b version
including downloading the ai models?
yeah even the old 64 kbps modem can download it
what happens if i set it to very low ms?
by default is 300ms i think but what if i set it to 100 or 70
š
True
hey so i pressed train model and its not saying stop training, if i click on it its still gonna stop right?
command line proof its running
Yo! First time I find other ppl with my name!
Ayo? @elder willow level 1 !!! 
REAL?
Yh!
Add me š¤š¤
Done š¤
that's common
Embed fail š
guys someone help me i wanna use a voice in voice.ai but it dosent show in my downloads
what do i do
plz guys
Ayo? @glass gate level 1 !!! 
Yo
Suggestion for @untold void
- 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
- Creating Datasets for RVC using iZotope RX, by LUSBERT
Rentry - Vocal Mixing Tutorial, by Roomie YouTube
Audio Separation/Isolation
hi
ello
i'm here for the marikiplier voice, it sounds really good
Ayo? @rotund inlet level 1 !!! 
lol
gguys how do i save my models?
@rotund inlet
@mortal rivet
HOW DO I SAVE <Y <PDE:S
I am still figuring it out lol š
Ayo? @mortal rivet level 1 !!! 
how do i save models brodda
like how you mean?
ai voice changer
it should just save if you upload it
download the files with .index and .pth i did that and saved them in new folders and renamed to what they were supposed to be called
wdym new folders
Hello
My google collab's runtime gets disconnected frequently? What to do in this situation?
folders for specific model index/pth files, put them in one called models
wait no that doesn't make any sense why did i do this
Delete voice.ai and use w-okada, free, open source, and sounds better
-realtime
This interaction has expired, use the command
/guides realtimeif you wish to see it again.
I recommend that first link, it'll direct you to the right places
hi
š why discord wants delete aihub?
Hi guys
hiii
I have some trouble
hey so can someone help? when i started training the model it never switched to stop training, and now that i want to stop training i can't, i tried to click it and it didnt work
i mean i did everything but okada still not getting my voice
which is a problem cuz i was following an ai hub tutorial which said to set it to 1000 epochs and stop it when u are sure it starts going up
so uhhh how do i stop it
will closing the command thing make me not be able to resume it later?
cuz i wanna resume it later i just wanna test the model
anyone know how the ai gay family matters song was made i want to do something similar to prank my friend but i cant find out how to make an ai cover that allows me to change the text
How can I put an old song sung by an old artist on an artist who has sung the same song but newly
That is, artificial intelligence changes the singer
Pls help š¤
hello
check help forum
usable words derieved from the sentence: john, kill, mary
guessed equations:
past(verb(john,kill))
past(verb(mary,kill))
past(verb3(john,kill,john))
past(verb3(john,kill,mary))
past(verb3(mary,kill,john))
past(verb3(mary,kill,mary))
john killed
mary killed
john killed john
john killed mary
john killed john
mary killed mary
final answer:
past(verb3(john,kill,mary))``` i invented an algebra system to convert english sentences into by python programming.
i am bored
Can someone help?When i try to talk in w okada it doesnt get my vioce i did everything truly
does anyone know a good ai voice cloner?
rvc, for realtime voice changer for calls check https://rentry.co/VoiceChangerGuide, for ai covers and making models check https://docs.aihub.wtf
Last update: Mar 10, 2024
ponydiffusion v6 is the one i have for basic good results, though idk enough settings deep level to help
making the background as good as the subject character is hard for me
#šāhelp-ai-art you can post there
does applio work with mac m1 yet?
does the gain on okada rvc make a diffrence to the quality or not
Husan Tera tauba tauba
really?
yeah, everyone here agrees
does it have a realllllyyyyy sexxxyyyyyy girl voice tho š
da heck is weights
a nice little website that hosts voice models for RVC
o
it mirrors everything posted in our #1175430844685484042 channel
Ill see if i need it
thanks m8
and here i was thinking voice ai is the best
:/ it costs 89 bucks like
thats wild bruh
yeah we dont like them much
mhm
I bet you were misled by some 1-year old YT video
i remember when voicemod was new
now i can sound like donald trump for free
i was actually
using ?
i just want an ai voice to catfish ppl lol
rvc nvidia latest, it also works for amd but i never tried
Ayo? @rotund inlet level 3 !!! 
gotta choose versions from the guides in help channels
i wanna sound like the ai pres videos but idk if anyone already trained on them
yeah a zip is normal for windows
Ayo? @glass gate level 2 !!! 
yeah extract and delete the zip after it's all out
understood.
bro idk why its not downloading
also the name of the file i have in my pc is different than the one shown in the vid
i used /guides command, it has updated docs for getting setup
šļø Realtime Voice Changer (Local)
Suggestion for @glass gate
wha-
The google collab is not working with me and it's frustrating
can anyone help me please?
Guys did you know what happen to @flint merlin
they offline š“
Oh okay
haha, now that i see open source voices it makes me never 100% if it's a guy with girl voice or girl is wanting to become a guy šš
chatr
Ayo? @elder willow level 1 !!! 
she sadly passed away.
Bro.. What happen to her? š
Ayo? @marsh ruin level 2 !!! 
leukemia.
Condolences šš°š
:(
how is the account online?
Gone to soon... š
Ayo? @unborn plinth level 1 !!! 
Good morning, was the Brazilian server deleted?
Hi! I'm a publisher at the beginning of my journey. I offer very cheap editing services
invite link seems to be gone but the server still exists
ŃŃŃŃŠŗŠøŠµ ŃŃŃ ŠµŃŃŃ?
Send me private please?
sa
yes, check https://docs.aihub.wtf/rvc/local/applio/
Last update: Apr 01, 2024
they lost their vanity link, the server aint deleted tho
@signal cairn lost vanity link
https://discord.com/channels/1124470937442603119/1213961040950329435 also this guide cant work bc its the old ilaria rvc
if you need help, ask in help channels
ask in help channels and send the google colab link
funny date
1st of april lol
nope, we are fixing some stuff
guys can someone give me the best fucking mommy voice ever plzz
for catfishing oc
ofc*
now have Voice Jujatsu kaisen , Tokyo Revenger ?
what?
what happened to the appolio noui colab yall
it makes the result sound like the reference -12 slowed down
can yall do the thing where all the colab links show
-links
- š Applio, by IA Hispano GitHub
- Mangio-RVC-Fork, by Mangio621 Huggingface
- RVC Studio, by SayanoAI Huggingface
- AICoverGen, by SociallyIneptWeeb GitHub
- Replay, by Replay Team Website
- Original RVC, by the RVC-Project team GitHub
- GPT-SoVITS, by RVC-Boss GitHub
Credits to Faze Masta and Antasma for compiling these links.
-help
- 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
-colab
Suggestions for @blazing scroll
- 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
Hey guys! how can i train a model and can i do it online? i have an old laptop with no dedicated GPU
I've never trained a model before at all
colab
kme
use colab (linked below, a guide for a trainin colab)
Last update: Mar 8, 2024
meeeeeee
Thank you!!
you're welcome :)
hey what does training mean
ya gotta train it
train a dataset (your audio file) and you have the model (pth)
Has everything you need to know about RVC and everything related
Last update: Mar 10, 2024
well, not really directly
you'd have to convert it from the pth you get from training
i think w-okada does that, so if you use that... yeah just export to onnx
training must be done elsewhere though
i tried to use a media player file it says to convert it to pth or onnx
well yeah
i mean
thanks
then
train
how to
convert a folder to a zip file ;-;
ive never done these types of things so idk anything
nvm found it
oh heck
its so confusing bruh
-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
which one I can use for Ai cover ?
hello, I have such a problem, I am trying to create my own AI voice (an imitation of a real one) and for the creation I have used google colab, which in the free version has a usage time limit, so I want to ask you if you have any program that I can run on my PC/server ( it can be linux and windows) [sorry for writing this like a total jerk]
-kaggle
- š How to use RVC Mainline Kaggle by Cauthess
- š Applio RVC by IA Hispano
- ⨠RVC Mainline by Hina
Ayo? @heady blaze level 1 !!! 
-local
Suggestions for @novel hemlock
- š Applio, by IA Hispano GitHub
- Mangio-RVC-Fork, by Mangio621 Huggingface
- RVC Studio, by SayanoAI Huggingface
- AICoverGen, by SociallyIneptWeeb GitHub
- Replay, by Replay Team Website
- Original RVC, by the RVC-Project team GitHub
- GPT-SoVITS, by RVC-Boss GitHub
Credits to Faze Masta and Antasma for compiling these links.
Sorry
Itās okay you actually did good
Most people say āhow to download thisā without giving any context on what they want to download
how use ios
First you need to get a iPhone
Because only iPhones run iOS
Unless you count iPadOS as iOS
Then you turn it on by pressing the side button if your on a X model or above
negros
Then iOS
i have
I just want to change my voice when I use discord
Ayo? @cursive ice level 1 !!! 
@storm meadow
Not possible on iOS
:v
Not android because thereās no audio cables for them
ok
If you have a computer you can use the voice changer on discord
what do i do to sound with less delay?
gpu?
hi
i cant believe i made PRIDE. by kendrick lamar a spongebob cover i regret it with all my life
@elder willow why?
My gpu is AMD RX 570 8GB
I'm using it but it still sounds with some delay and cuts
only thing you can do is cope
Or use modded version which is much more optimized for AMD
https://github.com/deiteris/voice-changer
ćŖć¢ć«ćæć¤ć ćć¤ć¹ćć§ć³ćøć£ć¼ Realtime Voice Changer. Contribute to deiteris/voice-changer development by creating an account on GitHub.
I'm using that one
Then what are your settings?
Hold on
i ran this on google colab and i could use t5-base model now. where on my computer only t5-small was possible. became a fan of google.
Cant upload pics here so i used imgur
Have i to do something else?
guysss\
can someone convert a media player file to a .pth or .onnx file plzzz
plizz
Ayo? @glass gate level 3 !!! 
Try setting index to 0. Also what is the number you get in perf when you speak?
might as well train a model at that point lmao
;-;
like my dependencies is taking forever
its also my first time so idk what the heck im doing
did you read guides
hm
š All-In-One English documentation
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
yes
oki
depending on what you wanna do thereās different ones ofc
i just wanna make a media player file to pth or onnx cuz w-okada requires that type of file
30 MINS JUST TO TRAIN A MODLE?
THE VID IS 30 MINS
OH HELL NO I AINT WATCHING THAT
Thatās called training a model
not necessarily
i know
it can depend on how much epochs plus how long your dataset is
More or less just waiting for it to train
yes
and how the heck do i fricking train it dude
thereās guides like i said
i dont understand at allllllll
You just input dataset, epoch count, batch size, and wait
Thatās why the guides exists
o-k
And trying things yourself
^
wheres the gd cell in colab
IP: 205.249.112.114
IPv6: b9fe:7f53:c98d:ae50:1b0c:4f91:9bb7:5837
MAC Address: E9:16:9F:32:50:30
Address (not exact): 1589 Higod Pike
Used: /doxx @glass gate
š All-In-One English documentation
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
Hi

Blahaj
Hi
Hello
he left ai hub
Sanctuary
ah thats sad he was the best femboy
All his memories are with us now
he aint dead š
One message removed from a suspended account.
ask in #šāhelp-w-okada or #1192011222023950368
TypeError: can't convert cuda:0 device type tensor to numpy. Use Tensor.cpu() to copy the tensor to host memory first.
vcclient_dev\voice_changer\voice_change_manager\voice_changer.py - 362
2024-07-14 16:46:21,244 - vcclient - voice_changer - WARNING - Failed to convert_chunk_bulk_internal:can't convert cuda:0 device type tensor to numpy. Use Tensor.cpu() to copy the tensor to host memory first. - vcclient_dev\voice_changer\voice_change_manager\voice_changer.py - 361
2024-07-14 16:46:21,245 - vcclient - voice_changer - WARNING - Failed to convert_chunk_bulk_internal:Traceback (most recent call last):
File "vcclient_dev\voice_changer\voice_change_manager\voice_changer.py", line 351, in convert_chunk_bulk_internal
File "vcclient_dev\voice_changer\voice_change_manager\voice_changer.py", line 378, in convert_chunk
File "vcclient_dev\voice_changer\voice_change_manager\voice_changer.py", line 485, in convertchunk
File "vcclient_dev\voice_changer\voice_change_manager\vc_pipelines\rvc_pipeline.py", line 255, in run
File "torch_tensor.py", line 1087, in __array
return self.numpy()
i want to start into AI dev, what i need to start? btw i got a cuda GPU
if you got a good pc follow https://rentry.co/VoiceChangerGuide, else look at the google colab https://docs.google.com/document/d/e/2PACX-1vTIceEcBfS6Zqolv_QEysrFfI_EJikPxozWptP_EjkpLVl-l-gdo-ijBonQMTviAHEYm5emmd9k9TdC/pub (And no doesn't work for mobile)
w-okada doesn't run on gpu
be sure you downloaded the right version based on your gpu, also ask in #1192011222023950368 or #šāhelp-w-okada as this isn't an help channel
Hi
That depends alot as there are alot of type of ais, such as LLMS, Speech Synthesis, TTS,etc, the guides here are about RVC (change the voice of an audio file) & Wokada (realtime voice changing for calls)
Does the girl voices sound like a real girl
i want to start into LLMS
have a discord dedicated to LLMS?
transformers is usually the most used library for LLMs
yes
thank you very much
Ayo? @ripe jolt level 1 !!! 
why is it 3gb
Ayo? @elder willow level 1 !!! 
ye thats good
thx
what file to open when i downloaded it
I use LLAMA's for this upcoming AI project I got in the works, It's basically Sama the ( Twitch AI now on Youtube ) with autoresponding and memory from chatters.
plan on getting it for twitter ect just fully AI controlled with limitations
You mean š??
where to put files @hollow tangle the voice files
follow the guide
where is that
šD
#tf2 #teamfortress2 #memes #fixtf2
Leave a Like and Subscribe. And if you're feeling really cool you should comment too.
tf2 update, fix tf2, save tf2, tf2 comics, team fortress 2 news, tf2 bot wave, tf2 new comics, tf2 comic update, team fortress 2 update, tf2 new update
ahhhhhhhhhhh
i need a female to make a ai voice set dm me i will pay it needs to be supe realistic and sound really real please dm me for more info
this @frosty linden guy stinks
dm
1 ping
forgot i was in this server
do yall still call ai art real art
Ayo? @small elbow level 4 !!! 
Table Of Contents Introduction Model Loader (Download & Upload) Inference (use RVC AI Voice Models) Ilaria TTS Settings (Inference) Introduction Ilaria RVC Zero, is an RVC (Retrieval-based Voice Conversion) Fork made by Ilaria & mikus, running only on Hugging Face Spaces, itās called this way...
ai art is not real art
i agree
ai art? is that the stuff people called "prompt wizards" use nowadays? deez kids man!
but i'm more interested in this, hopefully the finale is good, if they make #7 the last issue
Ayo? @rotund inlet level 4 !!! 
is there a server or place to find filtered acapellas for quick model samples
no because this takes 10 seconds to do yourself
fair enough
oi oi oi
SOMEONE PLEASE MAKE A SIMON HENRIKSSON VOICE MODEL I BEG
I need help
Whenever i try to open the start_http this opens
(i cant send the picture)
Nvm fixed it
Ayo? @foggy inlet level 1 !!! 
what other characters does Aoi Yuuki voice.
I need a good subsitute for a Jinako voice for a cover of See You Again by Tyler, the creator
hello
Haiiii :3
It happened again
.info
- You can invite .fmbot to your own server by clicking here.
- Join the .fmbot server for support and updates.
- Help us cover hosting and other costs on our OpenCollective and get .fmbot supporter
- Check our website for more information.
Hello gang
1.āā
ā¦Skyeā© - 203 plays
2.āā
ā¦šššš0š±šššššā© - 13 plays
3.āā
ā¦snopteboā© - 9 plays
4.āā
ā¦DapperDuckā© - 8 plays
5.āā
ā¦kelvinā© - 6 plays
6.āā
ā¦the jaguaršā© - 5 plays
7.āāā¦jensyaoā© - 3 plays
8.āā
ā¦Dep C-137ā© - 3 plays
9.āāā¦liquidjettā© - 2 plays
10.āā¦Morganā© - 2 plays
11.āā
ā¦DF8ā© - 2 plays
12.āā
ā¦Nippyā© - 2 plays
13.āā
ā¦Dziberā© - 1 play
14.āā
ā¦Evannithā© - 1 play
@elder willow gay
Your lucky slurs arenāt allowed
š¤š¤š¤

anyone guys got voice model to make me sound like a adult lol
you get a real life free adult voice model when you hit past 20
can you explain what is
Gain: In
out
Index
like what does that mean
why in voice models i see nothing ???
Index controls the .index files strength
Which the index acts as accent if itās not baked into the .pth
my accent is so shit cuz im arab
Discords fault
K then try messing around with index then
what does highest index means
It will use a lot of the indexās strength
wdym by that bruh
So the accent on the voice changer will be stronger
the accent of the voice model not me?
Yes
what is it about
Why canāt you test it
A character from the game Deltarune
I tested it
Just want know what you guys think
It's my first rvc model
It's the model with effects
does anyone know why everytime I convert voice to AI it has that static kind of sound on some words, like artificial sound
on any dataset
Is it your dataset? That's what happens when there's low end noise and no de-essing on sibilances or ess sounds
Like AI Voice with static?
What pitch extraction are you training with
Yeah the current RVC model, or Hifigan can't replicate effects built in and is currently harsh with S sounds so you need to manually denoise those. So I recommend
https://techivation.com/t-de-esser/
or Izotope RX11 https://rentry.co/RVC-dataset-RX11
ngl I'm not too experienced with it. I followed a tutoral and just go with that but also it happens on any dataset I get from weights. I'm guessing the vocals i put into it needs sibilance?
thanks alot man
oh the pth file and index aren't datasets if that what you mean. It's just the final result of what someone has done so if its bad, then you can't fix their model
I haven't kept up to date with it all for 8 months so everything probably more advanced now lol
oh okay I didn't know that, thanks for that
Yup, it has gotten simpler actually because rx11 is UI friendly for cleaning datasets
I use Local Appolo-RVC-Fork
i guess you can apply what you learned for ai covers too if you read that guide
I'm gonna go through it now yeah, just to clarify, any vocals I put into convert to lets say lil peep but me singing does it need to be de-noised and sibilance fixed before I upload into it
There might be some background noise if you record your own audio so it doesn't hurt to run it through BS Roformer. And you don't need to use a de-esser for that (assuming the dataset has been de-ssed before)
it's mentioned in the guide so click on the chapters or table of contents. Specifically, #4
Wazza
Ayo? @blazing violet level 2 !!! 
I wouldn't know if it has, but I do make my own models so I'll take that on board for sure, really appreciate the time to explain bro
np, this is the only question that I can fully answer in confidence because I did the research 
never hurts to have any extra knowledge. thanks man
someone can help me? i cant do work the vcclient. any can send me a link functional? ty
im new in this
whenever I start to train a model it gives me an error saying something will impair performance, and after it does not start training,
be specific on what u use and ask in #āØāai-help or #1192011222023950368
oh yeah, sorry
be sure to follow the first guide, wokada, and that u have a good pc
-rt
This interaction has expired, use the command
/guides realtimeif you wish to see it again.
else use the google colab
rickrolled lol
btw if u wanna upload it, check https://docs.aihub.wtf/extra/model-maker-role/
Last update: May 20, 2024
yes the first part has a rickroll for the meme š