#🧬│ai-chat
1 messages · Page 284 of 1
rahul
hi
Hi, enthusiastic to be in great community.
https://fish.audio/voice-conversion/ - the secret hack hasn't worked, sad
Discover the best voice models and build yours in seconds
anyone know how to VB audio config ?
just there is choice but you can't choose Voice Conversion
hello there
i have a problem when opening start_http.bat i get a cmd and it wont open, does someone know how i can fix that?
aha
Ayo? @cold heron level 1 !!! 
💀
oh my fucking god why is so hard to train models on CPU, i cant even use tensorflow
hello gays
training models is not supposed to be done on cpu
but like is it possible? lol
to at least install tensorflow on CPU
I realistically dont think you should be training unless you want to wait 2 hours for one epoch
model quality will suffer most likely too
You can now
what is this
Haiii :3
it works on CPU for inference it’s just really really slow
Can anyone help me with something?
I have been using the Goth Mommy voice for almost 2 weeks now, but it can be glitchy at times.
(Dataset: 10 minutes, Hop length: 32, Pitch extraction: Crepe, Batch size: 8, Pretrain: Titan-medium 32k)
Is this because of my settings/pc, or would other voices run better?
I am looking for something for quick, real-time responses with a more mature, soft-spoken tone.
Use RMVPE instead of crepe
RMVPE_ONNX or just RMVPE
because CPU’s are not meant to train ai models
GIVE me link download v.1.5.2.9e ONNX(cpu,cuda), PyTorch(cpu,cuda)
they are quite literally missing the necessary components to do it properly
Well, they can but no good open source options at the moment
-realtime
This interaction has expired, use the command
/guides realtimeif you wish to see it again.
PyTorch comes with the voice chnager so you don’t need to set it up at all
real
yo
Hey guys
I'm so sorry to ask for this but after seeing that even the issues report on github didn't helped I'm getting desperate
The voicechanger soft only use my CPU instead of my AMD GPU
I did used the MMVCServerSIO_win_onnxdirectML-cuda_v.1.5.3.18a file which if I correctly read the description should use AMD GPU ( DirectML )
I'm wondering what i'm doing wrong as obnviouslyu selecting CPU, GPU0 ( my actual GPU ) or any other option do not do the trick
Use this fork which should use more of your GPU
Thank you ! I will give it a try right now
bro what the hell
Thank you very much my friend, it works perfectly !
Ayo? @hazy wyvern level 1 !!! 
i can run voice changer on intel hd graphics?
hello
did we need to know that?
general chat is always such a cesspool bruh
Hi does anyone can gimme the output of one AI Cover i have the model i just need the final output but mine google collab isn't working it's about AI Cover
Someone to talk?
use ilaria rvc zero
Table Of Contents Introduction (with link) Model Loader (Download & Upload) Inference (use RVC AI Voice Models) Ilaria TTS Settings (Inference) Introduction (with link) Ilaria RVC Zero, is an RVC (Retrieval-based Voice Conversion) Fork made by Ilaria & mikus, running only on Hugging Face Spac...
that’s why i said properly
Can someone explain to me where to download the voice changer? Because I was trying to download one that I saw in a video, but the Google Drive file is down
No
The file isn’t on google drive?
What’s your GPU I’ll give you the download
e
Can someone pls make a cash and Nico model
Ayo? @neat folio level 1 !!! 
Can someone pls make a cash and Nico model
is there a reason why my voice ai is not changing the voice? i have it set to the anime girl one because it comes with it and its just not doing anything.
This interaction has expired, use the command
/guides realtimeif you wish to see it again.
can i use commands in this chat?
yo
Don’t use voice ai
Use w-okadas instead
how i download
What’s your GPU
2070 super
-realtime
This interaction has expired, use the command
/guides realtimeif you wish to see it again.
rtx
Tells you how to set up, download, best settings, and bug fixes
alrighty thanks. but why does the gpu matter?
Howdy everyone.
different gpus proccess differently
Ayo? @elder willow level 1 !!! 
ohh
Ayo? @umbral tulip level 1 !!! 
lol
and its free correct?
i dont want to spend money for a little thing im trying out just for fun
you need a decent GPU to use it
Completely free and open source
is mine good enough?
is ilaria rvc working for u??
And you have to download a different version if you use amd
Yes
ok good
yea let me use a 12 core cpu instead of a gpu that has thousands
what does that mean
if i have an AMD RX 6700 XT is that good or just perfect?
Use this fork since your on AMD
the huggin face space doent work anymore for me
@umbral tulip you can also try this instead if you want more performance
nah i dont need performance. im just trying it out
so no W-Okada?
Hi!Nice to meet you all, and hello from Japan!
Hello Japan!
tell Japan that America said hiii
That’s a fork of w-Okada that gives better performance on amd
OK!!!!!!!
oh okay thank you
What doesn’t work about it
it works
i ran the start_http.bat but it didnt do anything really. is it supposed to do that?
oh my thats a lot of releases, which one is the latest for my GPU 😟
what gpu do you have
It won’t do anything for a second
AMD RX 6700 XT
dml
mk
okk
It should start downloading the required files and then start
Every step in here is explained on the GitHub by the developer aswell which you can find here.
Guide style is in the same as Blanc_dot's guide for simplicity and familiarity sake. Thanks to Blanc_dot for help on the guide.
Why should you use this version?
Minimum Requirements
Download
Download NV...
i downloaded the right one correct? it said nvidia and i have the 2070 super
@turbid mulch can you add this to the -realtime command?
it says building on zero on top left. could that be the problem
Yes
im restarting it
Wait a minute for the space to restart
Ila is restarting it
Gn
its downloading at a marvel of 5.56MB/s oh my god!
thxx
Just ate a pizza for dinner
it finished the download in under 2 minutes holy crap
Gtg sleep
i thought that hair piece was a filter or cgi but nope its a prop 💀
Just ate a pizza for dinner
a second one!
its done now
refresh the page
Ayo? @unkempt bluff level 5 !!! 
alright its up and running. how do i add custom voices? it keeps saying extension of file should be the following. pth,onnx
Download a model tagged with RVC in #1175430844685484042 and inside the zip file should be a pth and (most of the time) index
Omg i forgot this server lol
well what is a pth? is it a file
this looks complicated..
yes it is
so i got the model loading in right now and converting everything to FP16
Ayo? @elder willow level 2 !!! 
how do i change the input on discord to the voice?
Did you read the stuff about the audio cable?
model file
will now
im watching a video which should hopefully tell me how to do it
Ayo? @umbral tulip level 2 !!! 
Should be on the guide on both the GitHub repo and the rentry one
Videos usually contain misinfo
After that on the step Audio Setup it says what to use as input and output on wokada and discord aswell
Like for example you don’t need to download python or PyTorch to use it since it comes with it
videos are BAD
why
its time we make a video
how much happend in 1 year
alright we should be good now!
I just said why
oh mb i didnt see the message
Who where play Item Asylum?
Ayo? @ruby hound level 1 !!! 
Cool 👍
do other ppl in here use the AI realtime voice changer?? i need to know how to delete voices
Hello gays Help me how to create a voice model
check https://docs.aihub.wtf
Last update: Mar 10, 2024
#🌍│español also ask in help channels
hii are ur paid models higher quality than the free ones?
yup, thats why they are paid
you can find samples in the shop page
do u have one u recommend? that will sound good w american accent
dm me
what ai voice changer thats free should i use
just become good at impressions
hi
hi
Hi
how do we download the voice changer
can you guys help me please? i need to transcribe a youtube video, i wanna know any ai tool FREE to use cause im poor that can transcribe multilang videos for example videos mixed in japanese and english audio, i just need it transcribed dont have to be translated
Ayo? @rocky sage level 2 !!! 
hi
What’s your GPU
How do I fix the unauthorized error
Explain the error and what ur using in help channels
how to download the voice changer
Ayo? @faint kindle level 1 !!! 
somoene pls help
whats your gpu
Mm, you could try Whisper, you can do it locally or use Google colabs, a very fast and easy way in cloud is https://huggingface.co/spaces/Nick088/Fast-Subtitle-Maker
whats gpu
Do you have a good PC?
maybe
A GPU is a graphic processing unit
Do Ctrl+shift+ESC go performance tab of the task manager and check your GPU name
aymegadanna09
Is there a server the mods can be tested on??
is someone gonna help
thank you very much! it works! you re a life savior
is RTX 3050 6 gb good enough for RVC?
can someone help
@sterile anchor, I have found 19 results that match your search!
@sterile anchor #🔍│find-models
thx mb
Hi
D here
Yes
hi! 
Hiya
Hi
A friend from FakeYou recommended this server.
Hi
i cant get it to sound ok tho
it always sounds weird
Not much delay tho but its sometimes hard to understand what im saying
hello. I wanted to use a weights model, but I don't know exactly how to do that.
I'm wondering the same thing. A friend recommended this server as a bit of a FakeYou alternative.
my god,finally got a response
Ayo? @worn aurora level 1 !!! 
what is fakeyou?
It's an AI voice site that has indefinitely disabled user uploads.
They disabled user model uploads in February for site updates, and they haven't been reinstated.
always got a better option. find another similar product
that sucks,mate
but they should apologize
I don't trust them to reinstate them either.
I wanted to make a new voice in weightsgg from another one that had already been created. I want to add my base audio lines. Would it be possible?
Uberduck completely disabled user submissions last year because of voice actor complaints. I suspect FakeYou will do the same.
cuz ai taken their money away. they need to do something
but who can think about normal users like us who just trying to make life funnier.
We're not even taking their money. I doubt any of us have the budget to hire those people. If anyone takes away their livelihoods with AI, it'll be the big studios.
definitely true. those giants transfer the cost to us. they do the shit things, we gotta deal with it
anyone know how to make the voice changer more clear in discord?
⠀
Google Colabs :colab:
⠀
AICoverGen-WebUI
Useful for making quick covers, by Hina.
AICoverGen-NoWebUI
Useful for making covers, doesn't include a UI, by Ardha, by Eddy, Hina and Gdr.
RVC Disconnected
To train new voice models, by Kit Lemonfoot.
EasyGUI
The OG interface, by Rejects.
⠀
Yo, I'm r3dg0d
guys
I have seen that the default voice model in W okada
like the little girl one tsukoyomi or smth it's name is
it doesn't have any accent like I can honestly speak any language and it just matches my accent
does anyone have other voice model suggestion ( of girls ) that don't have much accent and sound natural
have index on 0 for least accent influence
I have no clue what index does so I always have it on 0 what does it do btw
hello guys, i am a Chinese college student. Developing my own AI video channel as my coursework. is anybody willing to have a try? It's free and safe. nobody response to me, plzzz.🥺 "BeFun AI" is on discord,pretty easy to use. plz help me
Controls the influence of the index
Which acts like accent
Some models have accent baked in so it’s not needed for those
So like I have a model which has a heavy english accent but I don't want it to have any accent and match me and my accent
what can I possibly do ?
Try uploading without the .index file
If the accent is still there try a different model
I will thanks a lot @storm meadow
note that in the stable version 18a, the index rate above 0 will eat more cpu usage
np my cpu is unused most of the times anyways
Ayo? @bitter hemlock level 4 !!! 
thanks for telling tho thanks a lot
se pueden utilizar modelos de voz?
Covers?
Ayo? @storm meadow level 107 !!! 
Can someone teach me how to use the GPT-SoVITS-beta api? I want to connect it to SillyTavern.
@forest quarry
@signal cairn n word
Ayo? @safe talon level 1 !!! 
Says the one who went into a discord server just to say the n word

anyone here listen to carti
Big carti fan
check dm
I just learned how to make good models and I thought to myself "I could make money off of this" until I remembered him
make a normal girl speaking voice model
wym by normal girl
just... a woman?
w-w-why would you want that
that girl still sounds like she's trying to be mommy
like it's a bit provocative still
you want a realistic mommy voice or a cutesy vtuber voice?
like dommy mommy, that's what he said
done
trust me i did that
people started reselling the free models
didnt give credit
or said they made it
so today i only sell models
i have multiple if u want
@storm meadow wtf i thought your pfp was a furry lol
damn, that's tragic. New patek
can you be my mentor 🥺
pleaseee, I suck at this. I'm retarted
I hate making models but I love using my ai vc with my friends. Some models that I want just don't exist and I really want this specific one and I'm trying to make it but ik it's gonna turn out like shit
Hello! I'm Zosia Foggy,
I’m tired of hearing the weights.gg example sounds😔
💀
Ayo? @ashen compass level 1 !!! 
😭
bad timing, this is not april
They should all be free
No
NFTs are lame
no
Yes
cope
They're not that expensive to make
and
I live in a country with some of the highest electricity and GPU prices in the world and it still costs like less than $2 to train a model
Why charge money for making an AI model from someones voice that you likely have no permission to use
and
I just lost my dawgg
i dont grt it 😃
Nah
hey babe
You need the knowledge, hardware and time to make a model
can we kiss under this hot sun
Kinda like saying all games should be free since anyone can make them
work (kissing me)
just finished fucking up my first model that I spent 6 hours waiting on 😊
ohh ok I was wondering what my volume should be
thanks dude
i have a trouble
Is there a good tutorial video out there that can teach you how to make a model for this discord?
there is an online web for creating voice models?
-colab
Suggestions for @half pond
- 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
- UVR5 NO UI for Google Colab, by Eddy Google Colab
- UVR5 UI, by Eddy Google Colab
It is incredible how people will enter this server and simply ask "what?" without looking on the server, reading the documentation or watching some tutorials
Hey everybody,
Can someone write me a google collab notebook, using the model realesrgan-x4plus-anime and 4x_DigitalFrames_2.5 ?
Hey guys, if anyone knows id appreciate your help:
Is the RVC hubert_base.pt a specific finetuned version?
how do we download the voice changer
hi
is there a good voicechanger for windows 11
no mention of flux t2i in this server yet?
hm?
@rigid cloak there has been a misunderstanding.
Yeah should be
What's your GPU?
As you said you got an AMD GPU, you could try https://rentry.co/forkvoicechangerguide or else use the Google Colab
Every step in here is explained on the GitHub by the developer aswell which you can find here.
Guide style is in the same as Blanc_dot's guide for simplicity and familiarity sake. Thanks to Blanc_dot for help on the guide.
Why should you use this version?
Minimum Requirements
Download
Download NV...
Modified wokada? What's this?
Ah there's a section on there
This seems really cool, I'm gonna grab this when I decide to be an egirl again
A really in depth guide too. I love this
It's the deiteris one, I seen shad talked about it #🔍│help-w-okada message
guys should i use rvc gui or is there like a better site
to make ai covers
i used colab before but it seems more complicated now
use rvc it’s good enough
in the task manager?
Ayo? @wraith pier level 1 !!! 
is it the one on github by Tiger14n
Ayo? @hushed ginkgo level 1 !!! 
Those require tens to hundreds of hours to perfect... same can't be said for AI voice models
It's not even creative work editing a dataset, just transformative
i think this idk i never tried it before Intel(R) UHD Graphics 630 @covert lake
I want to generate AI voice of the following voice actors:
- Molly Caitlyn Quinn
- Amy Gross
- Liana Mumy
- Morgan Decker
- Romi Dames
- Alejandra Reynoso
- Keke Palmer
- Elizabeth Gillies
- Ariana Grande
https://github.com/Tiger14n/RVC-GUI this? its very outdated
use mangio rvc
if you got a good pc use mainline or applio in our docs locally https://docs.aihub.wtf
If you dont got one, use Ilaria RVC Zero
Last update: Mar 10, 2024
Table Of Contents Introduction (with link) Model Loader (Download & Upload) Inference (use RVC AI Voice Models) Ilaria TTS Settings (Inference) Introduction (with link) Ilaria RVC Zero, is an RVC (Retrieval-based Voice Conversion) Fork made by Ilaria & mikus, running only on Hugging Face Spac...
you got a laptop and you got only the integrated gpu? then its better you use the google colab
-rt
This interaction has expired, use the command
/guides realtimeif you wish to see it again.
you could try cpu mode in this fork https://github.com/deiteris/voice-changer
its a pc not laptop
the only gpu you have is integraded one or do you see like GPU 0, GPU 1?
0
Then id advice the google colab i sent
its like: GPU 0
Intel(R) UHD Graphics 630
where
god dang it i wanted to change my voice with an app not voice clips
wdym? the google colab runs the program on a local google t4 gpu pc, you just need the rvc voice model
wait does that mean i can change my voice in discord and games?
yes for calls and games
do you need a realtime voice changer for calls or just change the voice of audio files/make ai cover ?
no i need a realtime and making ai cover is not a bad idea
the google colab i sent is for realtime, for making ai covers you can use Ilaria RVC Zero
Table Of Contents Introduction (with link) Model Loader (Download & Upload) Inference (use RVC AI Voice Models) Ilaria TTS Settings (Inference) Introduction (with link) Ilaria RVC Zero, is an RVC (Retrieval-based Voice Conversion) Fork made by Ilaria & mikus, running only on Hugging Face Spac...
for both? that sounds interesting
no not for both, like use the google colab i sent for REALTIME only, and instead if you need to make ai covers use Ilaria RVC Zero, but not like one does both realtime and ai covers
oh
Ayo? @wraith pier level 2 !!! 
maybe i will use this in the future
alright, for any help ask in help channels
alr
im new here so i didnt know where to ask
its fine
wokada is the realtime voice changer
rvc is for ai covers
lmfao i forgot the auto translator on
wha
i had the auto translating plugin on lol, just disabled it
thanks for changing it i couldnt understand what was that 
me neither, im not russian, but i was using a translator plugin because a russian asked for help in another channel 
so if he talks russian u can see it as english dub?
theres a vencord translator plugin for that and i also have an ejoy google chrome extension where i can just highligh any text, and i can translate it lol
vencord brings back memories for me
there was a server i was in using this vencord when i delete a message they use it to see what was it and screenshot it then send it

lmaoo
Arkadaşlar birşey sorucam
burası türkçe deyil
Ayo? @faint kindle level 2 !!! 
huh?
Does anyone here knows how to use RVC on Google Colab ?
Ayo? @steady spade level 1 !!! 
a
Hi
Do you need inference (use models) or train (make models)?
level 1 = send images in help channels
level 5 = send images in other channels
Make models
check https://docs.aihub.wtf and use applio colab or rvcdisconnected
Last update: Mar 10, 2024
k
might be a really stupid question but does mic quality heavily affect the ai voice changer
#1159290752195633273 and it’s not needed since all apps already have a create new account button
does any one have a daddy pig ai model?
HELL YEAHHH
Ayo? @elder willow level 1 !!! 
wheres the face swap collab
guys what is deepmale index?
/mix
/mix
do alt shift
how
or ctrl alt on arch linux
bro how does that work
wdym
why did my hotkey switch from win space to alt shift
what os are you on?
win 10
as far as I know, alt shift is the default for switching keyboard layout
why was my win space working before it suddenly switched to that lmfao
i do not know tbh
hi
Ayo? @gentle canopy level 10 !!! 
win + space still working for me
why "this application not responding" in find tab
this isn't edible
yesh it isss i made it edible now nomnomnom
😼
tank you sir or miss
Is there a larry and lawrie audio file?
Ayo? @pallid ridge level 1 !!! 
😔
gives u a cracked version of terraria

idk what im saying im really sleepy
shyways i'll see u later when i wake up
bai bai greenlauedeakzkzmxnn
what a leichter panzerspähwagen
/mix
Was scam anyways
You can search rvc ai voice model:
- #1175430844685484042
- #🔍│find-models
- https://weights.gg/
- https://huggingface.co/models (but watch out cus in hugging face there arent only rvc ai voice models)
- https://applio.org/models
- https://voice-models.com/
if there isnt one, you can:
- #1159289738314919936
- #1191429836321849435
- make it yourself with our docs guides https://docs.aihub.wtf/essentials/how-to-make-voice-models/
You can use FaceFusion https://discord.com/channels/1159260121998827560/1163571683848900629
Wdym audio file? If you are searching for datasets, they aren't shared for Copyright issues, if you meant a voice model:
You can search rvc ai voice model:
- #1175430844685484042
- #🔍│find-models
- https://weights.gg/
- https://huggingface.co/models (but watch out cus in hugging face there arent only rvc ai voice models)
- https://applio.org/models
- https://voice-models.com/
if there isnt one, you can:
- #1159289738314919936
- #1191429836321849435
- make it yourself with our docs guides https://docs.aihub.wtf/essentials/how-to-make-voice-models/
hi all
hello
@covert lake can you pls help me i am new here and i need help on an ai tutorial
don’t ask to ask just ask
wdym?
Ayo? @jade wave level 1 !!! 
Just say what you need help with
it's an ai voice thingy idk how to set it up
What’s your GPU
my what?
GPU
idk what that is
it’s a card inside of your computer used for graphics
i wanna know how to set it up on andriod phone
You can’t use the real time voice changer on android
You can do covers tho
i can't? isn't there like another app or something?
No because there is no audio cable for android
Which is needed for you to be able to use it on other apps
my phone is a samsung galaxy
doesn’t matter
is there a way you can set up an audio cable on android?
if you want to use the real time voice changer on android you technically can via colab but you won’t be able to connect it to any apps
No
It is possible to create ai covers tho
Not use the real-time voice changer on other apps
don't you just have to enable audio through USB in your Android device?
Hello
That’s not how the virtual audio cable works
It works by creating a fake speaker you out output to that works like a mic
Hii
hi
I think you already got your answer, you can't do it on mobile
Hi
Hi
does someone know a model that can scream?
hello everyone
i have some troubles with female voices
i dont know where to find russian good voices
realistic
everything that i have found just bad quality voices
How do you use what
Ai voice no pc
For covers or realtime?
huh
tts?
Yes
Ayo? @hollow steeple level 1 !!! 
RVC forks such as ilaria rvc mainline & applio have built in tts (using Microsoft Edge TTS to make a generated tts audio, which i suggest you to choose a tts model that is the same gender and language of the rvc model you wanna use, and then convert it with rvc)
NOTE: RVC isn't as good as GPT So Vits for tts, but gpt so vits can't use rvc models (and viceversa), and its only limited to: english, chinese & japanese, if you wanna check gpt so vits instead, read https://docs.aihub.wtf/tts/gpt-sovits/
If you wanna do tts locally (if you got a good pc):
If you don't got a good pc you can do it online:
-
Ilaria RVC Zero (Running on A100 GPU, free fasted rvc on cloud) and the guide
-
Use Applio 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
Bro simpler terms.s
U confused me
then you wouldn’t usedstand what to do
Bro j don't it before
Voice cloning of a website all I did was use a voice sample
And it let me generate any speech
Thanks
I literally told you all ways and explained you everything
Bro that was ai generated
I wrote it 💀
You'd just need to read to understand what to do if you want more emotions lol
nice ai reply
I even explained what to do to make it most similar to the rvc voice if you would have read it as it uses 2 different type of models for tts, as RVC is speech to speech
dint listen to that guy
💀
i use rvc andf it runs smoothly on just my cpu
if u got 12 cores rvc amd or intel will do u just fine
for inference it can work on CPU, but its slower, why not just use a cloud GPU that is wayyyy faster?
is it that hard to read SkullCry
what if some people in here are unable to use a good gpu
Ayo? @elder willow level 3 !!! 
I said Cloud GPU for a reason
btw alot of ur members asking for help in this server dont have amazing pcs like us
I dont either have a good gpu
pov my specs are in the 3 percent on the steam chart
i do it on cloud
That’s why we also link cloud options
Internet speed doesn’t matter
what? thats not how it works lmfao

I use Google Colab, Hugging Face's ZeroGPU
its all for free
ok

even the Ilaria RVC Zero HF Space runs on ZeroGPU
but whats ur internet speed
turn off ur wifi and use it then if thats not how it works
then it won’t work at all
seee
this is not cloud gaming 😭
Yeah but if you have slow internet the conversion speed would be the same
exactly
guy doesnt know wtf hes talkin abt has to use character ai to tell u that rvc is bad
The GPU processes it then sends it to you
first of all you are saying that internet speed has to do with cloud gpu 😭
second of all, DETAILED repo is NOT AI
is it that hard to read
so type c dock for a gpu lovely bottleneck bet its amazing performance
cloud gpu meaning cloud server
not my fault ur vague
No
it’s hard to respond to stupid questions
read the whole thing
hes talking non sense ngl
Yooo beeef this is mad
In order to use GeForce NOW, you need an internet connection with at least 15 Mbps for 720p HDTV signal format with at least 60FPS. For the best experience, latency to the NVIDIA data center should be less than 80ms but 40ms is recommended\

cloud gaming is different
thats COQUI TTS
🤓🤓
It streams video and inputs over
🤓🤓🤓
this is NOT CLOUD GAMING
its 2 different things SkullCry
🤓

Cloud GPUs are computer instances that provide hardware acceleration for an application without deploying GPUs on the user's local device, but rather using GPUs on a cloud service. They provide more flexibility and bandwidth than the CPU's L1 cache, resulting in lower hardware costs and total cost of ownership.Oct 4, 2023\
While HF spaces accepts inputs, has a GPU convert it and send it over
on a cloud service
🤓🤓🤓
Ayo? @hollow steeple level 2 !!! 
🤓🤓🤓

coqui tts is 0 shot which is lower quality than things like gpt so vits
again, this isn't cloud gaming
craz how both google and microsoft who offer cloud gpu services all say that it requires connection to there cloud servers
because it does
🤓🤓🤓
how else would you connect to it
meaning connection to the internet not running locally
Yes your right this time
he said exact quote his cloud gpu runs locally
ofcourse it requires a connection, you basically connect to a REMOTE pc that has good gpu, you send the inputs and things via internet and it processes on the gpu so the process doesn't depend on ur internet speed
Guys today I'm interview 2 dumbasses who are fighting over stupid sutff
you didn't even wanna read the whole thing lol
when did i ever say cloud gpu runs locally
i know how it works im just calling u out on the run locally part
any good site txt to ai voice
Let's see how long this video will be guys
👁️
i gotta get to work lel
you are talking to a walll
Now 1 dumbass dropped oit
Let's see who takes the win for the vid
when
W hype

This
where i put the ai voice model?
Use RVC instead
To use voice models from this server
If you need to use it online use Ilaria RVC
Table Of Contents Introduction (with link) Model Loader (Download & Upload) Inference (use RVC AI Voice Models) Ilaria TTS Settings (Inference) Introduction (with link) Ilaria RVC Zero, is an RVC (Retrieval-based Voice Conversion) Fork made by Ilaria & mikus, running only on Hugging Face Spac...
only he sees that i wrote that 😭
people nowdays think if its more than 10 words its ai lmfaoo
I want to generate AI voice of the following voice actors:
- Molly Caitlyn Quinn
- Amy Gross
- Liana Mumy
- Morgan Decker
- Romi Dames
- Alejandra Reynoso
- Keke Palmer
- Elizabeth Gillies
- Ariana Grande
Ayo? @cinder kestrel level 5 !!! 
You can search rvc ai voice model:
- #1175430844685484042
- #🔍│find-models
- https://weights.gg/
- https://huggingface.co/models (but watch out cus in hugging face there arent only rvc ai voice models)
- https://applio.org/models
- https://voice-models.com/
if there isnt one, you can:
- #1159289738314919936
- #1191429836321849435
- make it yourself with our docs guides https://docs.aihub.wtf/essentials/how-to-make-voice-models/
anyone know any telegram(or discord?) sources where I can find remix stems?
i mean still anyone can do a simple game
-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
- UVR5 NO UI for Google Colab, by Eddy Google Colab
- UVR5 UI, by Eddy Google Colab
helo guys
Anyone can do the deadpool German dubber Model???
can someone help me about prompting ai to create images
use super prompter or research about prompts
Hi can someone give me the latest version? Because I can't download it directly
bro
my problem is . i want to get side view vectors for my game
but AI keeps coming up with cross profile shots
as in the angle of the gif for example
Ayo? @hidden furnace level 1 !!! 
Can you give me the latest version? Because I can't download it directly
use image to image
Can you give me the latest version? Because I can't download it directly
what
Voice ai for pc
we dont use voice ai
we use okada
For pc ore android?
use controlnet
true
never do anything on android
thanks .
PC, u cant use realtime voice changer on android/mobile
i,m using browser https://stabledifffusion.com/generate its img to img produce not really good results
Thank
Ayo? @unreal scroll level 1 !!! 
if you have a good gpu just install stablediffusion locally
I recommend comfyUI
Can i use this for real time at pc?
i got 1050 ti
how much vram
DPM++ 2M SDE Karras
J Eulera
Euler
LMS
Heun
DPM2
DPM2 a
DPM++ 25 a
DPM++ 2M
DPM++ SDE
DPM++ ZM SDE
DPM++ 2M SDE Heun
DPM++ 2M SDE Heun Karras
DPM++ 2M SDE Heun Exponential
does it has anything to do with these settings ?
it keeps producing side angle images
no
4 gigs i gues
can you tell how man gb it is
i only need 3-4 images lol dont wanna bloat the hard drive
yes, whats your GPU?
idk
ComfyUI_windows_portable_nvidia.7z
ComfyU I_windows_portabIe_nvidia_27_07_2024.7z
ComfyU I_windows_portab|e_nvidia_c u118_or_cpu.7z
ComfyU I_windows_portable_nvidia_cu118_or_cpu_02_07_2023.7z
which onwhoyuld you recomend
it probably won't take much if you just download 1 model
maybe i canshow you if you provide me with image permission
I'm not a mod lol
'ello how are we chat
anyone knows a good text to speech ? free ofc
elevenlabs
oof
heavily depends bro
I run a 3050 ti with 4 gb vram
ComfyUI is champion at VRAM efficiency
depends which version of SD he`s using
A1111 is just from 1998
also resolution
sdxl works fine with me
which res do you use?
normal sdxl res
1024x1024?
yeah
and how many seconds per image
how to download the voice chager
you get like 1200 characters for free
-realtime
This interaction has expired, use the command
/guides realtimeif you wish to see it again.
sometimes it's like 30 secs
i mean if he doesnt have enough ram he gotta wait
my ass needing to wait over an hour to install rvc from scratch because they forgot to put the install batch file in the newest release
what
mainline?
nah applio
how does it take an hour to install rvc
applio has a lot of dependencies
depends on your connection
skill (applio) issue
i'm not updating, it wasn't already on my computer lol
Ayo? @marsh sleet level 1 !!! 
nah it actually works better than mainline in most cases
mangio honest reaction:
mangio is deprecated
like half an hour to download the 5 gb file and then another to extract it
oops
for some reason the python files extract SO slowly
whats your internet speed
5400RPM HDD be like
i am using an nvme ssd everything else extracts at 150mb/s
the .py files just are like 700kb/s for some reason
cpu issue
true
this is a 14th gen cpu i bought less than a month ago the pc is new 💀
cropped, worst quality,cross shot,cross profile,sport car, angled views,three quarter perspective, front view , rear view, perspective, depth
for the negative prompts
but i need one where i can clone my voice with mp3 and then use text to speech 😄
RVC then you can use another tts service then infer RVC over it
Or you can try GPT SoVits
I am getting brainrot from reading this chat
WHAT THE FUCK HAS A CACHE FROM A CPU TO DO WITH A FUCKING GRAPHICS CARD DEPLOYED IN THE FUCKING CLOUD
thanks so much i am a noob but i will try my best even tho i bet it wont work for me
yeah train xtts on your voice and then use rvc on that
so many words i dont understand 😄
haiiii yui
same but not as much the green names
that's so TRUE
can you please explain what a CPU cache has in common with a graphics card?
they are computer parts
Both have to do with computers
cause apart from the silicon and electricity they are not the same
fair point but so do dust particles
true
Most people think they know, talk nonsense and don’t go away from their yapped opinion/response
dust filter looking like some kind of felt carpet after a year
hi, do you have a google collab notebook that makes ai covers + separates vocals from instrumentals, and is there an updated version of covergen
because I have an old version, it does not work more precisely already from hina
but like how the hell do you mix up a CPU cache with cloud computing
I know scenarios where both matter but still wtf
Nah it's the same speed :p
Only thing limiting you is your download
downloading cell 1 taked me like 9 mins
The gpu speed remains the same
I know 😭
but if you have shit download speed that's between the backend and you
the speed between the backend and the download server is still the same
If your making covers use Ilaria RVC on hf spaces instead
if using cloud
Please don't bash him yui
It isn't welcoming
archually, you are using your rj45 connector as a pcie4 connection to connect your computer to the cloud gpu
fr SkullCry
Woof ^^
Well that's too technical
yo i tried to download the popular girl voice changer for github but i cant from drive bc too many viewers downloaded this recently, any bypass?
Average Litsa Impersonator:
You could instead download a version from hugging face
me when I connect the glooper joopert to the jimber but my gloop speed is only 5 h/s instead of 17:
What’s your GPU
You are lucky this chat has to be sfw
radeon hd rtx5090tixtx
thank goodness.
can someone help when i tried downloading cell 2 a ngrok url didnt show up even when it finished
Did you enter your token for it
Furry chat is still sfw sadly :p
yes
sadly ?
Yui smells
oop.
He is actually super cute I'm kidding
i got banned from a server once because i had a better discord plugin that showed hidden channels and i sent a screenshot of a channel with a name like this to general chat
F
Finally... Someone that wants to do it to me (joking)
DONT CRY
fav AI hub moment today
nothing beats L1 cache, no ram no nothing
i didn't get banned from a server, but i didn't feel very welcome or appreciated as a member with half of the staff team in that discord possibly being ableist or something like that because i wasn't like, treated fairly and whatnot.
that shit is fast as fuck boy
how it feels to finally let go of everything and KILL people
did that change?
so i just left bc i couldn't handle it and it wasn't good for my mental health
Meow :3
not sure and it isn't my concern anymore, bc doubt anyone rlly noticed or rlly cared i quit the server 🤷♂️
staff still shouldn't make ppl uncomfy
and yet they do
right, and you guys aren't like dat which makes me feel more welcome here and all that. too much drama in the last discord and in their minecraft server i got targetted on
star react 
if anyone from the staff team is an idiot just tell one of the admins and we'll deal with them accordingly (kill in Minecraft)
Hey guys :DD
Please ignore my user
Heya
ye, im aware! litsa helped with one situation involving a model maker speaking so harshly to me so that was sorted out
change or kick
that's good to hear
Give me a raise
Aight
anyone can help me clone a voice quickly with GPT-SoVITS?? 😦
Ayo? @frigid cairn level 2 !!! 
Lmao
Join the sanctuary server and ask there
You’ll get better support for it there
link?
The vanity is gg/osai
@pliant elm I'll be waiting unde your bed
under my bed is not somewhere you want to be
there are like
50 books
So much knowledge
holding up my bed because I'm too lazy to fix this shit
who is stopping you from pronouncing them the same
Ayo? @marsh sleet level 2 !!! 
the british peasants did and that’s how we ended up with “ed” being pronounced differently at all
nakeeeeeeeeeeeed
but with the e pronounced as in eat
naked (one syllable)
Oh god what is this
linguistics 🔥
fr
@pliant elm give me a good reason to train on anything less than fp16 you furry
rx 6600 but i couldnt even download it bc its not available on drive anymore
@timid musk bitch
wheres that
you train on fp32 and quantize to lower when inference bbg
Ahh I thought you were saying training on dat is okay
💀
Pookie I misinterpreted, u are so cute
thx
Ayo? @jagged crystal level 1 !!! 
Stop pretending to be menhqueen
how tf do i open this bc on the w-okada looked simpler
It tells you
this is a fork of w-Okada that works better on AMD GPUs
Read the readme
okk
hello
do i just download feom the firdt page like download code bc there isnt any exe there
me and cute are like matter and void, can't exist at the same time
I beg to differ
there is no other valid opinion
@storm meadow
Shut, you cute
my opinion is the correct one and every other opinion shall be treated as high treason against humanity
where do I put the voice models at?
voice models folder
wheres the actual voice changer thpo
👍
@pliant elm
I don't understand the question