#🧬│ai-chat
1 messages · Page 207 of 1
Sovits gpt in development. And diffsinger (similar) is good sound quality. What are you trying to make?
👋
Musicgen ai
hi everyone!
yurrr
with on l
Yo wassup
a
Need help learning how to train my own voice model for music and then utilize it. Please message me privately if u can help
👋
Hi
Wasup lind here, why i cant select or see the gpu option to my dedicated graphic?
@winged wigeon whats your voice how can i download it
i made it xD
Hi all,
I am a Singer. I am wondering is there a way I can generate similar music from an Original song and sing using my voice.
Any help/info is appreciated
Thanks
my vc isnt working
!howtoask
How To Troubleshoot 
- Don't simply mention your issue, like "
my rvc is not working". - Describe the step you are on, what you're trying to do, the RVC you're using, a screenshot, etc.
- The more context, the better.
- Don't be desperate. You can ping a Helper, but if they ignore, they aren't available/don't know the answer.
- It's okay if you're frustrated, but don't take it into this server.
- Don't DM without prior consent.
- Don't ask for every little instruction. Put your own effort & test things by yourself.
- Don't ask to ask.
- Check if your answer is a Google search away/on our guides website.
i mean, i joined like last week idk
Hello
Yo can someone gimme the link to google colab version
check our docs https://docs.aihub.wtf
Last update: Mar 10, 2024
Cant find in there just send ples
there are different google colabs with different things, just check the rvc folder, and iside of it the cloud folder, you will find the google colabs here
with also the guides
could i get the google colab version of the app, like link to it
@paper blaze можете помочь мне в ЛС?
all the links and guide are in the docs link i sent, just check indide of it and read inside of the cloud folder of the rvc folder
There are many colabs
that do different things
like
oh
please just check it out
alright ty man
yw
Hi
H! everyone
hello
Hello
Ayo? @lilac nova level 1 !!! 
What is it
Good evening, AI Hub!
anybody got a girl voice model for a deep voice person like me?
Hello
Any model will work
Tune it +15 or +16
Hey
how setings for rtx4050 i use delay
hello. is there any rankings based on the reviews/qualities etc? thanks.
@pulsar zodiac Are you the one doing the Nikke voices?
Nah it doesn't work like that for eleven labs, there isn't a way to use it for free unlike rvc and the tts we offer support with
hello
Nope, i dont think you can do that
Also bc rvc is audio to audio, eleven labs is text to speech
So nah
Because kits.ai is greedy, it matters more about the quantity of users they can reach than the quality, thats why we dont like it
It isnt like the rvc v2 which is open source, they prolly use the v1 or even and older technology for their service
what's an ideal length of clips for a voice to be trained and sound p decent?
hey, what happened to Harmonify?
no such file or directory as Harmonify
did something happened to the github
can someone do that thing with the list of colabs
We use RVC v2 and other tts programs, if you need a TTS and want to use the rvc models in #1175430844685484042 , you can use the rvc mixed with tts, check it out more in our docs https://docs.aihub.wtf we got many ways to do it either locally if you got a good pc or online hoth for free
Last update: Mar 10, 2024
Harmonify? That @twin fractal colab ?
5-10 mins
I guess so? that's the only one I know of
is there a new interface colab?
some one can help me ??

Nah you cant train or that
Too old of a GPU chief
Do it online
Ask in help channels
would it be a little wonky with anime characters? i'd have to get the voices from episodes most likely and use the vocal remover thing
can you do the list thing with all the colabs pretty please
For making ai covers or training models? Sure there are in our docs https://docs.aihub.wtf idk much of harmonify as its just a rvc fork made by eempostor ig
Last update: Mar 10, 2024
I really wanna interface again🫢
These are all the colabs with all their respective guide
Some have ui
Some dont
Some are for training
Some just for using the voices
Depends on your needs
thanks
Ayo? @blazing scroll level 4 !!! 
Yw
Wot
Ayo? @lilac nova level 2 !!! 
Check the cloud folder inside of the rvc folder in our docs https://docs.aihub.wtf
Last update: Mar 10, 2024
hi
what can i do if i can hear myself but my voice is not changing
Ask help in #🔍│help-w-okada or #1192011222023950368
does anyone know any sites to train on like voicemyai where i don't have to stay on the site during the training
You can use rvc google colab which you can find in our docs https://docs.aihub.wtf and its all free, but you can't still like leave the site
Last update: Mar 10, 2024
thanks, but do you know any where I can leave the site ? and that it's free to train ?
RVC/any forks to train locally if you have decent 8+ gb vram Nvidia gpu
girly all i have is my phone that barely works and looks like it's about to seperate into half at any given minute
i used to train it on kits and voicemyai but they all cost now
Ayo? @elder willow level 1 !!! 
anyones got the acapella for hide away by synapson? 😢
THATS WHAT I LIKE TO HEAR!!
KITS.AI IS TRASSHHHH
TY
yea those sites are also greedy dogshit, so the colab space is your only option
Nope its not possible, there isnt any online way where you could leave the site for training any type of ai model
The only your free way is google colab
It cant ever work if you leave the site
Is like you want the youtube video to play but at the same time leave the yt site literally close it
Not possible
You can seperate vocals and instrumentals with some free programs and sites, check in the reaources folder inside the rvc folder of our site https://docs.aihub.wtf
Last update: Mar 10, 2024
was wondering what the best settings for mdx23c was.
You don't have any other options than google colab, and btw it doesnt depend by ur device as its on cloud, its a site so it wont be slower or anything, either do smt else and wait while it trains, or request someone to do a model for you for free in #1159289738314919936 , or if your phone got multitasking, use it at the same time with another app, as long as you dont close/leave the google colab site
Wdym with best settings for mdx23c
how can i make a module ?
it's all good now
I GOT A GLOCK IN MY RARI 🔥
You mean model ?
yall has anyone tried bs reformer v2
Mvsep said the quality metric was higher than mdx23c
its more aggresive
@timber grotto nuh uh
he sent some hindi form
i assume it only int
it's thai bro
whatever
Wdym
it is for de-echo de-reverb
Think I should ask in verified chat lol. that place is more active
nvm
i need the zip file of some one i have the voice
Ayo? @gritty slate level 1 !!! 
So you mean make a model, check out our doca https://docs.aihub.wtf
Last update: Mar 10, 2024
You mean the wokada realtime voice changer or loke rvc ai cover tool takes alot of time? Ask in help channels
Hi guys, I know it doesn't have much to do with voice cloning, but I wanted to know if there were any free tools or colabs to translate videos from one language to another while maintaining the original voice.
Do you know anything about it?
too many errors any easy way?
this is the easy and free way tho
if you got errors
ask help in help channel
maybe SoniTranslate but idk much of it, check it out here https://github.com/R3gm/SoniTranslate
those 300 apoch take too much time
what should i do?
you are using google colab? also its normal it takes time, training ais isnt just a click lol, and also depends by the dataset lenght
Nick sono italiano anch'io, comunque grazie mille
ask help in help channels not here
ok
Ah okay lol, prego
what should be the batch size for gpu
Sai se riesci anche a clonarti la voce durante la traduzione?
8
ehh non credo che puoi con sonitranslate, pero puoi usare i modelli rvc del server
doesnt matter the gpu ?
Ah ottimo!
gradio training section
local or colab
local
what gpu
rtx 3060 6g
👆
so 12gb vram
i put 12?
stick with 8
wont damage gpu?
i mean ai prob makes ur gpu have a smaller lifespan
thats just how it is
so 12 or 8 ? for more healthy way ?
8 will use less gpu
ok then would this damage too much after all?
hm?
tnx for help
laughs in training models for 12hrs or longer straight hundreds of times and hours of gameplay
i am not new here
Back from the death 💁♀️
😭
my gpu refuses to die
па
What will get if I boost server
u should worry on the dust build up over long term usage (ex-crypto miners having run 24/7 laughing even more)
ai booster role
lol i bought my gpu second hand and it was caked with dust
had to give it a good clean
guyss need help jsut got the voice changer for the villager voice and res is at 11665 is that normal
Raga come faccio a vedere le ricerche complete su weights?
Wow, is there anything similar that clones the original voices, or uses rvc models?
soni translate seems to have that ability
Hi, is it possible to run a RVC model entirely on the cloud without requiring a high-end PC and for free?
its on 9 after like 15 minutes
and how long will it take to finish with 8?
(time per epoch) × (target epochs)
Is it possible?
this could be done with whispering tiger
can please someone @me?
@hoary crystal

hello everone
Can you tell more about this?
wsp
Native UI for the Whispering Tiger project - https://github.com/Sharrnah/whispering (live transcription / translation) - Sharrnah/whispering-ui
hi
Need voici model for french
you can search:
- #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
if there isnt one, #1159289738314919936 or make it yourself with our docs guides https://docs.aihub.wtf
Yes, check our docs https://docs.aihub.wtf
Last update: Mar 10, 2024
So I made this
Ayo? @elder willow level 1 !!! 
Don't promote yourself here, use #1159290752195633273 .
Okay
nvm wrong channel ^^
Hello guysss
i know that, but im searching for an official acapella or a sung version so that my AI cover is cleaner.
i've been here for a while wym 💀
unless the creator of the song has posted one, i dont think you can find an official one lol
thats why i told you its better to separate it yourself
Hi i'm new here
hi
hi
how can I upload a model to hugginface
🤗
how can i make my own model
Last update: Mar 8, 2024
guys I have a problem with tensorboard I'm on Paperspace not locally
-colab
- Applio, by IA Hispano 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
- RVC Disconnected, by Kit Lemonfoot Google Colab
- easyGUI, by rejects Google Colab
- Applio, by IA Hispano Huggingface Spaces
- 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
👋
Hello!
Hello
I keep getting this error when I try to open UVR
Oh didnt know much abt 11labs, but you're welcome i just tried to help
For help please ask in help channels
uh do anyone know an ai voice changer to use the models in #1175430844685484042 withouth having to pay? ._.
Hello, how to separate the beat from the vocals well
because these sites vocal remover etc don't work well
i need a song of Gibbs - DRIVE
yup, wokada ai voice changer for realtime, please check out more about it in the pinned messages of #🔍│help-w-okada
alr thx bro
yw
mm maybe this could help you out https://docs.aihub.wtf/rvc/resources/vocal-isolation/
Last update: Feb 29, 2024
Thanks so much
are there any free girl vc models that sound acctually legit
Ayo? @stable belfry level 2 !!! 
how do i upload a voice model?
Hey there!
merhaba
What 🍴 does means in conversation? My english friend sent me it and dont explains
hello everyone!
Hello
Can someone pretty please make a model for me. I’ve been trying to make a model for an inside joke with my friend and I’ve been trying for the past few days to make it and can’t get it to work right.

hey men
yo
Боже
What a circus
Crocus City was attacked by cold-blooded militants, and migrant worker plasterers were caught
Spectacle
Ayo? @lyric umbra level 1 !!! 
???
hi
-colab
- Applio, by IA Hispano 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
- RVC Disconnected, by Kit Lemonfoot Google Colab
- easyGUI, by rejects Google Colab
- Applio, by IA Hispano Huggingface Spaces
- 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
yw
Anyone down to make an AI model?
for ai model requests, check #1159289738314919936
request it in #1159289738314919936
Nah nah i mean like on personal terms/business
I’m making an ai model of one of my teachers, that stuff isn’t just available
if you meant like request a professional paid rvc ai voice model then yea you can put the paid tag in #1159289738314919936 where only model masters can take it as commissions
or you meant request an ai model of another type of technology like llm?
wdym it isnt avaible ? i mean you can request it in the channel and then send samples of the person to the model maker which takes your request so he can make it
or if you want to make it your own, just try to ask in help channels
Last update: Mar 7, 2024
Pon
?
🥱
Does anyone know if there is a Smii7y voice model? i saw a YT vid of them using it
you can search:
- #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
if there isnt one, #1159289738314919936 or make it yourself with our docs guides https://docs.aihub.wtf
-colab
- Applio, by IA Hispano 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
- RVC Disconnected, by Kit Lemonfoot Google Colab
- easyGUI, by rejects Google Colab
- Applio, by IA Hispano Huggingface Spaces
- 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
Ayo? @frigid cloak level 1 !!! 
alguien me ayuda con las voces
What was the best girl voice for valo ?
Someone help
Can someone help
I really wanna know
Need for voice ai
@idle crag hiii
what does index do for rvc
whats a good thing to convert yt videos into mp3 files?
😭
i don't get it

yt-dlp
In your rvc Installation folder
i sent a screenshot
Hai
hello
Oops ok
what
I'm Nicholas
What did they say
how do you deal with voice cracks in rvc
Removing the reverb
Separating the main/lead vocals or separating harmonies
Clean acapella
Using the pitch extractor fitting the best
they mean with okada most likely from their recent message
Ohhh
hi
There is literally zero reason to use kits
anyone got okada working on mac?
yeah, on an m1 air
what's the issue specifically?
Paywall,limited downloading access per month,training models is paid
Is ov2super available in training colabs?
yes, in rvc disconnected
It's basically rvc but worse and paid anyway
wat does changing the index do
You just gave a reason why not to use kits.ai
Yea
It's something about model's accent
nothing so far, just wanted to make sure
Ayo? @full vale level 1 !!! 
There's like voicemy.ai,fakeyou.com etc or just use colabs or use it locally
ah
yup! it basically applies the person's accent and how they pronounce certain phonemes
Hi all
Ello there
Hi all
Hello
Hello
Hello
gorp
slam
Hi
Anyone here try suno along with rvc?
@torn tulip join the stack
who are you?
please man
in need of a good 5th human fan not cuting it
7-7 de_inferno inform me if joining is a possibility
yo for the voice changer, i cant hear my own voice, any suggestions as to why this is happening to me
why does it say this aplication is not responding
@fleet ingot 
@lethal swan 
Basic math
Are the bots down none of them are responding
Anyway to train the ai for my voice or someone else's voice? I want Amitabh Bachchan voice
Which one?
none of them
Hi
Ayo? @haughty stone level 1 !!! 
i dont think
but i was using appl
Oh no idea about Applio, but if you were facing any issue with AstraLabs one lmk
Hi~
a que juego
estaba jugando
onda por que tenia una guitarra
y eso
que se toque una de leo mattioli
yo
Ayo? @tepid sky level 1 !!! 
U
hi
@bleak fossil I'm eventually sorry to join AiHub model maker joint
Hi all,
I don't know if it is right to send messages through this channel? But I have a request about two models; Can you prepare audio files of one person being "Tom Hardy" and the other being "Brian Molko 2022"? I couldn't manage to make a sound file. I want help from you.
Thanks in advance.
Ayo? @elder willow level 1 !!! 
hi
hey guys I have this https://huggingface.co/huggingtweets/narendramodi but when I insert it in the RVC v2 it doesnt work
Hello guys
Bro how long should the model voice be ? 10 min ?
Download it, and upload to Google Drive, then give access to all, and can edit your files. Copy the link and paste in the Colab
how do I do that?
Go to the HuggingFace file, and upload it to google drive
can u share a tutorial?\
Ayo? @eager bloom level 1 !!! 
I am quite busy right now...
hi

yo many epocs are needed on an average to get a decent voice?
or does this not do well with speaking
oh wrong channel mb
Voice my ai is not free anymore
Video send super papa
Ayo? @proud cloud level 2 !!! 
ok #🔊│ai-development @proud cloud
hi
why
Worst type of memes to ever exist
hey hello
hello
You can also help me create a sound model
idk how. i stolen
is there a model easist to use
hello

What's the recommended pitch to change a song a male originally sang to a female?
maybe +12, but it depends, its better if you change it slightly till you hear which is the best
all rvc ai voice models are used the same way, check our docs to know more how they work https://docs.aihub.wtf
Last update: Mar 10, 2024
ask in help channels
and also check our docs https://docs.aihub.wtf
Last update: Mar 10, 2024
check in our docs https://docs.aihub.wtf
Last update: Mar 10, 2024
-colab
- Applio, by IA Hispano 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
- RVC Disconnected, by Kit Lemonfoot Google Colab
- easyGUI, by rejects Google Colab
- Applio, by IA Hispano Huggingface Spaces
- 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
A question on that… It seems like if the pitch change is not +12 or -12 then the original instrumental doesn’t sound right
What should you do to instrumental to match the changed pitch?
alright buddy
you mean the original instrumental sounds lower ?
guys I need help with tensorboard
I'm on Applio on a VM and I can't run it it's running on localhost
I was making a male voice sing a female song so -12 works with the original instrumental but the voice then becomes too low and not natural
Turns out -6 works best but then it sounds like singing off tune when combining with the original instrumental
Any reason you're running it in a VM ? Performance will be horrendous
If you want to access the instance without a public link;
You should be able to edit the code to make applio listen on the right network to connect from the hypervisor system
Just make sure that the firewall isn't preventing VM <-> Host communication
I'm on Paperspace
Oh nevermind then
everything was ok with the mangio fork
I typed make tensorboard and it worked
but now with Applio it only sets it up locally
how are you running tensorboard ?
I've tried ssh tunneling and all I could find alone online hut nothing worked
tensorboard --logdir=logs --host=localhost --port=6006
doesn't work tho since it's local
no I tried via putty
I struggled finding my ip address of the vm
then I read an article to type arm -a in terminal
There's probably better flags to do it, but I use this regularly, from my machine :
ssh -L 8080:localhost:8080 user@paperspaceVmIp
and an IP popped up but ok not sure if it is the one
replace ports with appropriate ones ofc, but that does port forward the remote's 8080 to the local machine's 8080
how do I find the user and Paperspacevmip parameters?
I don't use paperspace, but you should have been given the VM's IP and a user to connect with ?
nah I'm on a gradio interface
I just press buttons like create notebook on pytorch
Ah fuck
and I run then the commands to run applio thru the terminal
you're connecting via a gradio.live link right ?
yes
when I had the mangio rc fork
the tensor was working with a public url
and it was josted on a url in the form of tensorboard/jdhsifi/paperspace.com
Ayo? @daring canopy level 5 !!! 
something like that
tried it already
--bind_all ?
let me try it again hold on
there we go
the thing you send me is the sauce I was looking for
I'm bumping my head since yesterday thank you so much man
Glad I could be useful 👍
finally oh my goodness
Hi guys, just entered this discord😆 Are there any good devs here that want to join me in starting revolutionary AI software?
Elaborate pls
are you a good dev?
you a good dev?
Kinda ? Still, people would most likely want to know what they're getting into first
I mean what is a good dev?
100%. I'm looking to start a new AI system and I'm looking for talented devs to help me with it (it's a revolutionary idea) therefore I want to partner up with great devs to make this work out! Do you think you could solve a buggcode if I gave you one to test your capabilities?
Ayo? @abstract wing level 1 !!! 
I don't necessarily have time to spare these days 😅 Not really interested in being part of bigger projects too much either, at the moment
which AI system? another LLM for what purpose?
have you heard about musicfy? it's a great text-to-audio AI software. What I'm thinking of doing is something else, something new that almost nobody is doing. already got some great distributors to put this on the market. if you're a talented dev/software engineer and would like to hop on this journey then shoot me a private message
hello its me
There we go, people are gonna know which fields are involved now 😉
err... i assume you are talking about the idea of new competition against Musicfy and other software.
maybe it should be keep enclosed so that the idea doesnt leak to others?
music generation? idk much about but could be interested on some open solutions
no, my idea has got nothing to do with musicfy. my idea isn't a text-to-audio software, it's something else, something new. And you're right, i don't want to disclose too much here, therefore if you're interested in partnering up and make some big bucks, the shoot me a private message
lets give the question to others to guess for their own 
I am not a something so sorry no.
do you think you could solve a buggcode if i sent you one here?
I will give the code to ChatGPT because I dont know anything about web dev / software dev.
so you cant solve a code on your own?
Hell, I am not even a programmer or something ( it is completely unrelated with what I'm working on), but we got some developers out here that may able to help you.
if i clone a voice are there like programs that i can put that clone voice file and they do voice changer?
Like realtime voice changing?
ye
no worries, good luck on your work. For anyone else, please send me a private message if you're interested in partnering up and make this revolutionary AI software into reality and make some big bucks
My head would say Tortoise / XTTS pipeline. Actually I dont even think I know one program that could use just audio file for voice changer.
A 👍🏻
i want a voice changer and to sound like a specific person for funs
yeah, check out musicfy. it's free too
Ayo? @abstract wing level 2 !!! 
- he said realtime
- musicfy poopy
About the pipeline I am thinking,
You saying something to the mic while sending those directly to Tortoise/XTTS. And when it done in couple of seconds then put it onto the output audio

Which is... quite a brute force method that required programming knowledge
why....
just use rvc
😭
True :clueless:
Only if you have like 2 hours or so to train
xtts wont sound close to the person
i dont know why tf ur pairing it with tortoise?
also tortoise models take hours iirc
From my experience both programs are having similar quality and speed.
That's finetuned model which is optional?
ohh
yea but if its 0shot it will be shitty af
also probably slower
needing it to go through whisper then tts then back
tortoise aint the fastest
and xtts is shit
for vocal cloning
"Never Be Scared To Fart While You Pee, There Is No Rain Without Thunder..."
TF2 Player, "THE KING"
💀
i wish i could send a stupid video i made
I went to the Coqui docs jus to make sure.
XTTS finetuning have at least 2 min audio limitation, but I didn't see anything that required XTTS training to have the transcription files?
If you want to promo yourself, use #1159290752195633273
i made a meme with the ai voice
Ayo? @woeful flax level 1 !!! 
which to be fair, much inaccurate than when I just give it a 1-2 min sample
Ye thats rthe right channel
( go make sure it is not copyrighted )
oi
i dont think it is copyright
then it is fine to put it #1159290752195633273
oi
Aqui tem mais do EUA dock the other server
well thing is i can't put it in there it's just a file and i cant post files there
does higher epochs mean better RVC?
i'll just upload it on youtube and make it unlisted
@jolly flint onde estão as vozes em ptbr
not necessarily,
in which ways are higher epochs better then?
A mn simples,vai no Voices models aí tem a tag ali se clica,aí depois acha o BR e clica no Portuguese
god... the original guide was gone.
anyway, you see the TensorBoard
Now if you'll excuse me I have a test to give to the students
Ayo? @jolly flint level 3 !!! 
if I remember correctly it is g/loss? where it may have a huge slope downward and get flattened.
g?
loss/g/total
choose the one the most bottom of the line.
I remember I once some guide say that if you look at the other graph, the spiky one.
when it starts going up
the spiky one? 😭
…. G
Ayo? @upbeat vigil level 3 !!! 
I no longer train RVC models since my training on Mori Calliope's model.
https://docs.aihub.wtf/ check the guide regarding tensorboard
Last update: Mar 10, 2024
ty
I moving back to the AI Art field so...
im not training any models though, just using okada
@jolly flint vc teria alguns nomes de vozes que estao boas
Ayo? @void cairn level 1 !!! 
yeah I think.
We Training some Models with a Voice Singing Cover Versions for using a Voice.AI
Hello there.
You have my curiosity because I have been playing with all of these and I know some developers
Desculpa @void cairn mas eu nn sei qual são as melhores,mais espero ter ajudado e peço perdões por nn conseguir algumas voices boas para isto,Sorry
I Decided to Making a Song with using an AI Cover Versions.
Ayo? @serene sequoia level 2 !!! 
So you train model with AI sample to AI?
And so I Made this is a Song Called: Everybody Wants to Rule The World From Tears for Fears - Sing with Super Mario (Nintendo), So I Have any Unfinished with using My Capcut and Bandlab.
You're using ai covers as a dataset?
Ayo? @jade geyser level 2 !!! 
you must at least have a GPU
not integrated GPU like Radeon 680M or Vega 8 or UHD 630
so is there anything like this?
no I mean you need a GPU or at least CPU to run it.
running Stable Diffusion on CPU is slow compared to GPU
assuming you are using a desktop
am using a laptop
you have any idea how much VRAM you have on your GPU?
i cant use cloud?
hold on
you can.
so no need to
but how i can use it?
✅ Official Website: https://aicontroversy.com/
✅ Awesome AI Tools: https://linktr.ee/aicontroversy
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
🎦 In this video:
Kickstart your AI art journey with this CivitAI stable diffusion tutorial! Uncover the new feature that lets you dive into stable diffusion models directly on their website. Bid farewell to tedious setups and...
skip to CivitAI Tutorial Walkthrough
its not 100 perecent free
it has points
They are free for now
The thing about buzz or credit system usage on image generator is still under discussion
yo
And well you dont have to know this much within the discussion
i cant do from image to image?
cuz like i wana make albumcovers uk what i mean
Yea it is one of its limitation
Ayo? @tight cypress level 13 !!! 
😔
sa
Tomorrow, Sing with Mario and Luigi for Modern Talking - You're My Heart, You're My Soul, and so for This, so Stay tuned Guys Released on 2024. This Coming soon for Let's Go Brothers! from The Super Mario Bros. Movie 2 Soundtrack. On June 2024

@tall vapor check dm
Hola
Ayo? @dry lark level 1 !!! 
when?
When
just when
can anyone give ops on a ken carson ai?
idek why they didn’t time out mikus
sapphire did it
like wth
Are there any afro-american man models?
hi
stinky
Poopy
Y'all got drugs?
???
guys where can i ask for help regarding problems with mega on step 2 in the colab?
which one is the latest colab stable rvc version please share
Ayo? @pale raven level 9 !!! 
Whats considered the best/easiest text to speech ai (that is also free)
Play HT
can it do voice cloning
Only 1 for free
mb, i should have said the best locally/online hosted one that can do voice cloning, completely free
...
The best ai was voice my.ai
Ayo? @vague bolt level 1 !!! 
For free but it's now 10$ a month
hey , can someone help me with github voice changer , i have done all the installations completely but the only problem im facing is whenever i speak, it dont generate the ai voice , my voice is repeated
Hi
sup
who
-links
Suggestions for @daring garnet
- 🍏 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
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.
better than that paywalled site
Hello
How do I use a downloaded voice model, instead of the hugginglabs link
hi
@covert lake
Hi, does someone know an ai for answer question about documents i give ? Like the ai remember all the documents and can answer about question i ask? Thanks.
@elder willow please don't spam , you can use #1159290752195633273 for promoting your ai covers in that channel but no spamming. and no promoting in other channels
ty
Howdy
Alright so gpt sovits
Ayo? @daring garnet level 2 !!! 
Which is the best ai voice changer for these voice models?
why tf did my vid in #🔊│ai-development get deletes
Skill issues
i wish you could see how straight my face is
Lmao
@covert lake nicholaaas

hi
#links
hi
hi
is there a way to get okada google colab Real Time Voice changer for free? I'm on MAC, and the GPU isnt that good
hello
hai
I need help with something
?
yes there is a wokada colab
-realtime
This interaction has expired, use the command
/guides realtimeif you wish to see it again.
i already have that. but it disconnects me
cause u have to pay for the GPU'S
if its because of the free daily limit finished, you can't do nothing about it than waiting 24 hours or using an alt google acc, there is no other way
hi guys where do i find the download
download of what
the voice changer
-realtime
Tag suggestion for @dry oar
Description: This one has more options and is somewhat more convenient to use than Real-time RVC.
Link: Rentry
Credits: ravencutie21
Description: More accurate than W-Okada's, but requires a decent GPU.
Link: Google Docs
Credits: teas.hi
Description: Text to speech with RVC
Link: Rentry
either if u dont got a good pc, check this
oh ty
and for help of it ask in #🔍│help-w-okada or #1192011222023950368
hi
hi
you can search:
- #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
if there isnt one, #1159289738314919936 or make it yourself with our docs guides https://docs.aihub.wtf
Hello i'm rapterhumaraptor
hii
Why hello there every!


Ayo? @fleet ingot level 12 !!! 
Nah miku is better the way she is. Her sister teto has ai now
Hey y'all
Is there anyone who can help me in voice channels?
Please for help ask in help channels
ok
so whats ya favorite teto used song :3
hi
hoi
yo guys what is the best girl voice
hi
письки
what is bro waffling about
mine
can you send it over
Hai poopsies
Do NOT send text to the ai hub text channels!!
Join me in VC sometime if you want to really get AI'd up
Ayo? @scenic cairn level 1 !!! 
hi
AAAAAAHHHHHHH
can u make me a rich amiri voice model?
no stfu
i was mod here bitch
i aint new
bro check when i joined
Ayo? @oak vale level 2 !!! 
Welcome bro
hii
羊文学さんの「more than words」をカバーさせていただきました
アニメの雰囲気にぴったりでホントにいい曲です
羊文学 - more than words
TVアニメ『呪術廻戦』「渋谷事変」エンディングテーマ
▼OriginalMV
https://youtu.be/kGY6N9DL4Jw?si=OF6HiQ2XeltqG6qJ
----------------------------------------------------------------------...
This is what's playing right now
whaaaooo that sounds amazing]
the voice model has gotten so good
thats amazing tuning :o
im used to the old voice though
-colab
- Applio, by IA Hispano 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
- RVC Disconnected, by Kit Lemonfoot Google Colab
- easyGUI, by rejects Google Colab
- Applio, by IA Hispano Huggingface Spaces
- 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
Maaaaaan hace mucho tiempo que había traducido esto, pero soy bien perezosa xdddd
Link:
Romaji: no lo hice D:
#neru #teto #kasane #synthv #重音テト
Whisper utau is the best vb
im still used to this shit
This song contains questionable elements; it may be inappropriate for younger audiences. Parental guidance is advised; better watch this with your parents.
SUPPORT
■Patreon→ https://patreon.com/tanjirotaidana
■Ko-fi→ https://ko-fi.com/tanjirotaidana
Join the Twin-Drill Revolution Discord server!
→https://discord.gg/kbtrg5P
Special thanks to bi...
5 years ago XD
《原曲》
https://youtu.be/pgXpM4l_MwI?si=o9bNVkYVgLSyFRdl
《歌》
重音テト
《調声・イラスト》
やすたんげ
→ https://twitter.com/anco8pizz
can someone help me?
i can't make ai cover can someone make me song ''DR. VODKA - NARKOTYKI'' with Senko voice?
Ayo? @elder willow level 1 !!! 
-colab
- Applio, by IA Hispano 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
- RVC Disconnected, by Kit Lemonfoot Google Colab
- easyGUI, by rejects Google Colab
- Applio, by IA Hispano Huggingface Spaces
- 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
jhai
Hey guys, im still searching for the best E-girl voice model. Any suggestions?
Hello, anyone know why this is? so i have been making my own models and i wanted to test if it sounded real and sended to a buddy of mine, now he can just do 5 pitches up and sound exactly the same as the person i trained the voice off, what i have to do is have the pitch around 14/15 and i sound a little bit ai, if i do 5 pitches up a sound like a guy who has something in his throat
(i have nvidia)
Not been aleble to fix it myself
@tardy vector
he can help
how many epochs for roughly 3-4 minutes of data?
damn
Should i dm him?
yes
I dm'd him, thx for helping dude
are there any other good live voice converters than okada and mangio? mangio doesnt seem to work ingame. okada works but the quality is worse than mangio
hi
Guys
lol
let me know if you find any good ones please
Ayo? @elder willow level 1 !!! 
Is there any GPT-SoVits Colab?
Yea but that shit might kick you
Im using multiaccounts xd
By kick i mean the disallowed code one
For the colab it's on the rvc boss repo
Just type his github name one the github search shit and go on the gpt sovits repo
On mobile so too lazy to get the link
Gpt sovits
Xtts poop
Gpt sovits is where it's at
🗣️
can anyone direct me to any simmilar servers like this one?
i mean this cant be the only one right
how do i fix the voice change my cpu keeps spiking up to 100 everytime i speak
hi
gpt soviets
Hi
✌️
You shut up xd
Gpt soviets
yo
hi
hi
Anyone can help me on #✨│ai-help please? (sorry if I am being annoying, because I am so excited making my first AI cover).
shut off pls
@fleet ingot 
@lethal swan 
Greetings everyone
What does the DDR in ram mean?
WHY THERE 5 DANCE DANCE REVOLUTION GAMES
yo
I haven't used RVC since the last server went under.
Has there been any significant improvements and updates?
i forget when rmvpe happened but use that instead of crepe
aaaaand theres custom pretrains now. worth using for the most part. thats really all
Thats... pretty much mammoth shit-tier of old.
What are pretrains for?
Ayo? @quiet hedge level 1 !!! 
the way i was explained, 80% of the human voice is basically the same, so when using a pretrained, most of the model is made of the pretrain, then tuned using the dataset
you only need to worry about pretrains if youre training models yourself
Hi guys you know where i can find the voice of the noise from pizza tower?
Ok
Oh really? And here i thought i would use pretrains to cook lasagna.
lasagna voice model

Good,now bye,see ya NEVER
Ayo? @mystic basin level 1 !!! 
Hello, how is everyone doing?
I am not able to connect to voice chat after setting up my input device
can it be fixed?
We need chatgpt emoji
Hello
Hi
@elder willow who r u
just saw that msg
how many days of mute do u want
you can only choose between 7 and 7
Hello guys
Hi
Hello
Pinged
how doi post a rvc
damnn
do u get automatically joined when u download a ai app?
No
Hi can you maybe check youre dm?:)
Ayo? @distant leaf level 6 !!! 
i dont check my dms
i mostly have them turned off because i talk to friends
what
Hey
check here to know how to post ur rvc ai voice model https://docs.aihub.wtf/extra/model-maker-role/
Last update: Mar 7, 2024
Thank! You I already figured it out
Ohh because someone told me to message you so thats why i asked
He said you where the man
All I can say is to make sure you have a good and clean dataset with all of your vocal range
I have
how you look at tensorboard on 1006rvc
Any decent dev/software developer looking to join in starting a revolutionary AI software, hit me up privately. (There are big bucks that can be made💰❗️)
tomm1 is crazy
I'm interested
Hit me up in private
indeed
how do I gain access to post voice models?
very provocative question, will ignore it

