#🧬│ai-chat
1 messages · Page 309 of 1
i tried to train a 500 epoch model on intergrated graphics like damn it took a whole day.
to train 1 model
hola
Penis
sinep
I could ask someone else to train the model for me, but I'm going for a Finnish voice model, which I doubt it's anyone's strength here
And preferably for voice-to-voice purposes, not tts
@solar zealot ok
Does someone know how to like exclude background sounds ?
Yes I do
Can you please help me?
Okay
It’s making some Wierd (POP) sounds
the original or the ai voice
From the ai voice
@golden canopy dont trust him all hes gonna try is telling you things that will harm your pc
Oh okay Ty
No I wouldn't
@earnest dragon rizz
You are making stuff up
Just Tell me 😂
What
I just ruined your call
Send me the ai voice audio
No you didn't and I'm not in a call
No I won't and you are weird for saying that
The word call doesnt always mean phone call.
U mean the model?
then what
@golden canopy hes a dev of hentaihaven
-rt
This interaction has expired, use the command
/guides realtimeif you wish to see it again.

Stop making up stuff
tf dev on hentaihaven o--o

What am I supposed to do with that I just have the problem that there is some random popping sounds
Ayo? @golden canopy level 2 !!! 
Guide style is in the same as Blanc_dot's. Thanks Blanc_dot for corrections. Most technical information comes from deiteris.
Last update August 30th, 2024: New b2309 version
Translations added for:
German: https://rentry.co/ForkVoiceChangerGuide_de
Turkish: https://rentry.co/ForkVoiceChangerGuide...
@golden canopy why are you talking to the troll
I'm not a troll your the troll
are u using a cpu or a gpu?
Gpu
follow the link I sent
what chunk did u put?
@golden canopy its virus
he should just follow the settings guide I sent
yeaaa he should
It's not and what problem do you have have.
WHAT IS THAT
roblox is getting weirder
@pale patrol
wat
@golden canopy use 32k
Guide style is in the same as Blanc_dot's. Thanks Blanc_dot for corrections. Most technical information comes from deiteris.
Last update August 30th, 2024: New b2309 version
Translations added for:
German: https://rentry.co/ForkVoiceChangerGuide_de
Turkish: https://rentry.co/ForkVoiceChangerGuide...
bro
Follow this. this tells you per gpu
There is no 32k
Anything above is studio quality
his talking about okada for fuck sake
Wtf is okada
@pale patrol your momma is pregnant with a car
😭
yeah because Nep is on something
I just this real time ai voice changer
Im giggling
Yeah just follow the link
the voice changer ur using rn
@pale patrol ur mom ate a entire bus
Okkkk
imagine he is using rvc gui
I heard
Im too
oh god that would be terrible
Send the picture of it here #🔍│help-w-okada
Ok
Nah this is better https://www.youtube.com/watch?v=pkpVg71HPVo
What better way to go back to Hogwarts than with the remastered LEGO Harry Potter Collection? Experience the adventure all over again as you battle the basilisk, compete in the Triwizard Tournament and take part in the Battle of Hogwarts with enhanced graphics and 4k resolution.
Available Tuesday 8th October, 2024 on PS5, Xbox Series X|S and St...
I played it on xbox.
Its not
I returned on pc cuz no achievments
Luckly the remastee will havw
@earnest dragon im about to comen
Im boutta 100% lego marvel super heroes
Prove it
4k enhanced graphics on the already good game the only thing it's missing is some kind of way to use motion controls like the wii version
Lmao 😆
Ayo? @fallen ruin level 25 !!! 
ayo
why tf did that random japanese dude marry hatsune miku 
What's the most realistic girl ai model here
Your mom
I wanna troll my gc 😭
Get gud
@fringe haven @fringe haven
Donald Trump
I moaned
@fringe haven
why did u have to say it 
hello
No
hello
hi
hello
how can i create a voice model?
anneme hidrojen bombası atmam diyenler 👈
@warm harness shur up
😔sorry
whats ur pc gpu
error:
t4x2
@elder willow
https://github.com/aris-py/RVC-AI-Cover-Maker-UI-Kaggle/blob/main/core.py#L334 you forgot to add the f before ""
hi
Ayo? @elder willow level 1 !!! 
hi
Ayo? @split owl level 2 !!! 
Thanks bro
Get off discord then
Vote Booster: Vote now for a 10% boost. https://arcane.bot/vote
I'm currently programming (web development) for 7 months, but I want to create a web app using the RVC model: https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI. Is it possible to use this model in a web application using JavaScript, React, NextJs? So no Python.
Why would you want that as a web app when you can use applio
What is applio? I don't really have experience with building ai apps.
Ayo? @leaden flax level 1 !!! 
@latent hedge
then if you don't have experience then why are you wanting to make a web app if you don't know that stuff.
@ionic crystal
Hmmmmmmmmm
Really strange opinion
https://soundcloud.com/lilgiackvi/cartel is it good for ai?
can i get help with making an ai cover?

monitor set to headphones
Ayo? @elder willow level 1 !!! 
Use mvsep to convert out the background vocals
Elaborate
I recommend uvr bv remover but you can use mel roformer karoke
Use the other option instead of default to get the background vocal files
The one in the middle
Ayo? @elder willow level 2 !!! 
what do u mean
so i use the uvr bv remover to get the file and then how do i convert the file
Download the vocalsback
Wait lemme send you a rec
then it will work?
do i just put the vocalback straight into to be converted
or do i need to convert vocalback to something else
Spaming that much makes me not help you at all
DAWG WILL THIS SHIT FUCKING LOAD
what
hehe
So
Audiostrip.com free trial vb splitz 4 I reccomend over uvr or mvsep
Go into mvsep press ultimate vocal remover go to the bottom and press that, you can either use the default or .5 aggression
You have to press the 1st dropdown tho
Mvsep isn't as good
The fuck are you gonna do with 3 isolates for a month
You have to elaborate whats the issue
Not just “HELP ME!” Dumbass
thats been there for god knows how long
do you make it acapella before doing that step - surt?
what's the issue if you can't hear yourself then set monitor on voice changer to head
can others hear it
why r u doin that fiona
send a screenshot of it to here or here #🔍│help-w-okada
dont fight guys
What is the site for voice models
@wide cargo
i did it and it seperated but the ai doesnt apply to backing vocals still
Hi
yeah you have to do each separately then combine
Hello, does anyone know how to download as exe? i not knowledgable enough to compile source on VS 🙏
what if i asked 2 questions instead of needing help
why would you need to compile
there's no download on the github on in the releases tab, only the code
why do u need a good pc to use this software and not like other vc
whats inside this w-okada thing that leads u into requiring a good pc?
It's ai.
-rt first link
This interaction has expired, use the command
/guides realtimeif you wish to see it again.
what ai is that
RVC
rvc okay thanks for za information
it's basically obvious when all the models are rvc
im bad at memorising and im lazy to do anything cuh
Then if you're lazy then why in a ai discord.
btw the wokada fork can help for not so good gpus, whats ur pc gpu? else u could do it on cloud
my gpu is bad lemme check
what gpu
intel(r) hd graphics 520 lol
oh integrated graphics
u can only do things on cloud
what that
For Realtime Voice Changing for Calls online (for who doesn't have a good pc, YOU CANT DO THIS ON MOBILE):
- Google Colabs (4 hours daily of free T4 gpu, easy to use, require only a google account) :
- How to use Original W-Okada's Voice Changer Google Colab
- Modified W-Okada's Voice Changer Google Colab
- Kaggles (30 hours weekly of better GPUs, T4x2 & P100, harder to use, requires an account and a phone number)
- Original W-Okada's Voice ChangerKaggle
- Modified W-Okada's Voice Changer Kaggle
u sure this would work on me?
He seems clueless with anything pc related.
its on cloud..
Locally = runs on ur pc
Cloud = runs on remote good pc
so yes
pls don't spam ping someone 
Yeah I told him a while ago
im bad at computers, btw cya
alr cya
why did he join if he is bad with computers imagine being genz and not knowing really how to do stuff on a pc
that's most of young people tbh, they use only social medias lol
there are actually people who buy phones just for socials, or whole ass gaming pcs just for roblox
Yeah they go from iPad roblox to pc roblox because there favorite youtuber has a pc
ye not like it really matters as roblox is not an heavy game
yeah thats what I'm saying and one of the big roblox creators this one guy told me he created deepfakes to replace the need for them in some of the videos and actors can be used instead.
Typing is not as good because they don't teach typing really in schools.
damnn 😭
Yeah I heard it was Lankybox
how do i search for a voice model
thing is school thinks its not needed to teach about IT because teens stay all day with their phone, but staying all day on tiktok doesn't really help you much with IT
You can search rvc ai voice model at:
- #1175430844685484042
- #🔍│find-models
- https://weights.gg/ (login required)
- https://huggingface.co/models (but watch out cus in hugging face there arent only rvc ai voice models)
- https://applio.org/models
- https://voice-models.com/
- https://thevoicemodels.com/ (for Turkish Models, login required with discord and level 2 on their server)
if there isnt one, you can:
- #1159289738314919936
- #1191429836321849435
- make it yourself with our docs guides https://docs.aihub.wtf/essentials/how-to-make-voice-models/
thx
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.
no because typing speed doesn't matter unless you want to learn coding and want to type fast.
this should become a command
real
now i understand why captchas are hard for me 🤖
Sbc
the openai captchas are the worst they are nine things long and they need to be perfect or you fail.
what
i used to use a local hosted rvc gui but i reset my windows and dont remember how to set it up again
does anyone have an easy online alternative for using index and model files with audio files for rvc
reuploaded*
it doesn't even include the config yaml files at all
btw refer to these public models instead: #708579735583588366 message
my favorite audio tools for making input and output sound good and stuff is SpectraLayers and audiostrip.com and borrisfx audio plugins
You mean wsg AI Enthusiasts
hello
I am looking for a developer have experience about OCR system.
If you are interested , plz DM
Does it matter in 2024
For what use case
can someone help me? it just says wait web server ... done and it just shows blank on voice changer client demo
Ayo? @rain crypt level 1 !!! 
I have spectralayers 11, but I'm still heavily using RX 11 for editing overall
spectralayer I prefer because it keeps the surround sound intact.
Soundmefreely is that one pretty as mf
do you have experience?
yo
Can someone make me Eldorado.gg seller account can pay him
No
What use case
if you are interested, plz DM
Ayo? @tacit cypress level 1 !!! 
hey can i get some help with a very simple problem im having with the voice changer ?
ok xd
Thanks but my homie just gave me a mobile version so sorry for askin
bruh there isn't a mobile version of realtime voice changer 😭
prolly u installed voice.ai app which isnt even realtime on mobile
Yes there is I just need to verify by getting 3 free offer
Ayo? @green dragon level 1 !!! 
its literally impossible bc phones don't have Virtual Audio Cables
You the real one ong
what lmfao, what app are u even talking about lol
It's a site
which?
Brb
wait @covert lake i have a question
Ayo? @violet granite level 1 !!! 
its literally impossible because realtime voice changers need VAC which no mobile phone has
Tweak fix .co
why is my F0 Det.. only giving me 2 options?
fck
thats a site about 'modded' apps..
Ok
💀
Its nothing more than a virus this shit
i warn you lmao
the 3 offer human verification is just a scam
is this some sicko ad lmfao
its literally connected to the same 'mod' site of before
It rizz tut.com a scam
Umm
Oh
there is no mobile voice changer, and u are saying sites about virus modded apps..
I'm to broke to buy a pc
then there is no way to do it on mobile, phones miss a virtual audio cable to do it
its just impossible
too bad for you
same here, that's why I got a laptop. It's cheaper than an iphone
Ayo? @humble minnow level 19 !!! 
Yeah but less performance less vram and not upgradeable
does anyone know how to use the voice changer on mp4's / mp3's
yeah, my 8gb vram limits me a lot...
same twin
Foobar2000 convert it to wav
covrt wat to a wav
the mp4 or whatever
and then use applio or ilaria zero hf
where do I put that in the voice changer? or is that what thoes r 4
no the ones I listed are file ones w-okada is realtime only
Ayo? @earnest dragon level 22 !!! 
so I put the voice models in applio or ilaria with the wav file?
Stop Giving this as a example gaming vram and ai are 2 different things gaming doesn't use that much but ai uses a lot more.
Clone the GitHub repo, the configs are there
Cool thanks but I was excited to try the melband reformer karaokee viper and the drumsep models mostly.
Why is there only cinematic and low
Vac ban
ok you're not wrong but the AI workloads actually vary a lot, from UVR inference that can run on 4 GB vram, to RVC training that takes between 8-12 GB for batch size 8 and 16 respectively, to some heavy workloads like Flux and 12-70b LLM inference
Yeah you never give a gaming as a example of ai vram usage and also the settings on that benchmark table is using bad settings.
My animate diff crashes at 576x384 resolution so I'm stuck with generating videos at 512x336 and upscaling. 16gb should allow me to do 768x512 or 720p videos, which results in better quality images.
reminds me of the old srgan I tried a year ago on a 6 GB vram gpu, and it threw OOM error on 800-ish resolution
@orchid slate
i heard someone in panic.
can't wait for this to get buried when ppl would just use any decent TTS
https://www.techspot.com/news/104661-audible-inviting-us-based-narrators-train-ai-voices.html

hi girls
Ayo? @weak flower level 1 !!! 
hi girls
Are there any good ai voice model for create an audio for listening test?
Ayo? @ionic forge level 9 !!! 
Kinda educational... and adative for English subject
what r the models used for if you dont mind explaining
I seen a youtuber show this and I thought it was hilarious
Create an audio about conversation
I saw Murf AI but it's not free
fuck.
So does it apply to a voice clip or your mic
No
text to speech
Edge, Bark, Tortoise, GPT-sovits, do you think any of them enough?
Yeah it would get buried when fishspeech and batch text exists and then you can even use this one paid AI to then lipsync a video to make it look like the characters or person is reading the book
Nah Fishspeech then paid ones are the best for tts
thanks for adding the former which is the newest, but he's looking for the free one which is also the former you mentioned
yeah so fishspeech then
RVC Voice Clone and New Paid Lipsync ai combined with tongyi emo portrait using one image https://autocompressor.net/av1?s=mzRQPjcf
hello?? anyone I can ask about an ai voice error thing?
What error
I keep getting "index -1 is out of bounds for axis 0 with size 0"
not entirely sure why
hello? @earnest dragon
Local or what
Local, I dunno what it means
I'm just using AICoverGen
Use Applio instead best local way
-local
Suggestions for @quaint pilot
- 🍏 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.
what text to speech app do I use
Fishspeech
idk how to install these its so confusin
how do i get my voice model into this thing
Ayo? @still chasm level 1 !!! 
hi
hii
rvc models are made to be used either in rvc for ai covers or wokada in realtime voice changing
depends on what u need and ur pc gpu
There are different Text To Speech (TTS) AIs:
GPT So Vits: RVC isn't as good as GPT So Vits for tts, but gpt so vits (few shot tts, which means needs just a lil training for models) can't use rvc models (and viceversa), and its only limited to: english, chinese & japanese, if you wanna check gpt so vits instead, read https://docs.aihub.wtf/tts/gpt-sovits/
Freemium 11labs: A easy way to do TTS is https://elevenlabs.io/, you can't use RVC model on this but its a mostly premium easy way for good quality TTS
FishSpeech: FishSpeech is a 0 shot (no explicit training needed) TTS, if you got a good pc you can use it locally else use their site
With RVC Models:
RVC is natively for Speech To Speech, but forks such as ilaria rvc mainline & applio have built in tts (using Microsoft Edge TTS to make a generated tts audio, which i suggest you to choose a tts model that is the same gender and language of the rvc model you wanna use, and then convert it with rvc)
If you wanna do tts locally with RVC Voice Models (if you got a good pc):
If you don't got a good pc you can do tts with RVC Voice Models on cloud:
-
Ilaria RVC Zero (Running on A100 GPU, free fasted rvc on cloud) and the guide
-
Use Applio UI Colab (with google colab T4 free daily limit gpu)
-
if you don't wanna use edge tts, you could try another tts ai from our tts index and use the output as an input in rvc
Hi I'm Eric from South Korea, nice to meet you
i understood that I got applio and when i open the bat it opens a chrome tab and Ive explored the options i just dont know how to import the models im finding
should be said in https://docs.aihub.wtf/rvc/local/applio/#download-
Last update: Apr 01, 2024
you can enter the model link in the Download Model feature like the following example:
or you can manually place the files in the logs folder like the following example, and then click Refresh in the inference tab
🙂
hi guys, Is there anyone here to help me with this? I can't understand what he's asking me for
Oh, I can't send the picture
[VCClient] wait web server...340 http://127.0.0.1:18888/
if it spams that message, delete stored_setting.json then restart
hey hey hey
I require assistance with fitting an image onto a 2560 x 1440 canvas
I wish to achieve it with generative technology
is anybody able to help?
-rt first link (edited)
Cxsmo
-rt first link (edited)
This interaction has expired, use the command
/guides realtimeif you wish to see it again.
Ayo? @tired token level 1 !!! 
use an upscaler like ESRGAN: #1221468455723733094 message
then you can downscale a little and crop it as needed using photoshop or anything
Ayo? @elder willow level 1 !!! 
PhotoShop is a paid service, any other method?
Ayo? @delicate prism level 1 !!! 
I said any image editor, gimp and krita are the example of open source ones

ah, got it
Made these today, Tell me what you think, Definitive is Young Elvis while 1976 is older Elvis.
Ayo? @inland zinc level 1 !!! 
u can't post audio files because you are level 1, also, don't post copyrighted audio files if u meant to send an ai cover u have to upload to yt and send the link in #1159290752195633273
ur welcome
Hi
selamün aleyjküm
Hello, good morning everyone, I'm using Applio, I downloaded it here on my PC, but it turned off on Epoch100. Can I continue training after 100? If yes, how do I do this?
Ayo? @frail wedge level 1 !!! 
hello guys im new here, you can call me nathan :3
yo ~ 's been a while
Yea, now yea
hi
Hello what's going on guys
hi
embed failure
How to input the mp3 file to change the sound
f
any tips on how to make a voice model sound less robotic and breathy and make it more clean?
Ayo? @deft dove level 1 !!! 
Trust me, you can be even more pale ( me )
erm
yea
im gonna do a little silly
hello
i thought u left lol
any tips on how to make a voice model sound less robotic and breathy and make it more clean?
Realtime or what
scam shit, gtfo
its like the 3rd time
i see that stupid message
how many bots acc does he have
why doesn't this server have the discord bot that has all the scam links and stuff an just auto deletes them
which?
Wdym paler
yo im new im just searching for a way to get a link to a lil uzi vert AI voice does anyone know
thank you
@earnest dragon @soft mural penes
anyone here a bit good with ai that can help me? lowk struggling and need it for school project
Ayo? @soft mural level 1 !!! 
You shouldnt have started it
Nice english
lol why, i just need to convert some lyrics into a lil uzi voice but
struggling w that yea
Get gud
thats kinda why im asking if anyonen can help me explain how to do it mhm
never heard of that before but that looks good ngl
look guys
No
smash
Thats tungsten
SMASH
smashsmashsmashsmashsmashsmashsmashsmashsmashsmashsmashsmashsmashsmashsmashsmashsmashsmashsmash
🧻
hi
So you want to cheat on your school project 🤔
nope we need to use ai!
but my duo partner sucks at using it and so do i we watched a million youtube vids about it
is it just a repository containing all links or a discord bot because i thought it was a discord bot that automatically deletes every scam link registered
and we still are at step 1 and it needs to be done 26 november
@arctic echo why are you here 😭🗣️
Ayo? @rose glade level 1 !!! 
ples respect the bot
aint that still a bit lol
-docs
- How to use RVC Mainline Colab by Cauthess
- Full AI Voice Model Training Guide (local) by Christopher Villanueva
- AICoverGen Colab Guide by Eddy (Spanish Helper)
- Create a model with RVC disconnected (colab) by Angetyde
yea but we need to make a a full song / disstrack against some teachers in a fun way lol + music video
anyone got a really good juice wrld model
Assalamu alaikum, is there any Rraenee cover?
Yeah it's constantly updating repo of all the scam links.
hi
Yeah if he doesn't level 5 will feel longer to achieve.
how do i use kaggle
What's the reasoning for kaggle do you not have a gpu.
i just want to use it thats all
i dont know how to run stuff on kaggle
If you have a gpu then there is no reason to use kaggle
-kaggle
- Applio Notebook, by Vidal Kaggle
- Applio Notebook, by Shirou Kaggle
- Music Source Separation, by Shirou Kaggle
- UVR5 NO UI, by Eddy Kaggle
- RVC Mainline, by Hina Kaggle
- Original W-Okada's Voice Changer, Kaggle
- Modified W-Okada's Voice Changer, Kaggle
- 📖 How to use RVC Mainline Kaggle by Cauthess
Note: Kaggle limits GPU usage to 30 hours per week.
nvm i figured it out
Why do you want interior kaggle if you have a gpu.
so i can have it attached to myu playstation for exactly 30 hours
but ia lready got it running now
they ass
there was a rlly good one on the old ai hub
-colab
- Applio, by IA Hispano Google Colab
- RVC Disconnected, by Kit Lemonfoot Google Colab
- RVC Mainline, by Hina Google Colab
- AICoverGen-WebUI, by Hina Google Colab
- AICoverGen-NoWebUI [English], by Ardha, fixed by Eddy, Hina and Gdr Google Colab
- AICoverGen-NoWebUI [Spanish], by Eddy, Hina and Gdr Google Colab
- UVR5 NO UI, by Eddy Google Colab
- UVR5 UI, by Eddy Google Colab
- Modified W-Okada's Voice Changer, Google Colab
While the Colab free plan provides up to 12 hours of daily usage, the GPU is typically available for only about 4 hours each day on average.
i just saw kitten fetus
https://www.weights.gg/ and also the newer ones are usually better because of better pretrains and stuff.
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.
nah that model from like 2023 on ai hub the best one till now i tried many also from weights
You can search rvc ai voice model at:
- #1175430844685484042
- #🔍│find-models
- https://weights.gg/ (login required)
- https://huggingface.co/models (but watch out cus in hugging face there arent only rvc ai voice models)
- https://applio.org/models
- https://voice-models.com/
- https://thevoicemodels.com/ (for Turkish Models, login required with discord and level 2 on their server)
if there isnt one, you can:
- #1159289738314919936
- #1191429836321849435
- make it yourself with our docs guides https://docs.aihub.wtf/essentials/how-to-make-voice-models/
ye true, but ig it would need the bot to be build, i cant add bots but i can tell staff abt this
Yeah I know someone else would have to add it.
hi
hi girls

eddy is going to release UVR5 UI kaggle
It's the first port that works well for me.
@ionic pumice
f
Hi
Nobody
hi
hello
ported by me
port minecraft to kaggle 
some improvements made by eddy
No
but.. I.. am steve
Nah your Nick
hi
Uncensored Version: https://youtu.be/GDHO7OVKB5w
Linktree: https://linktr.ee/cynthoni
Bandcamp: https://cynthoni.bandcamp.com
Instagram: https://www.instagram.com/cynth0ni/
TikTok: https://www.tiktok.com/@cynthoni
Censored version: https://youtu.be/CvkFUQRQVR0
Linktree: https://linktr.ee/cynthoni
Bandcamp: https://cynthoni.bandcamp.com
Instagram: https://www.instagram.com/cynth0ni/
TikTok: https://www.tiktok.com/@cynthoni
...
how does nobody know about cynthoni 😭
#ask Is this AI HUB software like Applio and Coqui?
Had a dream of your mom
No
I dont neither
I see you acquired new culture ☺️👍 very based
What program would you recommend for Real Time Voice Conversion w/ RVC models?
embedd fail
check this
uvr5 installer
Salut, quelqu'un parle français ici ? J'ai besoin d'un petit coup de main 😉
-rt
This interaction has expired, use the command
/guides realtimeif you wish to see it again.
Irl
stay tf back out of me you fking bloody eyes 🔪🐥
One two neps going to be here
Three four he fucks all your trauma
Five six he killd all your friends
oh hell nah
Salut, quelqu'un parle français ici ? J'ai besoin d'un petit coup de main pour crée un modeèle svp
Ayo? @sly robin level 1 !!! 
Does someone know how to get XXXTentation ai voice
doesn't uvr already have a ui just not a webui
eddy told me to do it
and the local uvr that already exists is old
does anyone know a free high accuracy text-to-video and image-to-video AI?
But currently UVR is not as good as other.
Free or paid
free
let me be happy with my achievement lol
Hi! I hope you're doing well. Sorry to bother you, but I’m reaching out because I need one of you to help me create a voice model pls 🙂
hell nah
Okay
sorry
ok sorry i feel bad now
i did a an ai cover but its not working, the bot says its done but i can't hear it
Why are you using the bot
its broken?
-hf second link
Suggestions for @stray condor
- UVR5 UI, by Eddy and Ilaria Huggingface Spaces
- Ilaria RVC Zero, by thestingerx Huggingface Spaces
- RVC⚡ZERO, by r3gm Huggingface Spaces
- Applio, by IA Hispano Huggingface Spaces
I need help..
thanks
I like's to get my dick sucked while I'm getting high
Make her deep throat, her mouth never get dry
I say, "Who pussy is this?" She say, "Dolla $ign"
"Who pussy is this?", She say, "Dolla $ign"
She strippin', still got a nine-to-five
Say that she's mine, but that's a lie
These hoes will tell you anything
She want the money and the fame
South Central nas really don't be loving these hoes
These hoes don't be loving these nas
Really, we all just want the money
Money, money, baby, baby, Pusha Ink, baby
Said she got blunts, I said, "I only smoke papers"
Come pick it with the Taylors, bunch of gang bangers
Pimps and players, young money makers
Ayo? @still copper level 1 !!! 
what
Ayo? @cinder mesa level 3 !!! 
wasn't there a local .exe
is so old
ohh yea i get it now
whats the difference between the .exe and this one tho?
isnt that the official uvr?
have more models
oh i thought what eddy's uvr uses gets their model after Anjok07's uvr
Guess they have the newer models then?
.
can someone please get me a working download link for the voice changer?
?avatar @stone eagle
Ayo? @prime egret level 2 !!! 
?avatar @timid musk
What’s the best AI app for text to speech?
There are different Text To Speech (TTS) AIs:
GPT So Vits: RVC isn't as good as GPT So Vits for tts, but gpt so vits (few shot tts, which means needs just a lil training for models) can't use rvc models (and viceversa), and its only limited to: english, chinese & japanese, if you wanna check gpt so vits instead, read https://docs.aihub.wtf/tts/gpt-sovits/
Freemium 11labs: A easy way to do TTS is https://elevenlabs.io/, you can't use RVC model on this but its a mostly premium easy way for good quality TTS
FishSpeech: FishSpeech is a 0 shot (no explicit training needed) TTS, if you got a good pc you can use it locally else use their site
With RVC Models:
RVC is natively for Speech To Speech, but forks such as ilaria rvc mainline & applio have built in tts (using Microsoft Edge TTS to make a generated tts audio, which i suggest you to choose a tts model that is the same gender and language of the rvc model you wanna use, and then convert it with rvc)
If you wanna do tts locally with RVC Voice Models (if you got a good pc):
If you don't got a good pc you can do tts with RVC Voice Models on cloud:
-
Ilaria RVC Zero (Running on A100 GPU, free fasted rvc on cloud) and the guide
-
Use Applio UI Colab (with google colab T4 free daily limit gpu)
-
if you don't wanna use edge tts, you could try another tts ai from our tts index and use the output as an input in rvc
Thank you!!
Always Fishspeech is missing
I seperate the backup vocals from main and put it seperately in vc and it still doesnt use the new ai voice?
i dont get why it wont work
Can you NOT mention me pls ??? I don't want you to talk to me ugh
anyone any idea?
What do you mean by vc
Hey guys, I'm new here!
I've decided to be a reference in AI field, but I have never had direct contact with it before...
Currently I'm working on a NLP model to cross 2 diferent types of data looking for similarities and them send it to a LLM to talk about it.
I would like to know more about everything in regards of AI. I would appreciate if anyone can lead me to some good stuffs
Thanks a lot
Yeah, I am the best.
oh didn't see it
yeah why aren't these commands yet are the people that are in charge lazy.
Ayo? @warm loom level 3 !!! 
No you are not show one ai thing you have used that is more complicated then voice cloning that you are skilled at.
No you haven't
Why are you talking about yourself to me.
I'm not transgender but you're a piece of shit for discrimination.
RVC Voice Clone and Lipsync combined with tongyi emo portrait using one image
Alright
Thanks
this shit sucked
It was not even a fun troll
guys
is there a way to somehow get the audio you trained on back? (weights.gg)
I have a few models I've been working on the data sets for, and I want to make sure there's a lot of difference before training again
do you mean backing vocals or what
wat
that's called datasrt, i dont think u can get it back
How did you do it?
its a screenshot of a part of one of my messages wdym
wjat
Hi
@azure hill do you know how to do a gard in Haskell ?
what is "wdym", i forgot...
wdym = What do you mean
bro i aint chicky like u, im just a brazillian
right
Are you a Antichicking coins?
Anti-chicky-coins
mouth
Can someone train a voice model for me? I have a dataset of it
Yes do #1159289738314919936 but also check your DM :)
hi
Can someone train a dataset of super Mari (Super Mari The Animated Series)?
I also requested a model of Super Mari (Super Mari The Animated Series)
Nah water transfer is a thing with them.
Hey guys, it's been a loooooooong time,how are you all doin?
thanks I'll check it out
hm seems quite accurate
but looks like there aren't any additional settings
also I think the generated video is limited to only a few seconds
Yeah because all the good ones like Vidu are paid for good quality.
ohh
Algum brasileiro fudido igual a mim quer jogar um servidor de Minecraft Bedrock?
Hello, sorry to bother you. I actually don't speak English at all and need help creating a template to use later. Basically, I'm going to create my own template from an audio clip that I already have.
What kind of ai stuff
The architecture of ‘Continual In-Context Learning with Adaptive Transformers” offered continues the sequence of Mechanical Concerns in Applying CL in a different domain. It extends the applicability of models based on transformer architecture and, in particular, in-context learning for consecutive learning scenarios. Specifically, such an approach takes a transformer that has been pre-trained and utilizes it as a base structure provided with specific additional layers that support effective learning routines such as gradient flow and closed-form regression. Upon encountering new activities or tasks, the system will first attempt to use an in-context approach with no updates made to parameters. However, if the performance does not meet the target criteria, the current controller can add additional settings, update the memory with important examples, or retune parts of the backbone model. In this way, the system is able to quickly adapt to various tasks that combine some basic elements of in-context learning and available modular updates. This makes it possible to achieve a large coverage of various tasks performed using this system and with a small risk of catastrophic failure. In relation to these components, the architecture is expected to be a self-preserving and relatively facets-aware one in addressing the concerns of the respective approaches to CLoTL in various contexts.
An excerpt from an unreleased paper
@timid musk the video contains swastika
And twin tower
-colab
- Applio, by IA Hispano Google Colab
- RVC Disconnected, by Kit Lemonfoot Google Colab
- RVC Mainline, by Hina Google Colab
- AICoverGen-WebUI, by Hina Google Colab
- AICoverGen-NoWebUI [English], by Ardha, fixed by Eddy, Hina and Gdr Google Colab
- AICoverGen-NoWebUI [Spanish], by Eddy, Hina and Gdr Google Colab
- UVR5 NO UI, by Eddy Google Colab
- UVR5 UI, by Eddy Google Colab
- Modified W-Okada's Voice Changer, Google Colab
While the Colab free plan provides up to 12 hours of daily usage, the GPU is typically available for only about 4 hours each day on average.
-local
- 🍏 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.
hi, i have exp developing LLM Projects in the past 2 years, i want to learn more and share exp each other here.
11/09
-colab
- Applio, by IA Hispano Google Colab
- RVC Disconnected, by Kit Lemonfoot Google Colab
- RVC Mainline, by Hina Google Colab
- AICoverGen-WebUI, by Hina Google Colab
- AICoverGen-NoWebUI [English], by Ardha, fixed by Eddy, Hina and Gdr Google Colab
- AICoverGen-NoWebUI [Spanish], by Eddy, Hina and Gdr Google Colab
- UVR5 NO UI, by Eddy Google Colab
- UVR5 UI, by Eddy Google Colab
- Modified W-Okada's Voice Changer, Google Colab
While the Colab free plan provides up to 12 hours of daily usage, the GPU is typically available for only about 4 hours each day on average.
Ayo? @elder willow level 1 !!! 
tf
One message removed from a suspended account.
hello
One message removed from a suspended account.
what
One message removed from a suspended account.
wdym
One message removed from a suspended account.
Ayo? @elder willow level 1 !!! 
you mean VSC?
that's for my minecraft server
One message removed from a suspended account.
One message removed from a suspended account.
One message removed from a suspended account.
.wk ghost mountain
👑 TFA - 210 plays
2. wilq - 206 plays
3. Kainé - 172 plays
4. Sick - 152 plays
5. peri - 94 plays
6. pugglezz - 80 plays
7. Monk - 64 plays
8. angelito - 41 plays
9. eyeblind - 40 plays
10. Stoic - 35 plays
11. DJ Clamor - 34 plays
12. 🪽 - 33 plays
13. lalw - 33 plays
14. sweatbuh - 29 plays
** 42. gublik - 0 plays**
Crown claimed by TFA!
Ayo? @pine mural level 5 !!! 
.wk xaviersobased
👑 adiiose - 5203 plays
2. remy - 3999 plays
** 3.** gublik - 3819 plays
4. exan - 3167 plays
5. luminal - 2823 plays
6. yeresin - 2555 plays
7. poison - 1731 plays
8. sqwab - 1645 plays
9. wg - 1302 plays
10. osc - 1178 plays
11. buga - 1003 plays
12. Teckmek - 927 plays
13. Markus - 906 plays
14. gtemq - 836 plays
guys, why isn't Mangio RVC updated, and comparing appolio and mangio, which is better
The AI scientist by sakana it's on github
We can run it locally, but my PC is not good enough
And there are no cloud services for it
are you perhaps running it on linux
omg
💀
i cant import model it keep saying "Model Load Error! Check your model is valid. local variable 'inferencer' referenced before assignment" do im missing smth or its broken
:RIP:
Ayo? @fiery geode level 1 !!! 
whats the best ai voice changer for trolling as an e girl?
try this fork for better performance esp in low end hardwares: https://rentry.co/forkvoicechangerguide
Guide style is in the same as Blanc_dot's. Thanks Blanc_dot for corrections. Most technical information comes from deiteris.
Last update August 30th, 2024: New b2309 version
Translations added for:
German: https://rentry.co/ForkVoiceChangerGuide_de
Turkish: https://rentry.co/ForkVoiceChangerGuide...
ai hub
hi
anyone wanna join some valo eune bronze/silver elo unfo,pls dm me we r looking for 5stack 
eww valo
sorry xd
hi, Ahmed
can anyone help me find clix voicemodel 😭
You can search rvc ai voice model at:
- #1175430844685484042
- #🔍│find-models
- https://weights.gg/ (login required)
- https://huggingface.co/models (but watch out cus in hugging face there arent only rvc ai voice models)
- https://applio.org/models
- https://voice-models.com/
- https://thevoicemodels.com/ (for Turkish Models, login required with discord and level 2 on their server)
if there isnt one, you can:
- #1159289738314919936
- #1191429836321849435
- make it yourself with our docs guides https://docs.aihub.wtf/essentials/how-to-make-voice-models/
Are voice models here safe? If you say they are safe then are they checked?
I've used some of them before and was reinstalling w okada so just wanted to be sure.
avast or the similar ones that give such false positives are the less trustworthy one that you should stop using it
I didn't get any positives myself because I didn't check with anything outside windows defender before but would a virustotal or malwarebytes search help if I wanted to check for a non popular source?
https://imgur.com/FoModwh this is from huggingface and it would tell if there was a suspicous import so it is relatively safe right?
Also I can't see an AI Help channel is it deleted?
Ayo? @ashen moss level 1 !!! 
Hi does someone here have encountered connection closed on runpod's terminal?
Ayo? @verbal wolf level 1 !!! 
we have the oldest list of voice models we predate all of them
yes it’s safe
thats wild
Ayo? @sour flicker level 1 !!! 
uh the okada voice changer ver i downloaded on the github doesnt work however the one i downloaded on hugging face work but it launched on the website instead an aplication like the github ver
anyway to fix the one on github ?
im tryna be like my king duckus he leading us to this server mane :(
hello
Hi
hi
try
Make sense
What's up?
Good 😅
Ayo? @half flame level 1 !!! 

this AI
depends on which u are talking about, i guess RVC, thats just for converting vocals though, which can be used in AI Covers
be sure u are following our guides
-rt
This interaction has expired, use the command
/guides realtimeif you wish to see it again.
1st is the fork optimized, 2nd is original wokada
ask in an help channel and wait for a helper
then wait for a helper, i seen its about wokada, which i dont really use,
only thing related to that error that i found is #✨│ai-help message
But its better u wait for someone who knows more about wokada
Yes, lots of choices
Hi, I'm trying to create an AI cover song for my wedding. I've tried a couple tools I found online, but they come out unusable. I'm curious what it would cost to pay someone else to make a good quality one as I can easily find on YouTube.
whats ur pc gpu? i can help you to get the right tools to do an ai cover, using things like 'kits.ai' are scams lol
Well, I can probably get my fiancee on board with buying one for this purpose. (and the fact that I will be able to game on my PC again will just be a bonus)
well here we help people into making them, if u want i can help you even with the easiest way, idk if theres a channel to request ai covers like there is for models #1159289738314919936
I can pick up a hobby for a few months to get what I want out of it, I think. How much would a video card good enough to do this cost me?
Ayo? @river frost level 1 !!! 
If u don't have a good gpu u can do it on cloud dw
you can use the cloud solution if you don't have powerful pc
There's Ilaria RVC Zero which is a ZeroGPU HuggingFace Space (uses A100 for free) that can do ai covers fast)
Ilaria RVC: CLICK HERE 🤗
Guide on how to use it: CLICK HERE 📝
Don't forget to thank Ilaria if you find it useful! 💖
Alright thanks, I go through this later when I have more time.
3060 is enough to do what u want, can also game and use this as an excuse lol
pretty cheap card
Thanks!
hi
is trained ai ahh models handing over to chinese deepstate?
What
Ayo? @calm vapor level 2 !!! 
Does anyone in here work with AI music?
only emvoice and stuff are singing tts but they are paid
dunno about singing, but the only open source thing suno did is bark tts, but its old and not really good quality except being emotional, but i dont think its good for singing tho
Table Of Contents Introduction Index of the best TTS 1. ElevenLabs/11Labs: 2. Bark TTS: 3. Edge TTS: 4. StyleTTS2: 6. XTTS2: 8. MetaVoice: 9. MeloTTS: 10. GPT-SoVITS: 11. gTTS: Use TTS in Realtime on calls (ONLY PC) Introduction TTS Means Text To Speech! Inference means when you use the TTS. ...
Oh didn't know about emvoice, thanks! I'm actually open to paid ones if they are good and controllable
Yeah Emvoice can do full range and stuff on new voices and all there voices sound really good once you add rvc to them.
Can’t believe that maybe the 5090 rtx could draw 600ws
Yeah but you can easily make a 3080ti draw 1000w and for 5090 for not as intense stuff you just undervolt and power limit it so it only pulls the power when you need the full performance.
Hello. I have a general question here.
I'm trying to write a song using AI with my lyrics, but I want it to be sung in the style of a certain known artist. Is this possible?
Hello, do you have video face swapping ai tool and free one
one image or not
hi
https://discord.com/channels/1159260121998827560/1163571683848900629 this mentions face swapper
k
Yeah but facefusion is not that good one image
ye its for deepfakes
Bad quality one image ones
i haven't compared it to deepface lab as its banned everywhere on cloud, but it isn't low quality
qq all
How do I get the contributor role?
No it's not banned forks are still up and also there is one colla b that works but it's not the good fork version.
what do you mean qq all
I need some help in connecting a model with java application. can anyone tell me how to do it
Ayo? @golden shard level 2 !!! 
For what reason
Uhh usually contributor role is given to inactive staff members
I dunno honestly if there is some way u can earn it as it's not in the /jointeam
@river adder pheraps you know?
suppose i want to get a number recognition model
i want to take input through the java program and pass it to the model
and then display it outputs
Could u share that colab? also i meant that yea deepface lab original repository and some of its fork are banned on github + google colab + kaggle, unless that colab u know has encryption
Only the ones attached to deepfacelab repo got taken down
Hey
Yeah I know one it just needs to be adapted to my fork so it can work https://colab.research.google.com/github/Cioscos/DeepFaceLab-Colab/blob/master/DFL_Colab.ipynb#scrollTo=Z0Kya-PJLDhv
☑️
the word DeepFaceLab/ is banned on colab lol
wtf why specifically written with the / 😭
Hi
yea its banned too
it needs encryption
Yeah but I know someone that used it before for 12 hours and had no problems
look
new theme tab
by me
wtf that's literally not possible, when u start a cell and get that type of warning at the start, in not even 5 mins they will disconnect u
its already detected even before running
👨🏻🍳
Ayo? @shell badge level 2 !!! 
No I saw someone recently using it with colab pro for 12 hours and they have anti disconnect module. and also the whole deepfacelab part needs to be adapted to my fork for it to work.
Ay thats cool for personalization
Are you really sure they were using no encryption?
I saw banned colabs alot, after not even 5 mins of getting a popup like that, u are alrady disconnected
Thats the same for RVC not encrypted, facefusion not encrypted, etc
Hi
hi
They were just using that colab and had no problems but now that github original is gone you need to adapt to my fork to make it the best it can be.
guys help i cant vfind the voice changer
i go into the github but cnt find the place he wemt in the vid
hi
someone help where can you train ai voice models for free
i have the acapellas but nowhere to train the voice
What video and videos guides are can never stay up to date
Its goöd i think i found it
Ayo? @uncut spruce level 1 !!! 
hello
new OpenAI model is announced
13% on the math olympiad with GPT-4o to 83% with the new model is crazy tbh
API only gets it if it's Tier 5
what does that mean
1000 dollars spent total for access or buy chatGPT plus for 30 messages a week
so it's 1000 dollars for permanent purchase?
No for API
Guess I ain't sleeping today
what
Ayo? @fair plume level 2 !!! 

wait, so you can actually get the API? wouldn't that be dangerous, no matter how much money someone has?
"ChatGPT Plus and Team users will be able to access o1 models in ChatGPT starting today." ok.
i will not fucking repeat this so listen carefully. Key differences between Java and JavaScript: Java is an OOP programming language while Java Script is an OOP scripting language. Java creates applications that run in a virtual machine or browser while JavaScript code is run on a browser only. Java code needs to be compiled while JavaScript code are all in text. SO STOP CALLING JAVASCRIPT "JAVA" AHSDIAHIDHAOIHFOI
Credits: FungusDesu
dsadsa
Thanks automaze
My name is Jennifer am from north Carolina but I live in Houston Tx am 37 years old
Am a single mom.
Damn you get mad so quickly lol
Hello. That's nice. Your bio says your looking for a marriage. Are you not married? 🤔
Ayo? @pure ruin level 1 !!! 
pretty weird it even worked as it has that popup tho, i forgot ur github ngl
Wtf is the emoji lol
Кто обмен аккаунтами в стиме
Ayo? @grizzled shadow level 1 !!! 
gracias
@strange cipher, I have found 12 results that match your search!
help ^^
No promo plz unless it's on #1159290752195633273 channel
its not a pro i seach a programm to do ai cover songs with my voice
You can read the docs and download RVC locally.
-rvc
- How to use RVC Mainline Colab by Cauthess
- Full AI Voice Model Training Guide (local) by Christopher Villanueva
- AICoverGen Colab Guide by Eddy (Spanish Helper)
- Create a model with RVC disconnected (colab) by Angetyde
its one of those voicify kits ai shit
Agreed
its just rvc but paid, its stupid fr
guys how can i make a IA sing lyrics made by me? like no talking, only singing
Yep it is
Record yourself singing.
And then use the audio you recorded with the model you wanna use on RVC.
ohh right! tysm
You're welcome buddy.
In case of anything just go to the #✨│ai-help channel
yeah if u help the server with something like making guides and stuff like that etx
From what i know, @elder willow made some Kaggle ports like UVR5 & AI Cover maker


AI HUB Docs