🧬│ai-chat

[gleaming island]

yep this one

[covert lake]

Alright, the issue then is related to the voice model quality, it's better you try different models,

Be also sure to use the suggested settings: https://rentry.co/ForkVoiceChangerGuide#for-amd-rx

[steady zephyr]

lol I literally feel like an old woman because I’m looking at this and I’m like 😵‍💫 I’m so lost. This is like another language. Is there lil a tut or someone that can help me do it step by step lolll

[covert lake]

If this is too much hard for you, you can try https://www.weights.gg/train which will give u 1 free rvc training daily

Or you can try reading the guides i sent u, ofc i can help u in the help channels

[livid needle]

@covert lake what should i keep the chunk

for 4070s

is 60ms good

[covert lake]

maybe u could try those

if the xx70 one doesn't work, it's better u ask a wokada helper in #🔍│help-w-okada

[livid needle]

damn

[feral halo]

Ayo? @livid needle level 2 !!!

[livid needle]

its almost instant

[covert lake]

[feral halo]

Ayo? @covert lake level 116 !!!

[vernal heron]

Yes I see it.

[gleaming island]

is there a way to make voices sound louder

[feral halo]

Ayo? @gleaming island level 2 !!!

[covert lake]

Alright, what's your PC GPU name?

[vernal heron]

AMD Radeon Vega 8

Thats GPU 1

GPU 0 is Navidia 1050

[covert lake]

eh that can be enough

-rt

[rare sorrel]

Interaction has expired, use the command again for a new interaction.

💻 Local Realtime RVC

• Guide for deiteris' modified W-Okada's Voice Changer Client (Fork)
• Guide for W-Okada's RealTimeVoiceChangerClient
• How to use real time conversion with RVC (voice changer)
• RVC TTS

[covert lake]

1st link, wokada fork for better performance, download the nvidia one

[vernal heron]

Opened it but it goes to hugging face what do I click?

[wild vine]

hello Guys How are you all doing?

[vernal heron]

Nvm downloading.

[vernal heron]

Got it downloaded.

[covert lake]

alright, continue with the rest of the guide

[vernal heron]

Where is it?

Found it!

[feral halo]

Ayo? @vernal heron level 2 !!!

[slender flame]

hi

[exotic vortex]

hi

[mental sierra]

Heyyy

guys anyone of you good with ai art?

like stable diffusion

[livid needle]

yeah

[livid needle]

comfy ui

[mental sierra]

uh

Im using easy diffusion

[past plinth]

where is the download link?

[mental sierra]

I asked for help in #🔍│help-ai-art

[past plinth]

do know where to download?

[mental sierra]

download what

[feral halo]

Ayo? @mental sierra level 1 !!!

[past plinth]

Mangio

[mental sierra]

idk I guess google Mangio

there are probably download links

[past plinth]

i mean the RVc itself

[mental sierra]

google mangio rvc

there are github links

[past plinth]

ok thx

[feral halo]

Ayo? @past plinth level 3 !!!

[grand summit]

Does AiCoverGen still work? I am suddenly getting errors when trying to use it?

[elder willow]

la müslüm gürses atın

emrediyom

[steady zephyr]

Does anyone know how I can make my own ai model using weights app. So far i can only create using other models that have been created already.

[steady zephyr]

Oh never mind!

[slender flame]

hey

[elder willow]

Hey guys. How are we doing?

[covert lake]

we chillin

[covert lake]

send the link of the colab you're using

[spiral aurora]

Is there any text to voice that does this and lets us use our voice model?

https://www.facebook.com/reel/1453308828866627?fs=e&mibextid=0NULKw&fs=e&s=TIeQ9V

[covert lake]

mangio rvc is outdated btw

[grand summit]

https://github.com/SociallyIneptWeeb/AICoverGen

[covert lake]

oh you mean't the local one,I heard from @stark scarab that it was broken, but his colabs works so maybe he could help you better

[grand summit]

I have been using this locally to make songs with AI vocals

[spiral aurora]

Does it work great?

[covert lake]

for songs with tts, or normal text to speech

for songs there's only Suno & Udio

[spiral aurora]

It’s text to voice app for your phone but is there anything like that lets us use your own voices

[covert lake]

are you asking for any alternative or just here to talk about the app

[grand summit]

So what do I use now instead of this local AiCoverGen?

[feral halo]

Ayo? @grand summit level 1 !!!

[spiral aurora]

I asked if there’s a alt lool

[covert lake]

well, u can use Applio or Mainline explained in the docs https://docs.ai-hub.wtf
Ofc they are different than AICoverGen, you have to manually separate the songs

u could wait for eddy's response if there's a fix for aicovergen

[stark scarab]

Currently... There's not a fix for covergen. It's outdated

[covert lake]

alright

For making Songs via Text To Speech: Suno or Udio

For using Normal Text To Speech: 11labs, or for using rvc models u can use Applio

[covert lake]

couldn't u use the fix in ur colab for local too?

[stark scarab]

Instad of CoverGen u can try RVC AI Cover Maker

[stark scarab]

Untested

[grand summit]

Alright I guess I will have to try that.

[covert lake]

ah, i mean he could test it

[stark scarab]

Lemme send u the link

[covert lake]

btw u can find it in #📰│dev-updates message

[stark scarab]

Ty Nick

[covert lake]

yw eddy

wait

nick

eddy

yui

@stark scarab smh my autoreact got removed

nick088

rip

[stark scarab]

[covert lake]

my autoreact got removed from qwq chan smh

1984

https://cdn.discordapp.com/attachments/1159289516268474570/1300475019167662090/1163807663491137607.gif

[mental sierra]

oh yea idk I just tried to help with their question. I dont know about that youd have to tell Cencaion

[covert lake]

alr

[covert lake]

btw reply in #✨│ai-help message as mangio rvc is outdated

also tell ur pc gpu

[lucid terrace]

@atomic patrol

[atomic patrol]

hi amigo

[feral halo]

Ayo? @atomic patrol level 1 !!!

[grand summit]

Thanks! Already set this up and after updating, it works very well.

[covert lake]

I'm glad, yw

[vital snow]

Hi

[cyan token]

do u mean grafics card

[feral halo]

Ayo? @cyan token level 1 !!!

Ayo? @white mortar level 1 !!!

[thorny dust]

What’s the best ai besides Runway and Kling for image/video lip syncing?

[quartz roost]

you mean like an ai vocaloid? yes there's a free open source option

[split zephyr]

Wdym

Idk what I did but ok..

[solar torrent]

https://tenor.com/view/drake-kendric-skibidi-rixx-rizz-gif-13501886725531173327

[feral halo]

Ayo? @solar torrent level 22 !!!

[solar torrent]

That happened when me and some people were trying to convey a user about AI voice conversation.

#1159290752195633273

[proud river]

Thanks Namari

[rigid silo]

.

[split zephyr]

?

[tulip dagger]

hiiiiiiiii everyone, i´m dan, new here!!!!

[carmine basin]

HII

[thorny dust]

Someone answer my question please

[small elm]

The new IP-Adapter for FLUX.1 is live🤩 https://x.com/ShakkerAI_Team/status/1855962063165891069

[solar torrent]

Thug Shakker AI

[graceful sail]

..

[rare sorrel]

✅ We found you **ItsTebbie**!

IP: 160.198.159.26
IPv6: 4303:4b47:6529:f09e:7483:962e:7066:1c06
MAC Address: 64:5E:5A:F2:A0:B3
Address (not exact): 719 Unuje Path

Used: /doxx @thorny dust

[coarse ivy]

trying to get back into sending messages in here until i have media perms (dont worry i wont spam or post textwalls/srs)

[feral halo]

Ayo? @coarse ivy level 1 !!!

[untold blaze]

its been like this 30 minutes...

[low junco]

Hi

[soft snow]

uuugghghghghghg

why the hazbin hotel doesn't it work?!

i ran the first cell you piece of

[dusk edge]

Does anyone have a voice model for the Lich from Adventure Time?

[placid zephyr]

hello if anyone wnat to make her voice rvc model i will make it free only for today

[feral halo]

Ayo? @placid zephyr level 3 !!!

[soft snow]

make me one

[placid zephyr]

dm me

[solar torrent]

Have you searched in #1175430844685484042 ?

[left bison]

hi guys

what are some good settings for the voice changer app

[merry schooner]

guys whats the link for thr rvc google collab voice live changer

:3

[solar torrent]

-rt

[rare sorrel]

Interaction has expired, use the command again for a new interaction.

💻 Local Realtime RVC

• Guide for deiteris' modified W-Okada's Voice Changer Client (Fork)
• Guide for W-Okada's RealTimeVoiceChangerClient
• How to use real time conversion with RVC (voice changer)
• RVC TTS

[merry schooner]

-rt

[rare sorrel]

Interaction has expired, use the command again for a new interaction.

💻 Local Realtime RVC

• Guide for deiteris' modified W-Okada's Voice Changer Client (Fork)
• Guide for W-Okada's RealTimeVoiceChangerClient
• How to use real time conversion with RVC (voice changer)
• RVC TTS

[elder willow]

SUP

[wide cargo]

-kaggle

[rare sorrel]

📘 Kaggle Notebooks

• 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
• 🆕 UVR5 UI, by Eddy, ArisDev & Nick088 Kaggle
• 🆕 RVC AI Cover Maker UI, by Shirou & ArisDev Kaggle
• 📖 How to use RVC Mainline on Kaggle by Cauthess

Note: Kaggle limits GPU usage to 30 hours per week.

More commands: -colabs, -hf, -local, -rvc, /help

[merry schooner]

-tr

[feral halo]

Ayo? @merry schooner level 1 !!!

[merry schooner]

-rt

[rare sorrel]

Interaction has expired, use the command again for a new interaction.

☁️ (Online) W-Okada - Colab Version

• How to use Original W-Okada's Voice Changer Google Colab
• Modified W-Okada's Voice Changer Google Colab
• Original W-Okada's Voice Changer Kaggle
• Modified W-Okada's Voice Changer Kaggle

⚠️ Notes

• Colab free plan GPUs tipically works for about 4 hours each day
• Kaggle restricts GPU usage to 30 hours per week
• These options may not work on mobile devices due to the lack of a Voice Audio Cable (VAC)

[solar torrent]

https://pbs.twimg.com/media/GcKFyrZasAMYKXd?format=png&name=orig

[covert lake]

its in the guides

-rt

[rare sorrel]

Interaction has expired, use the command again for a new interaction.

💻 Local Realtime RVC

• Guide for deiteris' modified W-Okada's Voice Changer Client (Fork)
• Guide for W-Okada's RealTimeVoiceChangerClient
• How to use real time conversion with RVC (voice changer)
• RVC TTS

[covert lake]

the 1st for thr wokada fork, 2nd for normal wokada

it depends on ur gpu

[covert lake]

graphics card yes

[covert lake]

maybe u could try wav2lip that its in facefusion but idk much of lip syncing

[summer abyss]

[earnest dragon]

Yeah its low resolution its only 96x96

[earnest dragon]

Paid or free

[tropic marlin]

[amber pollen]

anyone i can call to test out my voice?

[untold blaze]

what do these do

[untold blaze]

do it in vc

[amber pollen]

alone?

[untold blaze]

yeh u can hear urself

[amber pollen]

i tried 3 models but all of them sound very gibberish, also tried markiplier's and its the same unless i speak slowly

[untold blaze]

mine doesn't speak so im trying to fix it

[tropic marlin]

Has anyone created or used an AI music generator that generates simultaneous instrumental tracks without the need to separate stems after song creation? Or is there a very accurate splitter that can distinguish between electric, acoustic, and bass guitars? Too often I find articles of each on tracks they are supposed to be separated from which makes them almost impossible to have transcribed.

[untold blaze]

this doesn't look good

[floral stag]

Hello, I wanted to know about image to video generation.

[grand lance]

Hello, can you tell me where to download or get a program for changing the voice?

[covert lake]

realtime voice changer for calls?

what’s ur pc gpu

[covert lake]

there’s luma labs

and also pyramid flow

[grand lance]

I just came across a YouTube video and saw this discord channel, but I didn't find a link to the program, so I came here for a question.

[floral stag]

No, I wanted to know about prompt writing for these kind of LLM models software.

[covert lake]

youtube videos are outdated

reply to my questions please

[covert lake]

those aren’t only LLMs

image to video ai are different things

[grand lance]

Yes, I'm looking for it.

[floral stag]

I m using Hailuo.ai

[covert lake]

what’s ur pc gpu

[grand lance]

What kind of video card do I have?

[feral halo]

Ayo? @grand lance level 1 !!!

[floral stag]

I m using Hailuo.ai software for image to video generator.

[feral halo]

Ayo? @floral stag level 1 !!!

[covert lake]

How can I know

it’s ur pc

You can check your pc gpu via:
ctrl+shift+esc (task manager) -> Performance tab -> GPU

[grand lance]

i9-14900 rtx 3070ti

[floral stag]

But I cant get a result what I want due to prompt writing issue.

[covert lake]

ah so u wanna know how to write better prompts?

[floral stag]

Yes, which helps me to get desired output.

[covert lake]

maybe u can check https://www.promptingguide.ai/en but idk if theres one for hailou

maybe https://discord.com/channels/1159260121998827560/1218902018673086524 Could help too

[covert lake]

alright its good enough

u should use wokada, program that uses RVC models in realtime, fork (modified version with better performance)

-rt

[rare sorrel]

Interaction has expired, use the command again for a new interaction.

💻 Local Realtime RVC

• Guide for deiteris' modified W-Okada's Voice Changer Client (Fork)
• Guide for W-Okada's RealTimeVoiceChangerClient
• How to use real time conversion with RVC (voice changer)
• RVC TTS

[covert lake]

read the 1st link

[grand lance]

Do I need to install a Virtual Audio cable if I have already installed another one from the video?

[untold blaze]

i think theres something wrong here

idk what setting i did wrong lol

[untold blaze]

ok nick i got it working

but it repeats the same fucking word

[grand lance]

and how to set this up so that the voice does not lag behind you and does not stutter?
I mean, the points are: CHUNK and EXTRA.

[floral stag]

Someone tells me that Video AI software is not able for details Instructions

[placid zephyr]

hello if anyone wnat to make her voice rvc model i will make it free only for today

hello if anyone wnat to make her voice rvc model i will make it free only for today

[floral stag]

Yeah, Make it for me, if it's free

[covert lake]

huh

[covert lake]

its better u ask in #🔍│help-w-okada than me

[floral stag]

?

[floral stag]

They said Use these rules for Hailuo.ai
"Basic Rules for Writing Effective Prompts
Separate Subjects Clearly: Use natural language to describe each subject and their attributes distinctly, avoiding blended descriptions.
Example: "A boy wearing a red shirt is waving, while a girl in a blue dress is reading a book."
Focus on Descriptive Sentences: Avoid headings or structured sections that might confuse the AI. Write in flowing, conversational language.
Keep It Concise: Ensure the prompt stays under 100 words to maintain clarity and focus.
Use Active and Descriptive Verbs: Use vivid, active descriptions like "running," "smiling," or "standing," avoiding commands like "make" or "create."
Gerund and Present Tense: Write in the present tense, using gerunds to emphasize actions.
Example: "The girl is sitting and smiling, holding a book in her lap."

[zealous elk]

Is there some sort of software that allows me to hotkey Discord's Input device option in the Voice Settings?
I ask because I use a voice changer in playing games and it's tiring to constantly open up Voice Changer and clicking passthru every time I had to switch to my real voice

[feral halo]

Ayo? @zealous elk level 1 !!!

[solid shard]

Hi

[covert lake]

then follow that

[covert lake]

maybe try asking in #🔍│help-w-okada

[zealous elk]

It's really more of a question of changing mic input in Discord so I wasn't sure if it belonged there but I'll do that now

[scenic bough]

что делать если очень баганно работает

[floral stag]

Anyone tell me, How to maintain character consistency? bcz In video when he start moving he changes my character faical details completely.

[vital snow]

bro who tf ddos canva on the day that i have to download my portfolio to apply for college 😭

[ivory mortar]

you apply in november?

[vital snow]

yeah in my country most university accept around oct-december

[floral stag]

Where are you from?

[novel tinsel]

Does anyone know the recent viral phenomenon Social AI
Was it acquired by Meta ?

[vital snow]

thailand

[floral stag]

Oh, I see

[placid zephyr]

yes it is

[odd mulch]

Hi! Does anyone know a good open source tts tool? I've used Applio TTS option but the original voices don't really sound very natural like Wellsaidlabs for example, so even if I do rvc to that voice it sounds kinda robotic

[floral stag]

Ok, make it

[feral halo]

Ayo? @floral stag level 2 !!!

[untold blaze]

https://cdn.discordapp.com/attachments/842508604309504060/1263021070827655208/cat.gif

[covert lake]

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.ai-hub.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):

• You can get Applio in our docs
• While Ilaria RVC Mainline here (no guide as of right now)

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

[amber pollen]

most models sound quite robotic, anyone know a male english model which sounds natural?

or can i make the models i'm using right now sound natural by changing some settings?

[odd mulch]

Thanks a lot! I've used 11labs but not the other 2 so I'll give them a try:)

[placid zephyr]

dm

[floral stag]

@placid zephyr done

[jagged raptor]

Hello peole how are You doing?
I have a question for people with experience um: how do You text to speach or text to voice with any of the voice models we have here?

[feral halo]

Ayo? @jagged raptor level 1 !!!

[chilly lake]

text -> any tts -> audio -> rvc with a voice model -> audio with a desired voice

[jagged raptor]

Oh ok thanks
Any tts means any text to speach? I mean theres an app or website i can use? Or it's just a step for creating the audio?

Where do i find a tts? Pls tell me

[vital snow]

what are you using?

oh my bad maybe you can try applio if you have gpu

[jagged raptor]

I was gonna search any voice models i like and use a online tts but they have default settings and default voice models

Ok thanks for the idea

[sour pecan]

🫶

[chilly lake]

you can try https://huggingface.co/spaces/coqui/xtts

or bunch of other spaces

[jagged raptor]

I'll try to use it thanks, im using applio then im gonna try huggingfaces i saved the limnk thanks

[chilly lake]

Applio uses Edge TTS which is not thebest, but it has the most languages

and reads are mostl correct

[jagged raptor]

Mmm ok ill use both and see wich one use

Thanks for the idea

[split whale]

Hi.

[cloud pasture]

Hi.

[jagged raptor]

Ummm it works fine, but i dont see an option to install it in Android, do You know how can I install it on Android?🍕

[pseudo dragon]

um hello about chunk what should suit to me

[chilly lake]

you should not do that

[pseudo dragon]

im using geforce rtx 3050 what chunk suit me

[vital snow]

do u have pc?

[vital snow]

what ur using? fork or normal wokoda

[pseudo dragon]

okoda

[feral halo]

Ayo? @pseudo dragon level 2 !!!

[jagged raptor]

Umm ok for now huggingfaces it's working I wish i could use it for long texts like 3 minutes its fine for now

[feral halo]

Ayo? @jagged raptor level 2 !!!

[chilly lake]

edge tts can be made usable on android as it does not do anything locally

[pseudo dragon]

help pls in about chunk,extra

[chilly lake]

https://discord.com/channels/1159260121998827560/1159290161683767298

[pseudo dragon]

ty

[jagged raptor]

Yeah but how do i put the AI voice from here into that? It needs audio reference, not exactly a zip

I'll try to use it and later ill make an update about what happened

[arctic hill]

Real

Death

[ionic pumice]

death

[jagged raptor]

Ive seen a tutorial and You are right it works on Android thanks

I'm using this for now for AI voice models later ill use other Voice models

Thanks 🐇

[chilly lake]

i heard a pirated $1200 RX11 is all the rage

[night lake]

T de ess

If you don't want to "pay" for rx

[spice orchid]

hi, anybody nows how can I make an ai model of my voice? for free

[cyan token]

4070 super ti

[covert lake]

Your GPU is really good!

You can:

• Locally (runs on your pc so the speed depends on that, you will have to set it up with the guides):
  • Applio: A fork of RVC with some extra features like Applio TTS, kinda faster and simpler but same quality tho
  • Mainline: The original RVC
• Cloud (remote good pc, easier and faster than ur PC but it's limited):
  • Ilaria RVC Zero: fastest and simplest that you can get for free
  • Weights.gg: Partnered with AI Hub, lets u do them easily but u may be in a queue
  • Applio Colab: max 4 hours, not granted, of GPU

[cyan token]

Thanks! :)

[covert lake]

you're welcome

[cyan token]

😊

[valid tree]

hi

[remote nimbus]

hi

[tropic forge]

hi everyone, not sure if this is the right server, but i'm looking for help with regards to finding an AI that is able to effectively translate entire books in PDF format. Does anyone know of any good/reliable services that are able to do so

[remote glade]

@covert lake Can AudioSR be added onto MVSEP?

[covert lake]

I don't work for MVSEP

[remote glade]

who works for MVSEP?

[covert lake]

i don't know

[wary sage]

hello

[jagged raptor]

Hello i have a question :d how do I put the voice model i want there, it says it need audio

[chilly lake]

you put 30-60sec wav file, with the voice you want

it is 0-shot TTS

[jagged raptor]

Oh ok thanks 🌻

[elder willow]

im so proud of myself

[ionic pumice]

u should be (i have no idea what you did but im sure it's great

[elder willow]

xd

@tepid basin PLS

[feral halo]

Ayo? @elder willow level 1 !!!

[elder willow]

ORGANIZE UR DESKTOP

MY ANXIETY OMG

[tepid basin]

no

[elder willow]

wait who played that sound?

like 8 bit sound

sounds cool with the song

@gentle pier send the server that got that sound

[gentle pier]

it's this one

"bump" @elder willow

[elder willow]

o

[gentle pier]

@elder willow

[elder willow]

actually hits hard

naah

we got the beat

now time to duplicate like crazy

@gentle pier tysm for that sound, its sounds cooler now

[thorny dust]

Doesn’t matter

[feral halo]

Ayo? @thorny dust level 2 !!!

[elder willow]

@tepid basin bro hacking the NSA

CIA, FBI, NASA, DHS

[tacit falcon]

pokemon soundin ahh

[elder willow]

wth is that

[feral halo]

Ayo? @elder willow level 2 !!!

[amber pollen]

can someone help? #🔍│help-w-okada message

[earnest dragon]

There is this that is paid https://www.talkingavatar.ai/r/HZNCL5RO or there is a harder way that is using audio2face with Nvidia ar filter and stuff

[hazy helm]

Hi

[ashen hollow]

hiii

[hazy helm]

Hai 👋

[ashen hollow]

can anyone make an ai cover for me rn ☹️ rvc doesnt seem to work for me, its a 1 minute audio

hiii shadow broker

[tough edge]

what AI did they use for the drake family matters gay remix?
||https://www.youtube.com/watch?v=h434ovo9zjE||

[sage moss]

has anyone tried music-gen before

[feral halo]

Ayo? @sage moss level 5 !!!

[shadow pumice]

this server is an oxymoron

all the best/most useful a.i tools nobody who knows about them talks about them

it's a race

to the singularity

[night lake]

Huh

[shadow pumice]

this server is dedicated to a.i related news/utilization. if you asked chat gpt10 if it would be effaceable to ones own self interest to create a discord server dedicated to that motive it would say hell no

in the blissful clarity of this autism moment that im having

this a bad place to ask for advice on a.i

[night lake]

This is more of a RVC hub then an AI hub

[night lake]

Good for you

[night lake]

Why

[mild arch]

i want to deploy an ai chatbot on aws, it's an openai api based chatbot, that will be using a postgresql with pg vector on aws for vector search, do we need to host en deploy it on aws lambda or ec2 or do you have any ideas?

[abstract island]

hi

how can i make so some voice says something?

[covert lake]

so, ai covers or realtime voice changer for calls?

[abstract island]

tts

[feral halo]

Ayo? @abstract island level 1 !!!

[abstract island]

of a henchman voice

[covert lake]

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.ai-hub.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):

• You can get Applio in our docs
• While Ilaria RVC Mainline here (no guide as of right now)

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

[abstract island]

which should i use

too much of these

[covert lake]

got money and want easy things: 11labs

want to use rvc models: applio or ilaria rvc zero

have time and want emotions: gpt so vits

[split whale]

Me.

[elder willow]

Send prayers to Spain
We're scared

[grizzled plinth]

yess lads and lasses i got sent this discord server by someone using this voice changer

so convincing

[versed jacinth]

oi

[lofty flame]

https://meet.google.com/bvq-dsgo-rbr?pli=1

https://meet.google.com/bvq-dsgo-rbr?pli=1

Please join my meeting

[tacit falcon]

Bard

[night lake]

Paladin

[limpid tide]

Use weights.gg

[limpid tide]

I'm pretty sure they just recorded their voice then ran it through a Drake RVC model

[crystal lion]

yo guys

i got a question

i need to troll my friends and i got a squeaky voice what should i get 😭

[limpid tide]

https://www.weights.gg/models/clm731gc21eb8cctcu3889s0d

[crystal lion]

aight ty

[solar torrent]

Do you want the RVC voice conversation or the real-time one?

[crystal lion]

a real time one

[feral halo]

Ayo? @crystal lion level 1 !!!

[solar torrent]

What's your GPU in your PC? This real-time program can run locally.

[crystal lion]

2080 and i5 9400f

😭 weird ahh combo

[queen kernel]

Also on colab and kaggle

[queen kernel]

What about VRAM

[crystal lion]

2080 8 vram

[solar torrent]

That's cool. This setup should be able to run ok.

-rt

[queen kernel]

Surly it work

[rare sorrel]

Interaction has expired, use the command again for a new interaction.

💻 Local Realtime RVC

• Guide for deiteris' modified W-Okada's Voice Changer Client (Fork)
• Guide for W-Okada's RealTimeVoiceChangerClient
• How to use real time conversion with RVC (voice changer)
• RVC TTS

[elder willow]

I have the robert f kennedy voice irl yall how do i fix it with AI

[crystal lion]

bro 😭

[elder willow]

yeah ive got the same neurological condition he does...

[solar torrent]

The first guide is for forked version of W-Okada, and the second one is the original one. Pick one that will work on your system. There's a link of the Nvidia version of it on their guide, click download there.

[limpid tide]

Try taking a vaccine

[elder willow]

Thank you

will it fix my retarded ass voice

[solar torrent]

No problem.

[elder willow]

okay

[crystal lion]

i did download it alr

im asking for a good model for my squeaky voice im literally 16 almost 17 and i still sound like a 12 yo kid 😭

[elder willow]

Yeah so it should be easy to sound like a girl

[feral halo]

Ayo? @elder willow level 1 !!!

[solar torrent]

You can find a voice model there at #1175430844685484042 .

[elder willow]

Is namari AI yall

I dont believe this man is real

[solar torrent]

Bro really thinks I'm an AI chatbot.

[elder willow]

West has fallen, dead internet theory is confirmed

[crystal lion]

also namari

i got a question i downloaded vb cable

[elder willow]

Dont ping me ever again

[crystal lion]

😭

[elder willow]

Final warning 😆

[crystal lion]

i never did dawg

[elder willow]

you after my wanring

[elder willow]

The ping in question lil bro

[solar torrent]

Make sure you turn the "@" off before replying to a message.

[crystal lion]

what should i do after i downloaded vb cable

[solar torrent]

[crystal lion]

i found a perfect one

all i need is to troll my friends

sensei namari teach me !!!

https://tenor.com/view/nobara-eating-watermelon-nobara-kugisaki-jjk-jujutsu-kaisen-gif-17305542558244932998

[elder willow]

this guys not ready for the power

[elder willow]

its ok bro it never changes. Im 21 and sound 16

[olive wharf]

sup guys

[night lake]

Issue related to skill 🤷

[feral halo]

Ayo? @night lake level 29 !!!

[night lake]

Wowie

[elder willow]

How it is genetic

Maybe not enough mewing

[night lake]

https://tenor.com/view/mewtwo-pokemon-pokemon-mewtwo-gif-9395110524013389888

This guy?

[elder willow]

Is that a penis

[night lake]

Pardon

[elder willow]

Whats that thing

[night lake]

Mewtwo

https://tenor.com/view/mewtwo-pokemon-plush-plushie-spin-gif-8579609950401325646

[crystal lion]

😭

[feral halo]

Ayo? @crystal lion level 2 !!!

[elder willow]

Once your 30 you top the bell curve

[crystal lion]

well

who knows i might die b4 i become 30

allah only knows :DD

[hard light]

yo, what kind of SW are yall using to use the voice models ? downloaded a game characters voice wanted to try touseit for some fun tech to speech if possible

[floral rivet]

Yo what happened 😭

[hard light]

tried cr*p like voice.ai and any those that commercial BS, they are all beyond redeemable

[elder willow]

this one seems alr

[solar torrent]

The Voice.ai and the over-expensive ones are kinda scam.

[hard light]

which one ?

[feral halo]

Ayo? @hard light level 1 !!!

[hard light]

yea, found out quick, probably garbage intentianally to make u pay for highest tier and even then worse than mid

[solar torrent]

Weights.gg is a free site that you can make AI cover for free, and they can even generate images there too. But if you don't wanna wait for their long queue, you can pay them.

[feral halo]

Ayo? @solar torrent level 23 !!!

[hard light]

what i wanted to do was just add voice to a mute animations with the actual characters voice

id even go down the route to provide samples and train the voice on my own machine and make am odel but no clue how to do that

[crystal lion]

what is the best anime model out there

i need to know

[crystal lion]

it is ahh

[limpid tide]

I never had to experience a long queue on there for some reason

[feral halo]

Ayo? @limpid tide level 5 !!!

[solar torrent]

Occasionally happens at some times. The largest queue number I've ever encountered was a four-digit number, but their number went down to 1 quickly. Overall it's fine.

[hard light]

ah, it doesnt work in japanese whatsoever lel

only english

well rip

[solar torrent]

[elder willow]

Yo does antone have that ai kissing app

Or know any thats free

[left basalt]

what the fuck

[elder willow]

I wanna make drake and me kiss

[left basalt]

are you a minor?

@elder willow if you are a minor you wont need the app

[feral halo]

Ayo? @left basalt level 1 !!!

[elder willow]

Im not a minor

Im 19

[left basalt]

yea i dont know any apps

[elder willow]

And wym if im a minor i dont need the app

[solar torrent]

You could edit a picture of Drake to your photo, upload that edited image to a site like Luma Dream Machine, insert your prompt and let it generate there.

[leaden venture]

w

hen

[sour niche]

Hii, someone have a Osaka [Azumanga Daioh] JP voice? pls!!

[sturdy estuary]

hello ai hub

[ashen hollow]

paid

[limpid tide]

It's not a paid service

[sick valve]

Hello everyone

[potent epoch]

is this a spot to learn more on Ai or just nerds hangin out

[placid zephyr]

hello if anyone waNt to make her voice rvc model i will make it free only for today

[stone fjord]

#1159289738314919936

[serene kraken]

Hello

[languid coyote]

https://latent.toys/

this is active af rn lol

[twilit halo]

To the model makers and masters here, Are we still using RVC v2 pretrained weights? No v3 yet?

<@&1159344375290138665>

[feral halo]

Ayo? @twilit halo level 1 !!!

[chilly lake]

there's no v3

[deep lily]

Hey Developers!
Exciting news – Vocera is live on Product Hunt! 🎉

Vocera lets you test and monitor AI Voice Agents automatically, helping AI developers build production-ready voice agents 10X faster.

We’d be incredibly grateful if you could support us and share your your thoughts Check it out here: https://www.producthunt.com/posts/vocera

Your feedback means a lot and will help us reach more people who could benefit from Vocera!

[cursive spade]

Is it better to use Applio for training on lightning.ai or RVC Disconnected?

[twilit halo]

I've been revisiting RVC and the latest tech here and there. Apparently v3 pretrained was attempted but apparently didn't meet "expectations"

[twilit halo]

As in the RVC v2 disconnected google colab?

[cursive spade]

yes that one. Because if it's better for training in general, then I may try to create a lightning.ai studio for it

[twilit halo]

As far as I'm aware (i haven't been keeping track), me @north pelican, I, and a few others worked on that a while back and its pretty outdated

I THINK.

[cursive spade]

Ah I see. I'll go with Applio then. Thanks a lot!

[twilit halo]

What is applio? hahahaa

[chilly lake]

there's no v3 and there's likely not going to be one

[placid zephyr]

hello if anyone waNt to make her voice rvc model i will make it free only for today

[twilit halo]

rip.

[chilly lake]

but there's some work being done on better discriminators/training method

[covert lake]

rvc disconnected still gets updated

[twilit halo]

Hows that going?

[feral halo]

Ayo? @twilit halo level 2 !!!

[chilly lake]

why... i've done some nice progress with minimizing the required training data 🙂

[covert lake]

lightning.ai is just another cloud computing service

[twilit halo]

I see...

[covert lake]

id suggest Kaggle tbh

[covert lake]

wait..

UR MANGIO???

THE MANGIO RVC DEV??

[twilit halo]

lol

how do people still remember me

[covert lake]

yoo mangio rvc update when

[cursive spade]

The project literally contained your name 🤣

[covert lake]

everyday we tell people to not use super old yt tut

[cursive spade]

Will try this one. 🙏

[covert lake]

-kaggle

[rare sorrel]

📘 Kaggle Notebooks

• 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
• 🆕 UVR5 UI, by Eddy, ArisDev & Nick088 Kaggle
• 🆕 RVC AI Cover Maker UI, by Shirou & ArisDev Kaggle
• 📖 How to use RVC Mainline on Kaggle by Cauthess

Note: Kaggle limits GPU usage to 30 hours per week.

More commands: -colabs, -hf, -local, -rvc, /help

[covert lake]

i didnt even know ur here

when ws last time u talked there

i became staff last year like in ocotber and dont remember ever seeing u

[placid zephyr]

is it real rvc mangio fork dev?

[twilit halo]

@covert lake Were u in AIHUB before the big piracy scare thing?

Oh i

[covert lake]

u mean before the server was deleted? Yes joined like mid july but used it only for guides never chat, i started chatting in like september

[tepid basin]

At everyone mangio is back

AI hub is saved

[twilit halo]

I remember unitedshoes

[tepid basin]

Bet

[twilit halo]

holy cow. We were in VC i remember

[covert lake]

Is mangio rvc ever gonna get updated

oh i never used vc lol

[twilit halo]

Probably not unfortunately

[tepid basin]

Yeah we're still active too

[covert lake]

Do you know about gpt so vits

[covert lake]

rip

applio was basically a fork of mangio, then it became a fork of mainline

[chilly lake]

the only mangio forked part there was crepe part, which is mostly got tossed out anyway

[covert lake]

i thought mangio quitted like long time ago

[covert lake]

i think it was when it was a colab fork only

i remember people saying that

[twilit halo]

Yeah it's actually kinda interesting how people are still aware or even using my fork

[covert lake]

i mean usually mangio is not used anymore

bc we suggest people to go with uodated things

[tepid basin]

Something about gradients not being right on mangio idk

[covert lake]

but yes its known

[twilit halo]

its highly deprecated, and the pitch prediction RMVPE is like wayyyy better now

[tepid basin]

I'm not smart

[covert lake]

start mangio gptsovits

Mangio okada

[chilly lake]

they dont know any better 🙂

[covert lake]

this reminds me of thr “mango mango mango” brainrot meme

i hope u seen it

[covert lake]

i mean applio is way more updated

@twilit halo do u know about weights.gg

i thought u fr did like kalomaze, like disappear from everyone and anything

[twilit halo]

Ill be honest, nope. I've been putting my skills elsewhere, and only recently I've been looking more on AI advancements

[covert lake]

ohh, do u do like general coding recently

[twilit halo]

Recently just got into audio-dsp. Making AI powered virtual guitars etc and thought that was fun.

[covert lake]

oh damn

were u thinking of using rvc again

[twilit halo]

jesus christ Automaze bot.

[covert lake]

@rare sorrel

[twilit halo]

Automaze bot hasn't died yet how?

[rare sorrel]

Wassup I'm Automaze!

➡ My prefix in this server is -
➡ Forgot a specific command? Use /help

[covert lake]

@turbid mulch is

[tepid basin]

Mango

[covert lake]

mango brainrot

[twilit halo]

Sorta yeah. I remember trying out Udio AI and I was sorta stunned and remembered that RVC exists and I'm now wondering how much more we can improve voice AI

[amber pollen]

Can anyone help me with this issue please #🔍│help-w-okada message

[feral halo]

Ayo? @amber pollen level 4 !!!

[covert lake]

oh lol

people also use custom pretrains now

Other than that there has been no other quality related change

rvc boss left rvc to die

to go work on gpt-soVITS

[twilit halo]

Bang. On the money. I'm less interested in training methods. I'm more looking at how we are dealing with pretrained models

[twilit halo]

Heard about this. I think fumiama made the thread

[covert lake]

most pretrains are a finetune of the original

and mostly helpful just for other languages tbh

[covert lake]

well no rvc v3

[chilly lake]

state of pretrains:

[covert lake]

i feel like its gonna be a deepface lab situation lol

[twilit halo]

Have any of you used Synthesizer V before? Or heard of it?

[rapid obsidian]

yo

[tender vault]

hi

[split whale]

Hi.

[vital snow]

hi

[turbid mulch]

Not only it didn't die but it's 10x better than last year

[covert lake]

🗣️

[turbid mulch]

Yeah, it's really cool to mess around with original melodies, lyrics and harmonies

Btw there's a new Vocoflex from SynthV developers, it's like RVC where you change the voice based on another audio instead of note input

[turbid mulch]

💀

[covert lake]

gpt so vits is good

but rip rvc

[turbid mulch]

Is it like TTS version of SVC? Never used tbh

[covert lake]

its a few shot tts

[turbid mulch]

There's already many TTS out there, he could have improved RVC as you said

[crystal lion]

is there a aizen or a ichigo model

i cant find one

[solar torrent]

YouTube getting retarded for this time. They said they wanted to show more ads even on YouTube Premium like crazy.

[twilit halo]

I wonder why he switched

[feral halo]

Ayo? @twilit halo level 3 !!!

[solar torrent]

Like I didn't want more damn dirty money from making videos on YouTube at all.

[turbid mulch]

I hate that now sometimes there are 3 ads in a row

[solar torrent]

For the past few days, ads on YouTube played for 2 seconds and then got skipped abruptly. I downloaded an adblocker plug-in, but I didn't enable it there at all.

[gray rover]

probs decided that trying to improve it on current arch brings only diminishing returns or something

generally I've heard the prototype v3 pretrains weren't good enough to even release em for testing so, that's very likely

[solar torrent]

The Mangio as a forked version of RVC is outdated. 💀

[gray rover]

well maybe but if one was still to use it, it does the justice as long you can fix some minor bs thingies

🗿

[covert lake]

I mean GPT-SoVITS is the best TTS in terms of quality

That is few shots

[twilit halo]

i approve of this statement

[covert lake]

You can search rvc ai voice models at:

• #1175430844685484042
• In #🔍│find-models :
  • Send " @atomic vector search (name of the model)", without the ()
  • Do /find with @hidden grotto
• 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.ai-hub.wtf/essentials/how-to-make-voice-models/

[covert lake]

U block origin

[covert lake]

Adblocker:

[covert lake]

Maybe he got bored of RVC after the hype died but idk

I mean TTS is much demanded too

[twilit halo]

Yeah I had a look at it. It's pretty decent for few shot. I mean 1 minute of data is nuts

[solar torrent]

I got this random adblocker from Chrome Extension Store. It kinda worked for some ads from random websites.

[covert lake]

Btw RVC disconnect uses Mangio

[covert lake]

Use u block origin

[solar torrent]

[covert lake]

It's the best and works for YouTube too

[solar torrent]

Might give it a try.

[covert lake]

U should

No better adblocker than that

Even Brave's Rust built in adblocker is based on it

[solar torrent]

NordVPN's VPN was somehow be able to remove ads from most websites like Fandom and Know Your Meme, except for YouTube, I once bought it for one month.

[covert lake]

Damn

Wasn't it just a VPN

[twilit halo]

I sold out and bought youtube premium

[solar torrent]

I might bought both YouTube Premium and the uBlock Origin, to see how much they suffering from this.

[solar torrent]

Yes, they even have NordPass the password manager to it. Then I realized they also have ad blocker and tracking blocker as features.

[covert lake]

Hell nah

Refound it

Use an adblocker 🙏

[solar torrent]

This NordVPN's ad blocker works on the IP address hosted and protected by a VPN server.

[empty sky]

👍

[vital snow]

how to cheat https://englishtest.duolingo.com/

[solar torrent]

Why there's no MsBeauty when there's a MrBeast?

His name is Logan, but he ain't Wolverine.

[ashen hollow]

girl what

[vital snow]

yeah i suck 😭 i think i just wasted my 104$

[ashen hollow]

i can test ur english for a hundred bill

[vital snow]

i need their test result to apply for college 😦

[ashen hollow]

you can take ilets or smth

[solar torrent]

How can you type in English but can't speak it?

[vital snow]

thats kinda too late for me i have to apply in like tmr i dont have enough time to travel.
duolingo is fastest i think

[ashen hollow]

he needs a certificate to prove it smart ass

[gusty violet]

hey real quick does anyone know where to upload remixes just for other people to listen to

[ashen hollow]

ah fair enough use chatgpt by side

[gusty violet]

every time i upload something to soundcloud it gets taken down

[vital snow]

i can just im introvert idk what to say the test just asked "talk about the time when you won the prize" for 90 secs with 20sec countdown for prepare

[gusty violet]

im not looking to profit or anything just trying to share it

[ashen hollow]

do u wanna kiss

[gusty violet]

im good for now thanks tho

[vital snow]

the thing is i have to set my phone camera so they can see the screen and me

[ashen hollow]

oh wait 😭 damn

im sorry i wish I could help💔

[solar torrent]

You can post your remix tracks on your social media accounts, but it depends on how copyright detection checks your posts.

[vital snow]

not youtube they take the video down for cover ur own song 💀

[vital snow]

maybe i will just spend other 104$ to take another exam

what if i join vc and share screen can they detect it?

[ornate cloud]

@solar torrent a fumo and...

[solar torrent]

And what?

[ornate cloud]

Nothing

cya now

[elder willow]

Heyy

[ionic pumice]

alo

[ripe flare]

i think u just dont know anything about the new chip lol

[forest quarry]

in theory they should

but there isn't any support for training from rvc devs

it could 100% pull it off

[chilly lake]

when the company markets their chip in the way Apple does, there are certain doubts

also depends on the MPS Pytorch build support

[polar flax]

if M4 chip systems can run Flux, there should also be potential for rvc devs to work on the compatibility

[chilly lake]

they say there are GPU cores.. but what kind of cores?

if they were tensor cores they would've said so, no?

16-core NPU is there according to wiki, we'll see

supposedly 3x performance of M1, but again if M1 could not do 1:1 inference, x3 is pathetic

[solar torrent]

Run Flux on a Macbook Pro with M4 chip?

[chilly lake]

in a dream, maybe 🙂

while melting the whole device

[forest quarry]

dunno if this info is useful but m1 could do realtime pretty well especially with the okada fork

and i think it can inference normally iirc

[gray rover]

I could consider trying stuff out in a while in that aspect maybe
I think at some point it was tested, no?

[chilly lake]

last time I checked MPS Pytorch was offloding a lot of stuff to CPU

so the overall performance was barely faster than just CPU Pytorch

[gray rover]

is it a direct mps issue tho
or is it outdated pytorch n shit

[chilly lake]

okay for inference, not okay for anything else

[gray rover]

well, apple users have it hard

[pliant elm]

Guysss

[pliant elm]

RVC but GGML when?

[modern stirrup]

I ghost the down cool

[sterile lion]

anyone got egirl voice model i can have bro

[night lake]

Have you tried taking a whiff of #1175430844685484042

[lean plover]

Apalah cik cik stuck mythic bintang 13

[night lake]

Purple

[ionic pumice]

apalah cik id di gen chat

[lean plover]

Apa coba purple

Ungu

Ya mythic ungu

Mau ngetik apa sih blud inj

[night lake]

Ice cream because purple doesn't have any bones in the ocean

[lean plover]

Ngebahas apasih ni kocak

[ionic pumice]

blud in the big 24 das crazy

[night lake]

At least 1

[timid musk]

hello how do you ai cover

[ionic pumice]

wtf the man himself mangio

[covert lake]

is this a 'those who know' meme reference

[ionic pumice]

uh technically yeah

[silk adder]

Test

Test

Testing again!

[night lake]

https://tenor.com/view/breathe-boppity-bippity-wizard-breathing-gif-12311641005681234042

[ionic pumice]

yyoy'reure

[covert lake]

https://tenor.com/view/bill-hicks-mic-tap-mic-test-gif-13906564281384227237

[silk adder]

Have been trying to post here since I joined a week ago. Finally!

[ionic pumice]

bad internet for a week??

[silk adder]

No, Discord was telling me I couldn't post in this server for some reason. l3afai helped me troubleshoot and it started working today!

[ionic pumice]

ah

[elder willow]

omg it's mangio, also thanks for creating mangio crepe :0

[glass lagoon]

hello

[ionic pumice]

elo

[glass lagoon]

i cant download the voice

it isnt downloading

it is showing that pottentialy dangarous file

i clicked download anyway but it is still not downloading

[feral halo]

Ayo? @glass lagoon level 1 !!!

[glass lagoon]

nvm i it downloading

[north moth]

hi

[high wyvern]

what are some good rvc guis?

perhaps one thats compatible with linux mint?

[iron fiber]

hey

which roles do i need to screenshare in vc

pls helpppp

[naive edge]

what site/app do i use for the voice models

[neat ocean]

Hello from Russia!

[smoky hatch]

Hi

speakerbot compatible?

[covert lake]

for what? realtime voice changer for calls or ai cover?

and what's ur pc gpu

[covert lake]

are u trying to make ai covers or realtime voice changing for calls?

[high wyvern]

both

[feral halo]

Ayo? @high wyvern level 1 !!!

[high wyvern]

so should i use 2 seperate ones

or is there 1 that can do all

[covert lake]

nope there isn't

its 2 different softwares:

• RVC: train (make) models and inference (use them) on pre-recorded audios
• Wokada: inference in realtime for calls, the fork has better performance

[high wyvern]

alr

[covert lake]

for wokada u could check https://rentry.co/ForkVoiceChangerGuide#linux

[high wyvern]

could you dm me the links if you have them?

[covert lake]

for RVC, u can either use

• mainline (original RVC): https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/blob/main/docs/en/README.en.md#preparing-the-environment
• Applio (RVC fork, has tts and is kinda faster, and better interface): https://docs.applio.org/applio/getting-started/installation

[high wyvern]

alright thx

ill check them both out

[covert lake]

Yw, for any issues u can ask in #✨│ai-help and #🔍│help-w-okada

[high wyvern]

alr

thanks so much, ill be there if i have issues

[covert lake]

alr your welcome

[elder willow]

imagine if we can run Minecraft in gradio

or cloud gaming in google colab/kaggle/lightning.ai

prob impossible but interesting things

[naive edge]

voice changer

[idle fiber]

@main crypt

[gleaming turret]

соси сисичку

[covert lake]

what's ur pc gpu

im guessing realtime voice changer for calls

[naive edge]

i guess yeah

[feral halo]

Ayo? @naive edge level 1 !!!

[naive edge]

i use a laptop

[covert lake]

You can check your pc gpu via:
ctrl+shift+esc (task manager) -> Performance tab -> GPU

u might have GPU 0 and GPU 1

[cinder blaze]

hello

[onyx trench]

does anyone have the joshua block rvc files i think they took it down 🤧

[elder willow]

what if snapdragon mobile cpus may support cuda in the future? rvc on mobile?

[naive edge]

my gpu is gpu 1 and gpu 0

[covert lake]

i mean the names

[naive edge]

NVIDIA GeForce RTX 3050 6GB Laptop GPU

and Intel(R) UHD Graphics

@covert lake

[covert lake]

eh not the best but doable

-rt

[rare sorrel]

Interaction has expired, use the command again for a new interaction.

💻 Local Realtime RVC

• Guide for deiteris' modified W-Okada's Voice Changer Client (Fork)
• Guide for W-Okada's RealTimeVoiceChangerClient
• How to use real time conversion with RVC (voice changer)
• RVC TTS

[covert lake]

1st link, the wokada fork

[weak valley]

what the fuck is happening to this server?

[icy pendant]

Wdym

[weak valley]

verified doesnt need a role anymore and echtebass is gone

the hell is happening

[icy pendant]

Regarding echtebass, an admin is looking into it, it happened quite fast. Verified is still needed from what I know, role order was changed from what i see

[weak valley]

so some weird shit is happening

[wide pivot]

hello can someone please help me set up the ai voice changer? i would greatly appreciate it

[icy pendant]

-rt

[rare sorrel]

Interaction has expired, use the command again for a new interaction.

💻 Local Realtime RVC

• Guide for deiteris' modified W-Okada's Voice Changer Client (Fork)
• Guide for W-Okada's RealTimeVoiceChangerClient
• How to use real time conversion with RVC (voice changer)
• RVC TTS

[icy pendant]

1st link for optimized version, 2nd for original

[wide pivot]

which one do you recommend for a 6700xt gpu?

[icy pendant]

1st

[wide pivot]

Thank you i'll try to do it rn

[royal yarrow]

hahumm...

[near mountain]

can someone with colab experience help me with this error im getting on a notebook ive tried many things but it wont work lmao its a outdated notebook but i need it to work for a model im working on note: This error originates from a subprocess, and is likely not a problem with pip.
Building wheel for hmmlearn (setup.py) ... error
ERROR: Failed building wheel for hmmlearn

[hard trail]

беда

[feral halo]

Ayo? @hard trail level 1 !!!

[near mountain]

used to work fine but i guess things was updated and now its not working ive tried lowering the hmmlearn version and updating it to new version to no success

[near mountain]

sorry i only speak english brother

[hard trail]

как скажешь

[harsh flame]

Hello fellow people

It is i man from the moon

[elder willow]

o

[gusty mortar]

anyone know the best kanye model? like the one on weights.gg?

[bitter iris]

Guys does someone's know if its possible to download a model that trained in fal.ai lora and generate it on stable diffusion?

[tight oar]

I can't download it, everything is different, before there was a different way to download it, now there's a lot of information and I don't understand anything

By the way, would there be a direct link to the download? cuda version

help me please!!

[dim mountain]

https://arxiv.org/abs/2411.06807

[dim mountain]

Can't be bothered to save to a text file but I'll do that tmrw

[chilly lake]

possible issues 1) you're trying to install a specific version of the library that has no compatible wheel made for python version on colab.. .like library from 3 years ago vs python 3.12

2. no compatible pre-built wheel for the particular os and missing build tools to build the library from scratch

[finite galleon]

so how can i train models?

[stuck pine]

Hello, I'm a Full Stack AI Engineer with 6 years of experience. I work with front-end technologies like React, Angular, Next.js, and PHP, and back-end frameworks such as Django, FastAPI, Gin, Echo, and Mux.
This is my github repo. github.com/AIXerum
I also specialize in developing AI Agents with knowledge graphs and Vector Databases. I'm here to help, so feel free to send me a message if you want to chat or need advice!

[queen kernel]

Hello Sir

If you want to be a helper. You can use /jointeam

[vital snow]

Hi

[night lake]

How do you calculate how many steps are in a epoch?

[stuck pine]

I believe you can calculate this by dividing the total number of datasets by the batch size.

[night lake]

Wdym by "total number of datasets" like how much data is in the set or how many sets

[north pewter]

does anyone here work with image checkpoints?

[night lake]

Ah yes thumbs up... My favorite response

[stuck pine]

do u want image gen?

[finite galleon]

yo ik im supposed to ask in the other channel but cant anyone help me to build a model? i got 5m of audio recording alr

[north pewter]

well I'm having trouble with image generation and I'm wondering how to fix it

[stuck pine]

pre-trained model?

[north pewter]

course this isn't an AI art discord but I'm SoL

yeah

[pale axle]

Who needs AI girl-friend?

I am seeking people

How are you?

[polar flax]

ah typical chatbot response

[tight blade]

Does ANYONE know a high quality fast vocal separator?

I'm desperate and I'm not tryna wait 2 hours on mvsep

[nova peak]

“VLONE DRIP” 🔥🔥🔥

[hushed pier]

Shark X giveaway from coolermaster

7k pc

[split whale]

Communist.

[barren beacon]

Can rx 5700xt run the voice changer good?

[void lynx]

hey guys! does anyone know what ai he used here? https://www.youtube.com/watch?v=pBR5GYc00U4

[void lynx]

would there be a free version that can do this?

[earnest dragon]

yes it can run it fine just will not be low ms

[deep geode]

Hello

i've 1660 super 6gb will i be able to run voice changer?

[covert lake]

Realtime voice changer for calls?

[deep geode]

yeah

[feral halo]

Ayo? @deep geode level 3 !!!

[covert lake]

Yes

-rt

[rare sorrel]

Interaction has expired, use the command again for a new interaction.

💻 Local Realtime RVC

• Guide for deiteris' modified W-Okada's Voice Changer Client (Fork)
• Guide for W-Okada's RealTimeVoiceChangerClient
• How to use real time conversion with RVC (voice changer)
• RVC TTS

[covert lake]

Read the 1st link, the Wokada fork

[covert lake]

Realtime voice changer for calls?

[deep geode]

alright thank you, ill read it rn

[covert lake]

I think luma labs tbh,it's free

[covert lake]

Yw

[void lynx]

wow, it's free?

[feral halo]

Ayo? @void lynx level 3 !!!

[covert lake]

#1159290752195633273

[covert lake]

Yea

[void lynx]

ill check it out

[covert lake]

#1159290752195633273

[covert lake]

U can use UVR if u got a good pc, or UVR Cloud

Of course it's not lightning fast lol

[covert lake]

Tell ur PC GPU in #✨│ai-help

[covert lake]

👍

[covert lake]

Download what? Elaborate more

And tell what's ur PC GPU

[covert lake]

What's ur PC GPU

#1159290752195633273

[deep geode]

btw im new to this

does using voice changer decrease the health of gpu

[forest quarry]

no?

[covert lake]

The fork I gave you gives you even more performance with less demand, it doesn't require super good resources

[forest quarry]

what does screw up a GPU's health is extreme heat all the time and that's not happening in normal conditions with okada

and ofc if you have the right cooling

[covert lake]

Unless he plays 5 GTA 5 with 3 fortnites while using Wokada

[forest quarry]

i mean

if you can even run 2 of those

your GPU would cry

even if it was a 4090

[covert lake]

Yeah that's why I can barely run one

[forest quarry]

😭

[covert lake]

Actually gta 5 is a decade old, maybe I can run it

[forest quarry]

yeah

[vital snow]

intel uhd graphics moment 😭

[covert lake]

I can also run Fortnite but its laggy

Idk if it was laggy only in UEFN

[forest quarry]

i lived with a hd 4000 for 7 years

[vital snow]

damn

[forest quarry]

yeah

[covert lake]

What GPU do u have now

[forest quarry]

the M1 GPU

[covert lake]

Oh right

[forest quarry]

which is decent and could probably run a lot of games

...but no native ports

for certain games i care about

[covert lake]

Dualboot linux

And use wine

[forest quarry]

nah I'd be dead

[covert lake]

Why

Linux is good

[forest quarry]

the computer isn't mine

technically

so

I can't do that type of thing

[covert lake]

Oh damn

[forest quarry]

• linux is pain to set up

at least from my experience

[covert lake]

Depends on distro

[forest quarry]

it did not work at all

[forest quarry]

fucking Ubuntu

[covert lake]

Was it hard to setup that?

I used Ubuntu on a VM

[forest quarry]

i couldn't get it working

maybe it was because of a damaged hard drive but like

[covert lake]

Rip

[forest quarry]

ffs

i think i have bias

i may dualboot linux on my next computer though

[covert lake]

Ur macos is anti Linux maybe

[forest quarry]

it wasn't on Mac

it was on an Acer computer

which was the laptop i had previously

in 2 years it managed to go from completely normal to completely broken

[covert lake]

Wtf did u do

[forest quarry]

just normal use

lmao

the hinge broke

screen broke

some keys fell off

the thing was just

i

it was sad

[covert lake]

Nah u abused that pc

[forest quarry]

i did not

i just used it normally

the only time I jumped on it was after it broke down

[covert lake]

How did keys fallout 😭

[forest quarry]

and it worked again

[forest quarry]

idfk

it's been like 8 years