s
#Hey i need your help in using the voice change program
hasty hound
rain lantern
s
This is a General AI Server, AI has many fields
Elaborate:
- your PC GPU
- your operative system
- what you want to do
- what tutorial link are you using (if you used any before)
- a screenshot of the program (if you used any before)
rain lantern
just a sex ill see what's the Gpu
You can check your pc gpu on Windows via:
ctrl+shift+esc (task manager) -> Performance tab -> GPU
rain lantern
its trash isn't it
yep absolutely, it won't be good for ANY AI related tasks locally (running on your pc hardware) as it's integrated graphics, but you can use cloud (remote good pc) with limited free time
can you elaborate what you want to do? like:
- ai covers
- roleplay
- e-girl trolling/catfishing
- change pre-recorded audios
hasty hound
just a single ai voice change
like
i wanna make my president say "type shit"
for a tiktok edit on my page
rain lantern
just a single ai voice change
there's different ones depending what you want to do
are you looking to do Text To Speech (TTS), or STS (Speech To Speech) on pre-recorded audios, or STS realtime for games/vc?
rain lantern
ahhh
yeah no there isn't a 1 click app that does anything, Open Source AI is complex and intensive
rain lantern
I'm not sure how good is the text to speech so ill prolly go STS
the choice depends on what you want to do, like you just want to write a text that joe biden will read for a tiktok, or want to instead voice over yourself and then use joe biden on that
rain lantern
Netanyahu lmao
idk what that means 😭
hasty hound
i don't think my computer will survive this terror though
rain lantern
I'll go speech to speech
im guessing you mean on pre-recorded audios, so RVC
Train (make) RVC Models on cloud:
- Prepare the Dataset
- Setup RVC:
Choose a cloud way to use RVC,
- Google Colabs (max 4 hours of daily T4 16gb gpu not granted for free, not much hours for training, but easy to use, there's a paid tier):
- Kaggles (a bit harder to use and needs phone number but gives 30 hours weekly of better gpus, either T4x2 16gb each or P100 16gb, only free):
- Lightning.ai (Kinda hard, needs login, no issue with web uis or anything, but only free 15 credits monthly, Free Studios run 24/7 but require restart every 4 hours. There's a paid tier):
- Be sure to know about the tensorboard
Google Colab = Easier but risk of getting disconnected
Kaggle = Harder but way more gpu time
If you are looking for the easiest way and for free, is using https://weights.com/ which ofc uses RVC
RVC Inference (use models) on pre-recorded audio on Cloud
You can use either:
- Weights.com: Easiest Possible Ever Automatic
- Ilaria RVC Zero: Fastest free on cloud
- Applio UI Colab: RVC Fork with some extra features like TTS
- RVC AI Cover Maker UI: Automatically Separates the Vocals and Instrumentals, converts the voice and mixes them back
rain lantern
i don't think my computer will survive this terror though
it will run all on the cloud, the only thing running on your pc is the browser and internet connection, which is why it has limited free time
hasty hound
im guessing you mean on pre-recorded audios, so RVC
# Train (make) RVC Models o...
and i can use all the models available on this server for each of these methods?
rain lantern
and i can use all the models available on this server for each of these methods?
as long it's an RVC model, yes
hasty hound
of course, can i dm u if i face an issue
rain lantern
of course, can i dm u if i face an issue
there's no need to dm, you can try the tools yourself, and let me know for any issues here
i will keep this up
rain lantern
you don't have to, except pitch which may be needed to higher it for female models, and lower it for male models
rain lantern
@hasty hound is this solved?