Mixed forum

Training AI Voices with RVC

Started by mad-gamer 4 posts last post 1 year ago

#1 Archived

Transcription

Hello everyone, this is MadGamer, and for the longest time, I was able to use this website called voicemy.ai to train AI voices. For whatever reason, not too long ago, they decided to make voice cloning, I think, a subscription because it doesn't work for me, for some reason. Like, I can't put files, I can't drop files into the window where it says, select audio file here, and it also says, under the heading, it says, please upgrade your subscription to use this feature. So if anybody knows how to use the actual RVC program to properly train a good AI voice, please. Please let me know. And by the way, the graphics card I have is an NVIDIA GeForce RTX 3050. My CPU is an Intel 13th Gen Core i7. So if anyone knows how to do this, please let me know.

#2

Relatively easy to train your own voice, but you'll need 2 applications, Applio and w-okada. You need good source material and a modern GPU. Info in the discord. Come through for details. codyhurst.com
CH Official

#3

Yeah pretty much what he said but also do note. The source material needs to be of at least moderate quality. The more accuracy you want, the more material you need. If you can get a wide range of vocal patterns and expressions in the audio it will give you the best results
Even if the darkness grows too deep, even if it looks impossible. You are never alone. You are never forgotten. Remember that.

#4

no you need consistant one though, so make microphone it same one, or you get very bad quality like electronic sound high pitched