#How to setup a voice model

1 messages · Page 1 of 1 (latest)

shut remnant
#

pc gpu, operative system

PC GPU: Nvidia 4060Mobile (Laptop)
Operating System: Windows 11 Pro Version 24H2

I am looking to help my trans friend to achieve the most realistic female voice changer, that can be used in real time such as on a video call.

I have downloaded w-okada, but if there's a nice instructions I would prefer to reinstall everything, since I downloaded an alpha version, with it appearing quite glitchy.

I do not have a VB-Cable virtual cable/audio device, I assume this will be needed.

I hear there are some differences between some GPU vs CPU models, but I'm simply looking for the best one that she can use.

I do have a female born friend that I can use to record reading a book or something to make my own model, but this would be great for later, I would first like to simply set up a pre-trained model.

Thank you!! <3

tidal sierra
#

-realtime

ebon hornetBOT
# tidal sierra -realtime
💻 Local Realtime RVC

Guides for Programs that use RVC Models in Realtime for Calls/Games

• Wokada Deiteris Fork

Most suggested. GUIDE

• Original Wokada

ONLY the latest alpha comes close to the Deiteris Fork performance, older versions in youtube tuts are way worse. GUIDE

• **RVC GUI Mainline Realtime**

Unavailable, the guide is outdated and the program is worse compared to the ones above, and much less updated

tidal sierra
#

the 1st one, wokada deiteris fork, has everything you need

#

it has everything you need

#

@shut remnant also, what's your trans' friend gpu? to be sure its good enough

shut remnant
#

Either 3070, or 4060-4070. (Now you know why it's my job to do this hahaha). I can't be bothered to make them find which model it is it will take 10 minutes. But since it's relatively similar to mine, it should be fine.

tidal sierra
#

It would be better you read up the guide, get vac lite, and then click on download Nvidia (not rtx 50 serie since you don't got one)

#

The GitHub link in the first thing is just for the introduction

shut remnant
#

Oops. I clicked on the right one here, and started following the instructions. Mb haha. Only installed a VAC (which turns out to be the correct one) and the files for the w-okada fork, I haven't installed them yet. I'll follow the instructions on the website you sent. Sorry!

image.png
tidal sierra
#

Because the guide has also the download link for vac lite, best known settings, suggested models and more info overall

shut remnant
#

I am here! Very easy actually haha, but thank you so much for the link to download all this. Are there any recommendations for the most realistic male sounding -> female voice changers? Thank you <3 Furthermore, client or server audio?

image.png
tidal sierra
#

@shut remnant Are they in the server? You could ping them there, is there a specific reason you're the one asking instead of your friend?

#

You can check your pc gpu on Windows via:

ctrl+shift+esc (task manager) -> Performance tab -> GPU

shut remnant
#

She has a 4060

#

She will join soon! Just sent them a message

tidal sierra
#

@shut remnant I saw u sent a voice message then deleted it?

shut remnant
#

Turns out the output .wav was fine. I was just hearing the "Monitor" really really poorly, but it seems to have simply fixed itself since.

This seems to be the best I can do so far, to me it sounds great! What do you think, are there any better models?

I have also uploaded my settings, what do you think. We have british accents (clean), and this voice appears to be american do the index is not to the max, but it is not extremely foreign.

image.png