Hi hi - I'm currently looking to make a voice model for one of my characters. As there's no existing voice for them, this currently means no samples to train it on. If anyone knows where or how I could start in trying to do this, I'd appreciate it greatly. I've seen models imitating existing voices, but for a case like this, I'm still rather stumped
#Original voice creation
1 messages · Page 1 of 1 (latest)
the point is that you find samples of audio to make your character's voice out of. no making voices from nothing here
you need make dataset
-rvc
Suggestion for @simple spindle
Documentation
Credits: AI HUB FRANCE
✨ More guides
Full AI Voice Model Training Guide (Local)
Link: YouTube
Credits: Christopher Villanueva
Model training with Mainline RVC
Link: Rentry
credits: Raven (ravencutie21)
AICoverGen Colab Guide
Link: Google Docs
Credits: Eddy (Spanish Helper)
Create a model with RVC disconnected (colab)
Link: Google Docs
Credits: Angetyde
How To Make an AI Cover With Ilaria RVC
Link: Rentry
Credits: 👽 Julia (ailen2091)
Since you're trying to make a unique voice, try merging multiple models to create a new voice. Select a few, let's say VTubers, who voices you like. Then merge the models with RVC to create a unique voice
I've heard this method create amazing results
This
But I would train a single model using multiple different voices rather then merging
Because sometimes merging can have a bad result
Interesting
I might try that
I did wonder if that was possible
To create a sort of 'inbetween voice', yes?
Yeah
I see I see, could try that