#How create AI of my voice
1 messages · Page 1 of 1 (latest)
-colab
- Applio, by IA Hispano Google Colab
- AICoverGen-WebUI, modded by Hina Google Colab
- AICoverGen-NoWebUI [English], by Ardha, fixed by Eddy, Hina and Gdr Google Colab
- AICoverGen-NoWebUI [Spanish], credits to Eddy, Hina and Gdr for translating and fixing Google Colab
- Ilaria RVC, by thestingerx Google Colab
- RVC Disconnected, by Kit Lemonfoot Google Colab
- easyGUI, by rejects Google Colab
- Applio, by IA Hispano Huggingface Spaces
- Ilaria RVC, by thestingerx Hugginface Spaces
- RVC-HFv2, by r3gm Huggingface Spaces
- AICoverGen, by r3gm Huggingface Spaces
- Advanced RVC Inference, by r3gm Huggingface Spaces
- RVC v2 Huggingface version, by Clebersla Huggingface Spaces
- GPT-SoVITS (demo), by litagin Huggingface Spaces
-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)
General Process:
-
Use a high quality microphone, preferably shotgun or condenser mics. If you don't have one you can use your phone. But when you record, make sure your internal audio processing settings are turned off, like noise reduction, EQ, or limiters or compressors.
-
When recording, use proper bit depth, don't use 16bit, it has bad dynamic range. But if you don't have any other options then you can is it instead.
-
Read a book or story and record yourself in an anechoic room, no noise and any static noises around. There are tons of tips on the internet on recording dry vocals.
-
Record yourself at about 15-20 mins, should be enough to accurately replicate your accent and nuances of your voice.
-
When recording, have different emotions, make different pitch ranges.
-
On the other tips, use the guides here to train your voice.