Here’s a full tutorial on how to train an AI on anyone’s voice, and use it to say anything! We’ll use RVC (Retrieval-based-Voice-Conversion) on Colab for training and voice-to-voice conversion.
0:00 Intro
0:15 Finding & extracting a voice
4:06 Training a voice model using RVC in Colab
https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI
13:20 Using the voice model (voice-to-voice)
15:11 Results!
15:52 Saving a voice model for use later
18:12 Importing a voice model
19:52 Training an existing voice model further
This tutorial can be quite complicated. Feel free to ask questions in the comments below if you get stuck!
Search the most complete list of AI Tools, also available in 中文, español, 日本語:
https://ai-search.io/
Here’s our equipment, in case you’re wondering:
GPU: RTX 4080 https://amzn.to/3OCOJ8e
Secondary GPU: GTX 1080 (too old, would not recommend)
Mic: Shure SM7B https://amzn.to/3DErjt1
Secondary mic: Maono PD400x https://amzn.to/3Klhwvu
CPU: i9 11900K https://amzn.to/3KmYs0b
If you found this helpful, consider supporting me here. Hopefully I can turn this from a side-hustle into a full-time thing!
https://ko-fi.com/aisearch
