Here's how to cover any song with any voice, all using FREE AI tools. You don't even need a nice computer, GPU, or Colab. Plus, I'll show you how to train a voice model completely from scratch, so you can clone anyone's voice.

0:00 Intro

0:57 Ed Sheeran to Taylor Swift
Download from Spotify https://spotifydown.com/
Free audio editor Audacity: https://www.audacityteam.org/
Isolate vocals online with Vocal Remover: https://vocalremover.org/?utm_source=ai-search.io
Isolate vocals locally with UVR: https://ultimatevocalremover.com/
^Tutorial on this: https://youtu.be/RvZM381wdmQ
AI HUB Discord: https://discord.com/invite/aihub
Voice conversion using Kits AI: https://www.app.kits.ai/?via=ref

12:58 Jpop example: Yuuri to Harutya

18:29 Bonus! Yuuri to Taylor Swift

19:02 Cloning Akie's voice from scratch
Do this locally or in Colab using RVC: https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI
^Tutorial on this: https://youtu.be/9TroP5mR3CM

Taylor Swift model by AIVERSE
Harutya model by Eddy

Discover thousands 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