Everywhere you look people are promising you the moon in "next generation" voice-cloning. But is it true? Can you truly clone a voice in mere seconds? While the answer may not be exactly what you were hoping to hear, the good news is that you can still do some highly impressive work!
Voice "Synthesis", or, Voice "Mimicking" is what we're able to do.. and while that may not be what you expected, I think you'll still be pretty amazed at what you can do with the use of a TTS server and a bit of Python code.
The Mockingbird-TTS (formerly XIN-TTS) GUI used in this tutorial (which I personally built) is available at: https://www.patreon.com/posts/mockingbird-tts-111336929
------ Helpful Video Tutorials -----
Installing Cuda: https://youtu.be/_GpyoEbs3Hs
Installing CuDNN: https://youtu.be/RY2mEbi7PJc
Fresh AI Setup (Windows): https://youtu.be/4aCtOVcvcj4
Installing Miniconda: https://youtu.be/ULAVtKBOKXE
Installing Python: https://youtu.be/1CdeBbk9A2k
Insalling Git: https://youtu.be/xxVOm3ndeSU
Installing WSL: https://youtu.be/3GNqg3GdEKA
Installing Llama.cpp: https://youtu.be/r-05yuXTEPE
Gary
2024-08-01 08:25:16 +0000 UTCGary
2024-08-01 08:20:40 +0000 UTCRabah visuals
2024-08-01 08:18:15 +0000 UTC