stable-diffusion.cpp VS bark-with-voice-clone

I did start with integrating SD with this repo: https://github.com/leejet/stable-diffusion.cpp

Interesting. It still doesn't seem to be very quick: https://github.com/leejet/stable-diffusion.cpp/issues/6

But don't get me wrong, I look forward to playing with ggml SD and its development.

And more stuff I’m often checking back on: - https://github.com/staghado/vit.cpp - https://github.com/serp-ai/bark-with-voice-clone - https://github.com/leejet/stable-diffusion.cpp (generate images) - etc … there’s too much fun stuff out there. Wish I had more free time haha.

Check out the Bark model: serp-ai/bark-with-voice-clone: 🔊 Text-prompted Generative Audio Model - With the ability to clone voices (github.com)

You can run a fork of bark locally https://serp.ai/tools/bark-text-to-speech-ai-voice-clone-app/

I want to install bark with voice cloning locally and I do not find any installation help with this. Can someone please provide step by step instructions for this? I tried the collab but that is very limited, and I can't get that to work properly, and it'd be way easier if I just set it up locally. I do not know of any scripts for local installs either so if someone could point me to a python script to use a custom voice with bark and run the TTS that'd be great too.

It's beyond my ability but apparently there's this: https://github.com/serp-ai/bark-with-voice-clone I'm forced to wait for a more user friendly alternative.

This fork with voice cloning unlocked