We have so many videos to voice, and voice talent is a rare thing. Plus, I want to narrate my own videos. Is there a way that I can get myself to do a faultless take every time?
I’m experimenting with Tortoise Text-to-speech, trained using my OWN voice using this tutorial: Docker images - TTS 0.22.0 documentation
Let’s see how it goes!
So I have it working using one of the built in voices: