I have heard about AIs that can clone voices from samples, but not sure which one to use.
Not using it for anything deceptive: I just want the voiceover actors I like to read me bedtime stories.
You must log in or # to comment.
I always see speech-to-text stuff and text-to-speech stuff but never voice-to-voice.
I played with xtts-api, Google the GitHub repo. Easy to get up and running, if you are good with self hosting and apis
