For two longer ones I had yesterday only garbage after half of the text. All before was perfect. No error messages.
Thank you for this program.

All-in-one AI voice studio with text to speech, voice cloning, voice changing, dubbing, and short clips from podcasts. · By
I'd like to see it (but of course not at the cost of more pronunciation errors.) If and when it can be done seamlessly, that would be great. The trade-off of longer processing times, would be acceptable. I suspect that 48khz would fit better with many users' workflow (DAW templates, sharing with collaborators, etc.) Thanks for considering it!