Professional voice clones are fine-tuned to sound as natural, accurate, and life-like as possible, requiring a minimum of 5 minutes of source audio (the more, the better, up to a maximum of 250MB source audio file size). They require some time to fully train (a few hours). You will receive an email notification after training is complete so you can begin using your voice.

Users are limited to a number of professional voice clones based on their plan.