What is the difference between Instant Voice Cloning and Professional Voice Cloning?

Instant voice cloning lets you clone voices from short samples without training (fine-tuning) the model. The process is computationally less demanding, but the voice is cloned with lesser fidelity. Instant Voice Cloning is available on the platform as part of VoiceLab.

Professional Voice Cloning involves training (fine-tuning) the model on large sets of a particular speaker’s voice. Speech generated by a trained model should be indistinguishable from the original speaker’s voice. Professional Voice Cloning is available to Enterprise-level clients requires securing a commercial use license from the voice owner and is not available on our platform but we will update our users when it is.