Professional Voice Cloning involves training (fine-tuning) the model on large sets of a particular speaker’s voice to create a custom model.
So, once you've uploaded your samples, your voice will be added to the queue. The estimated training time until you get your voice is ~4 weeks as the training is run in batches, but this is dependent on a few factors so it is hard to give an exact estimate. Unfortunately, it can sometimes take longer.
Hopefully, you will get your voice more quickly than the estimate, but we would still recommend you keep your expectations tempered. As demand grows, we can hopefully run these batches more periodically.
The estimated 4 weeks is after you've uploaded, verified, and requested fine-tuning as it is first then the voice will be put into queue. Once all of these steps are completed, the tag on the voice card in your VoiceLab should say "queued" while the voice is being trained.