Yeah, it's fast and hard to keep up with!
Eleven Labs also now has a more advanced version of voice cloning, which they call "
Professional Voice Cloning," but there's some caveats -
"For best results, provide at least 30 minutes of speaker training data (3h is optimal). The training data you upload should be clean recordings of a single speaker, containing no background noise or music.
Please remember: the speaking style contained in the training data will be replicated in the output, so depending on what delivery you are looking for, the training data should correspond to that style (e.g. if you are looking to voice an audiobook with a clone of your voice, the audio you submit for training should be a recording of you reading a book).
For now, we only allow you to clone your own voice. You will be asked to go through a verification process before submitting your fine-tuning request."
Notice the bolded part at the end, which would be a dealbreaker for doing an even better BWR clone.