Indicate whether TTS model supports voice cloning

[eginhard]

It would be useful to check in tts_with_vc() whether the underlying model supports voice cloning directly and direct users to tts_to_file(..., speaker_wav="...") in that case to avoid issues like in #3067. Is there some way to check this easily?

most of the models needs speaker_manager if they voice clone but I don't think it applies them all. We should probably attribute them in the model classes.

Originally posted by @erogol in #3275 (comment)

[DrewThomasson]

I thought it was if the model has multi-dataset in the name of the model when you make it print out all of the tts models?

#Python

print(TTS().list_models())

Or I may be thinking of something else

[eginhard]

I thought it was if the model has multi-dataset in the name of the model when you make it print out all of the tts models?

How many datasets a model was trained on is unrelated to whether it supports voice cloning, it's just a coincidence if that heuristic works for the currently available pre-trained models.

[DrewThomasson]

hm, In that case I'm all for the feature your requesting

[stale]

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions. You might also look our discussion channels.