[FEAT] Ability to load multiple voices

[josiah-roberts]

Is this a new feature request?

• I have searched the existing issues

Wanted change

Support specifying > 1 voice to be loaded, allowing callers to specify which voice they want to use.

Reason for change

My particular use-case is synthesizing audiobooks with multiple speakers that exist in separate onnx models.

Proposed code change

No response

[github-actions]

Thanks for opening your first issue here! Be sure to follow the relevant issue templates, or risk having this issue marked as invalid.