Support for Cartesia sonic-3-latest model

Is there a way we can get support for Cartesia’s “sonic-3-latest” model? Their latest model includes the recent Sonic 3.5, which includes a more natural speech. Right now there’s no way to access it, since Sonic 3.5 is only on their preview, sonic-3-latest. Thank you in advance!

+1 would be great if accessible via livekit inference

It was just added so give it a try.

Looks like it’s working! Thank you @CWilson