curious about the latency characteristics though. 1.5x realtime on a 9700 is fine for batch processing but for interactive use you need first-chunk latency under 200ms or the conversation feels broken. does anyone know if it supports streaming output or is it full-utterance only?

the phoneme-based approach should help with pronunciation consistency too. the models i've tried that work on raw text tend to mispronounce technical terms unpredictably — same word pronounced differently across runs.