VibeVoice: A Frontier Open-Source Text-to-Speech Model

does anyone know of recent TTS options that let you specify IPA rather than written words? Azure lets you do this, but something local (and better than existing OS voices) would be great for my project.

I'm using Kokoro via https://github.com/remsky/Kokoro-FastAPI. It has a `generate_audio_from_phonemes()` endpoint that I'm sure maps to the Kokoro library if you want to use it directly.

My usage is for Chinese, but the phonemes it generated looked very much like IPA.