mstar.model.kokoro

Modules

components
config	Kokoro-82M configuration, built from the checkpoint's config.json.
g2p	Grapheme-to-phoneme front end and sentence chunking for Kokoro.
submodules	The Kokoro synthesis node: one sentence chunk per loop iteration, batched across requests, with CUDA graphs per length bucket.
voices	Voice registry: the bundled Kokoro voice packs and blends of them.