kokoro-82m-stacked (Vokra GGUF)

Text to speech model, converted to the Vokra GGUF format for Vokra, a zero-dependency speech-AI inference runtime.

This is a conversion, not a new model. The weights are the upstream ones; Vokra re-packages them so its runtime can memory-map them directly. Credit for the model belongs upstream — see Source below.

Files

File	Size	SHA-256
kokoro-82m-stacked.gguf	338.8 MB	69a943a826fe93810770f1c164bbda59a0b175354899cf2e99a79f7aa22964f8

Usage

# Download (any HTTP client works — the file is a plain GGUF)
curl -L -o kokoro-82m-stacked.gguf \
  https://huggingface.co/vokra/kokoro-82m-stacked/resolve/main/kokoro-82m-stacked.gguf

vokra-cli run --model kokoro-82m-stacked.gguf --text "こんにちは" --output out.wav

Text input needs a G2P front-end; see the model notes below for which one this voice expects.

Provenance

Field	Value
Architecture	kokoro-82m-istftnet
Tensors	549
Upstream source	hexgrad/Kokoro-82M (Apache-2.0)
Upstream licence	Apache-2.0
Licence class	permissive
Registry model id	kokoro-82m
Vokra GGUF schema	1
Converted by	vokra-core 0.1.0-alpha.0

Every row above is read out of this file's own vokra.* metadata, so the card cannot claim something the artifact does not carry.

Licence

The weights are distributed under Apache-2.0, unchanged from upstream. Conversion does not alter the licence, and your obligations run to the upstream author.

Verifying this file

shasum -a 256 kokoro-82m-stacked.gguf
# expect: 69a943a826fe93810770f1c164bbda59a0b175354899cf2e99a79f7aa22964f8