neutts-air (Vokra GGUF)

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
neutts-air.gguf	1426.6 MB	f6caf559e919b16d77ac28177e59ee5427a5de92bdeedd719ecab00b4afbb754

Usage

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

vokra-cli run --model neutts-air.gguf --input input.wav

Provenance

Field	Value
Architecture	neutts-air
Tensors	291
Upstream source	neuphonic/neutts-air (Qwen2 0.5B LLM backbone emitting NeuCodec audio tokens, on-device instant voice cloning, apache-2.0 end-to-end; sibling codec = neuphonic/neucodec)
Upstream licence	apache-2.0
Licence class	permissive
Registry model id	neutts-air
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 neutts-air.gguf
# expect: f6caf559e919b16d77ac28177e59ee5427a5de92bdeedd719ecab00b4afbb754