A native FP16 MLX conversion of
ResembleAI/chatterbox-nano,
prepared by
Rybib for Apple Silicon and on-device experimentation.
Chatterbox Nano and its architecture were created by
Resemble AI. This is an independent conversion,
not an official Resemble AI release.
The converter strictly verifies that every required Nano decoder and vocoder
parameter is mapped. It also merges PyTorch weight-normalization parameters
into inference weights and converts convolution/GPT-2 layouts for MLX.
Listening tests on Apple Silicon found the output perceptually equivalent to
the official FP32 Nano model. This is not a formal benchmark; applications
should perform their own voice-cloning and long-form tests.
This package requires a Chatterbox Nano-capable MLX Audio runtime. At the time
of conversion, upstream MLX Audio did not correctly map all Nano mean-flow
decoder tensors without the accompanying runtime/converter fixes.
Voice cloning additionally requires the S3TokenizerV2 speech tokenizer. It is
included under S3TokenizerV2/ so applications can clone voices completely
offline after one installation.
The upstream Chatterbox model is distributed under the MIT License. Its
copyright notice is preserved in
LICENSE.
