mlx-community/MOSS-Audio-Tokenizer-MLX-8bit

MOSS Audio Tokenizer — MLX 8-bit

This repository contains an MLX-native int8 conversion of the MOSS Audio Tokenizer for Apple Silicon.

Note This repo is a community mirror of the canonical MLX conversion maintained by AppAutomaton at `appautomaton/openmoss-audio-tokenizer-mlx`.

Variants

Model Details

• —Developed by: AppAutomaton
• —Shared by: mlx-community
• —Original MLX repo: `appautomaton/openmoss-audio-tokenizer-mlx`
• —Upstream model: `OpenMOSS-Team/MOSS-Audio-Tokenizer`
• —Task: audio tokenization and codec decoding
• —Runtime: MLX on Apple Silicon

How to Get Started

Load it directly with `mlx-speech`:

from mlx_speech.models.moss_audio_tokenizer import MossAudioTokenizerModel

model = MossAudioTokenizerModel.from_path("mlx-int8")

The tokenizer is loaded automatically when you run OpenMOSS generation scripts. You usually do not need to instantiate it directly.

python scripts/generate/moss_local.py \
  --text "Hello from mlx-speech." \
  --output outputs/out.wav

Notes

• —This repo contains the quantized MLX runtime artifact only.
• —The conversion remaps the original MOSS audio tokenizer weights explicitly for MLX inference.
• —The artifact is shared by the OpenMOSS local TTS, TTSD, and SoundEffect runtime paths in this repo family.
• —This mirror is a duplicated repo, not an automatically synchronized namespace mirror.

Links

• —Canonical MLX repo: `appautomaton/openmoss-audio-tokenizer-mlx`
• —Source code: `mlx-speech`
• —More examples: AppAutomaton

License

Apache 2.0 — following the upstream license published with `OpenMOSS-Team/MOSS-Audio-Tokenizer`.