README.md

---
license: apache-2.0
base_model: Audio8/Audio8-TTS-Preview-0.6b
pipeline_tag: text-to-speech
language: [yue, zh, en, ja, ko, fr, de, es, it, nl, pl]
tags: [mlx, apple-silicon, tts, 8-bit, voice-cloning, streaming, arktts]
library_name: mlx
---

# Audio8-TTS-MLX-8bit

Native MLX 8-bit release of
[Audio8/Audio8-TTS-Preview-0.6b](https://huggingface.co/Audio8/Audio8-TTS-Preview-0.6b)
for Apple Silicon.

Inference code, installation, API documentation, tests, and benchmark evidence:
[vanch007/mlx-audio8-tts](https://github.com/vanch007/mlx-audio8-tts).

## Artifact

- Affine 8-bit, group size 64, `sensitive-bf16` policy.
- 827 MiB language-model weights; 2.08 GiB complete repository download.
- The shared 1.26 GiB neural codec, embeddings, and Fast AR depth decoder are
  kept at higher precision to protect speech quality.
- 44,100 Hz output, 10 acoustic codebooks.

## M3 Max benchmark

Seeded post-warm-up RTF on the release checkpoint: 0.983 English, 0.922
Chinese, and 0.793 Cantonese. Model download, loading, and warm-up are
excluded. Lower is better; values below 1.0 are faster than real-time. The
[reproducible script and report](https://github.com/vanch007/mlx-audio8-tts/tree/main/reports/evaluation/8bit-release)
are published with the source project.

## Usage

```bash
git clone https://github.com/vanch007/mlx-audio8-tts.git
cd mlx-audio8-tts
pip install -e '.[server]'

mlx-audio8-tts generate \
  --model vanch007/Audio8-TTS-MLX-8bit \
  --text "你好，欢迎使用 MLX Audio8 TTS。" \
  --output output.wav
```

This is an independent Apache-2.0 MLX conversion. See the
[upstream project](https://github.com/Audio8-AI/Audio8_TTS) for the original
architecture and checkpoint.