---
license: apache-2.0
base_model: bosonai/higgs-audio-v2-generation-3B-base
library_name: mlx-audio
tags:
  - text-to-speech
  - voice-cloning
  - mlx
  - higgs-audio
language:
  - en
  - zh
  - ko
  - de
  - es
---

# Higgs Audio v2 — MLX 8-bit

MLX port of [`bosonai/higgs-audio-v2-generation-3B-base`](https://huggingface.co/bosonai/higgs-audio-v2-generation-3B-base) quantized to 8-bit. 3B Llama-3.2-backed text-to-speech with multi-codebook acoustic tokens and delay-pattern streaming. Real-time voice cloning on Apple Silicon.

## Install

Requires the Higgs Audio v2 code from [`Blaizzy/mlx-audio`](https://github.com/Blaizzy/mlx-audio) (pending upstream merge — currently on the `higgs-audio-v2-port` branch at [`kaioct-labs/mlx-audio`](https://github.com/kaioct-labs/mlx-audio/tree/higgs-audio-v2-port)).

## Usage

```python
from mlx_audio.tts.models.higgs_audio import HiggsAudioServer
import soundfile as sf

server = HiggsAudioServer.from_pretrained(
    model_path="mlx-community/higgs-audio-v2-3B-mlx-q8",
    codec_path="mlx-community/higgs-audio-v2-tokenizer",
)

result = server.generate(
    target_text="Hello from Higgs Audio on MLX.",
    reference_audio_path="reference.wav",
    reference_text="Transcript of the reference audio.",
)
sf.write("output.wav", result.pcm, result.sampling_rate)
```

## Benchmark (M5 Max, warm, long-prompt)

| variant | RTF   | size    |
|---------|-------|---------|
| bf16    | 0.60× | 6.8 GB  |
| q8      | 0.36× | 6.18 GB |
| q6      | 0.33× | 4.75 GB |

## Quantization

Selective — Llama backbone and text head at 8-bit, `audio_codebook_embeddings` and `audio_decoder_proj.audio_lm_head` kept at bf16 to preserve voice character. Config in `config.json` → `quantization` block, automatically honored by `HiggsAudioServer.from_pretrained`.

## License

Apache-2.0 (inherits from base model).