---
library_name: mlx-audio
language:
- en
- fr
- es
- pt
- it
- nl
- de
- ar
- hi
license: cc-by-nc-4.0
inference: false
base_model:
- mistralai/Ministral-3-3B-Base-2512
extra_gated_description: If you want to learn more about how we process your personal
  data, please read our <a href="https://mistral.ai/terms/">Privacy Policy</a>.
tags:
- mistral-common
- mlx
- text-to-speech
- speech
- speech generation
- voice cloning
- tts
- mlx-audio
pipeline_tag: text-to-speech
---
# AITRADER/Voxtral-4B-TTS-2603-mxfp8

This model was converted to MLX format from [`mistralai/Voxtral-4B-TTS-2603`](https://huggingface.co/mistralai/Voxtral-4B-TTS-2603) using mlx-audio version **0.4.1**.

Refer to the [original model card](https://huggingface.co/mistralai/Voxtral-4B-TTS-2603) for more details on the model.

## Use with mlx-audio

```bash
pip install -U mlx-audio
```

### CLI Example:
```bash
python -m mlx_audio.tts.generate --model AITRADER/Voxtral-4B-TTS-2603-mxfp8 --text "Hello, this is a test."
```

### Python Example:
```python        
from mlx_audio.tts.utils import load_model
from mlx_audio.tts.generate import generate_audio

model = load_model("AITRADER/Voxtral-4B-TTS-2603-mxfp8")
generate_audio(
    model=model,
    text="Hello, this is a test.",
    ref_audio="path_to_audio.wav",
    file_prefix="test_audio",
)

```