---
title: stable-audio-3-small-sfx
canonical_url: "https://www.modelscope.cn/models/mlx-community/stable-audio-3-small-sfx"
md_url: "https://www.modelscope.cn/models/mlx-community/stable-audio-3-small-sfx.md"
repository: mlx-community/stable-audio-3-small-sfx
last_updated: 2026-05-26
license: other
model_type:
  - stable_audio_3
base_model:
  - stabilityai/stable-audio-3-small-sfx-base
base_model_relation: finetune
parameters: 567.6M
tensor_type:
  - F32
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
downloads: 67
stars: 0
tags:
  - audio-generation
  - sound-effects
  - diffusion
  - mlx
  - text-to-speech
  - speech
  - "speech generation"
  - "voice cloning"
  - tts
  - mlx-audio
---

# stable-audio-3-small-sfx

> stable-audio-3-small-sfx - mlx-community 在 ModelScope 开源的模型。mlx-community/stable-audio-3-small-sfx

mlx-community/stable-audio-3-small-sfx 是 ModelScope 魔搭社区上的 567.6M 参数机器学习模型，采用 other 许可，基于 stabilityai/stable-audio-3-small-sfx-base 构建。

- **Repository**: mlx-community/stable-audio-3-small-sfx
- **License**: other
- **Parameters**: 567.6M
- **Base model**: stabilityai/stable-audio-3-small-sfx-base
- **Tags**: audio-generation, sound-effects, diffusion, mlx, text-to-speech, speech, speech generation, voice cloning, tts, mlx-audio
- **Downloads**: 67
- **Stars**: 0
- **Last updated**: 2026-05-26

Source: https://www.modelscope.cn/models/mlx-community/stable-audio-3-small-sfx

---

# mlx-community/stable-audio-3-small-sfx

This model was converted to MLX format from [`stabilityai/stable-audio-3-small-sfx`](https://huggingface.co/stabilityai/stable-audio-3-small-sfx) using mlx-audio version **0.4.3**.

Refer to the [original model card](https://huggingface.co/stabilityai/stable-audio-3-small-sfx) 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 mlx-community/stable-audio-3-small-sfx --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("mlx-community/stable-audio-3-small-sfx")
generate_audio(
    model=model,
    text="Hello, this is a test.",
    ref_audio="path_to_audio.wav",
    file_prefix="test_audio",
)

```