---
title: parler-tts-mini
canonical_url: "https://www.modelscope.cn/models/mlx-community/parler-tts-mini"
md_url: "https://www.modelscope.cn/models/mlx-community/parler-tts-mini.md"
repository: mlx-community/parler-tts-mini
last_updated: 2026-04-05
license: apache-2.0
pipeline_tag: text-to-speech
tasks:
  - text-to-speech
model_type:
  - parler
architectures:
  - ParlerTTSForConditionalGeneration
parameters: 955.6M
tensor_type:
  - F32
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
  - fr
  - es
  - pt
  - pl
  - de
  - nl
  - it
downloads: 34
stars: 1
tags:
  - text-to-speech
  - annotation
  - mlx
  - speech
  - "speech generation"
  - "voice cloning"
  - tts
  - mlx-audio
---

# parler-tts-mini

> parler-tts-mini - mlx-community 在 ModelScope 开源的模型。mlx-community/parler-tts-mini

mlx-community/parler-tts-mini 是 ModelScope 魔搭社区上的 955.6M 参数text-to-speech模型，采用 apache-2.0 许可。

- **Repository**: mlx-community/parler-tts-mini
- **License**: apache-2.0
- **Tasks**: text-to-speech
- **Parameters**: 955.6M
- **Tags**: text-to-speech, annotation, mlx, speech, speech generation, voice cloning, tts, mlx-audio
- **Downloads**: 34
- **Stars**: 1
- **Last updated**: 2026-04-05

Source: https://www.modelscope.cn/models/mlx-community/parler-tts-mini

---

# mlx-community/parler-tts-mini

This model was converted to MLX format from [`parler-tts/parler-tts-mini-multilingual-v1.1`](https://huggingface.co/parler-tts/parler-tts-mini-multilingual-v1.1) using mlx-audio version **0.2.8**.

Refer to the [original model card](https://huggingface.co/parler-tts/parler-tts-mini-multilingual-v1.1) 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/parler-tts-mini --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/parler-tts-mini")
generate_audio(
    model=model,
    text="Hello, this is a test.",
    ref_audio="path_to_audio.wav",
    file_prefix="test_audio",
)

```