---
title: Soprano-80M-bf16
canonical_url: "https://www.modelscope.cn/models/mlx-community/Soprano-80M-bf16"
md_url: "https://www.modelscope.cn/models/mlx-community/Soprano-80M-bf16.md"
repository: mlx-community/Soprano-80M-bf16
last_updated: 2026-01-04
license: apache-2.0
pipeline_tag: text-to-speech
tasks:
  - text-to-speech
model_type:
  - soprano
architectures:
  - SopranoForCausalLM
parameters: 94.2M
tensor_type:
  - BF16
  - F32
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
downloads: 37
stars: 0
tags:
  - mlx
  - text-to-speech
  - speech
  - "speech generation"
  - "voice cloning"
  - tts
---

# Soprano-80M-bf16

> Soprano-80M-bf16 - mlx-community 在 ModelScope 开源的模型。mlx-community/Soprano-80M-bf16 This model was converted to MLX format from ekwek/Soprano-80M using mlx-audio version 0.2.10. Refer to the original model card for more details on the model.

mlx-community/Soprano-80M-bf16 是 ModelScope 魔搭社区上的 94.2M 参数text-to-speech模型，采用 apache-2.0 许可。

- **Repository**: mlx-community/Soprano-80M-bf16
- **License**: apache-2.0
- **Tasks**: text-to-speech
- **Parameters**: 94.2M
- **Tags**: mlx, text-to-speech, speech, speech generation, voice cloning, tts
- **Downloads**: 37
- **Stars**: 0
- **Last updated**: 2026-01-04

Source: https://www.modelscope.cn/models/mlx-community/Soprano-80M-bf16

---

# mlx-community/Soprano-80M-bf16
This model was converted to MLX format from [`ekwek/Soprano-80M`](https://huggingface.co/ekwek/Soprano-80M) using mlx-audio version **0.2.10**.
Refer to the [original model card](https://huggingface.co/ekwek/Soprano-80M) 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/Soprano-80M-bf16 --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/Soprano-80M-bf16")
    generate_audio(
        model=model, text="Hello, this is a test.",
        file_prefix="test_audio",
    )

```