---
title: Soprano-1.1-80M-bf16
canonical_url: "https://www.modelscope.cn/models/mlx-community/Soprano-1.1-80M-bf16"
md_url: "https://www.modelscope.cn/models/mlx-community/Soprano-1.1-80M-bf16.md"
repository: mlx-community/Soprano-1.1-80M-bf16
last_updated: 2026-06-17
pipeline_tag: text-to-speech
tasks:
  - text-to-speech
model_type:
  - soprano
architectures:
  - Qwen3ForCausalLM
base_model:
  - ekwek/Soprano-1.1-80M
base_model_relation: finetune
parameters: 79.7M
tensor_type:
  - BF16
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
downloads: 17
stars: 0
tags:
  - mlx
  - text-to-speech
  - speech
  - tts
---

# Soprano-1.1-80M-bf16

> Soprano-1.1-80M-bf16 - mlx-community 在 ModelScope 开源的模型。mlx-community/Soprano-1.1-80M-bf16

mlx-community/Soprano-1.1-80M-bf16 是 ModelScope 魔搭社区上的 79.7M 参数text-to-speech模型，基于 ekwek/Soprano-1.1-80M 构建。

- **Repository**: mlx-community/Soprano-1.1-80M-bf16
- **Tasks**: text-to-speech
- **Parameters**: 79.7M
- **Base model**: ekwek/Soprano-1.1-80M
- **Tags**: mlx, text-to-speech, speech, tts
- **Downloads**: 17
- **Stars**: 0
- **Last updated**: 2026-06-17

Source: https://www.modelscope.cn/models/mlx-community/Soprano-1.1-80M-bf16

---

# mlx-community/Soprano-1.1-80M-bf16

This model was converted to MLX format from [`ekwek/Soprano-1.1-80M`](https://huggingface.co/ekwek/Soprano-1.1-80M) using mlx-audio version **0.3.1**.

Refer to the [original model card](https://huggingface.co/ekwek/Soprano-1.1-80M) 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-1.1-80M-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-1.1-80M-bf16")
generate_audio(
    model=model,
    text="Hello, this is a test.",
    ref_audio="path_to_audio.wav",
    file_prefix="test_audio",
)

```