---
title: Soprano-1.1-80M-5bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/Soprano-1.1-80M-5bit"
md_url: "https://www.modelscope.cn/models/mlx-community/Soprano-1.1-80M-5bit.md"
repository: mlx-community/Soprano-1.1-80M-5bit
last_updated: 2026-02-05
pipeline_tag: text-to-speech
tasks:
  - text-to-speech
model_type:
  - soprano
architectures:
  - Qwen3ForCausalLM
base_model:
  - ekwek/Soprano-1.1-80M
base_model_relation: quantized
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
inference_backends:
  - "deploy_task text/emb"
  - "lmdeploy_turbomind 0.9.1"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 14
stars: 0
tags:
  - mlx
  - text-to-speech
  - speech
  - tts
  - "speech generation"
  - "voice cloning"
  - mlx-audio
---

# Soprano-1.1-80M-5bit

> Soprano-1.1-80M-5bit - mlx-community 在 ModelScope 开源的模型。mlx-community/Soprano-1.1-80M-5bit

mlx-community/Soprano-1.1-80M-5bit 是 ModelScope 魔搭社区上的text-to-speech模型，基于 ekwek/Soprano-1.1-80M 构建，可用 deploy_task text/emb、lmdeploy_turbomind 0.9.1、sglang 0.5.2 部署。

- **Repository**: mlx-community/Soprano-1.1-80M-5bit
- **Tasks**: text-to-speech
- **Base model**: ekwek/Soprano-1.1-80M
- **Inference backends**: deploy_task text/emb, lmdeploy_turbomind 0.9.1, sglang 0.5.2, vllm 0.9.2
- **Tags**: mlx, text-to-speech, speech, tts, speech generation, voice cloning, mlx-audio
- **Downloads**: 14
- **Stars**: 0
- **Last updated**: 2026-02-05

Source: https://www.modelscope.cn/models/mlx-community/Soprano-1.1-80M-5bit

---

# mlx-community/Soprano-1.1-80M-5bit

This model was converted to MLX format from [`mlx-community/Soprano-1.1-80M-bf16`](https://huggingface.co/mlx-community/Soprano-1.1-80M-bf16) using mlx-audio version **0.3.1**.

Refer to the [original model card](https://huggingface.co/mlx-community/Soprano-1.1-80M-bf16) 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-5bit --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-5bit")
generate_audio(
    model=model,
    text="Hello, this is a test.",
    ref_audio="path_to_audio.wav",
    file_prefix="test_audio",
)

```