---
title: csm-1b
canonical_url: "https://www.modelscope.cn/models/mlx-community/csm-1b"
md_url: "https://www.modelscope.cn/models/mlx-community/csm-1b.md"
repository: mlx-community/csm-1b
last_updated: 2025-03-23
license: apache-2.0
pipeline_tag: text-to-speech
tasks:
  - text-to-speech
model_type:
  - sesame
base_model:
  - sesame/csm-1b
base_model_relation: finetune
parameters: 1.6B
tensor_type:
  - F32
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
downloads: 533
stars: 0
---

# csm-1b

> csm-1b - mlx-community 在 ModelScope 开源的模型。mlx-community/csm-1b This model was converted to MLX format from sesame/csm-1b using mlx-audio version 0.0.3. Refer to the original model card for more details on the model. Use with mlx

mlx-community/csm-1b 是 ModelScope 魔搭社区上的 1.6B 参数text-to-speech模型，采用 apache-2.0 许可，基于 sesame/csm-1b 构建。

- **Repository**: mlx-community/csm-1b
- **License**: apache-2.0
- **Tasks**: text-to-speech
- **Parameters**: 1.6B
- **Base model**: sesame/csm-1b
- **Downloads**: 533
- **Stars**: 0
- **Last updated**: 2025-03-23

Source: https://www.modelscope.cn/models/mlx-community/csm-1b

---

# mlx-community/csm-1b
This model was converted to MLX format from [`sesame/csm-1b`]() using mlx-audio version **0.0.3**.
Refer to the [original model card](https://huggingface.co/sesame/csm-1b) for more details on the model.
## Use with mlx

```bash
pip install -U mlx-audio
```

```bash
python -m mlx_audio.tts.generate --model mlx-community/csm-1b --text "Hello world"
```