---
title: Dia-1.6B-fp16
canonical_url: "https://www.modelscope.cn/models/mlx-community/Dia-1.6B-fp16"
md_url: "https://www.modelscope.cn/models/mlx-community/Dia-1.6B-fp16.md"
repository: mlx-community/Dia-1.6B-fp16
last_updated: 2025-04-28
license: apache-2.0
pipeline_tag: text-to-speech
tasks:
  - text-to-speech
base_model:
  - nari-labs/Dia-1.6B
base_model_relation: finetune
parameters: 1.6B
tensor_type:
  - F16
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
downloads: 657
stars: 0
---

# Dia-1.6B-fp16

> Dia-1.6B-fp16 - mlx-community 在 ModelScope 开源的模型。mlx-community/Dia-1.6B-fp16 This model was converted to MLX format from nari-labs/Dia-1.6B using mlx-audio version 0.1.0. Refer to the original model card for more details on the model. Use with mlx

mlx-community/Dia-1.6B-fp16 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 nari-labs/Dia-1.6B 构建。

- **Repository**: mlx-community/Dia-1.6B-fp16
- **License**: apache-2.0
- **Tasks**: text-to-speech
- **Parameters**: 1.6B
- **Base model**: nari-labs/Dia-1.6B
- **Downloads**: 657
- **Stars**: 0
- **Last updated**: 2025-04-28

Source: https://www.modelscope.cn/models/mlx-community/Dia-1.6B-fp16

---

# mlx-community/Dia-1.6B-fp16
This model was converted to MLX format from [`nari-labs/Dia-1.6B`]() using mlx-audio version **0.1.0**.
Refer to the [original model card](https://huggingface.co/nari-labs/Dia-1.6B) 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/Dia-1.6B-fp16 \
--text "[S1] Dia is an open weights text to dialogue model. [S2] You get full control over scripts and voices. [S1] Wow. Amazing. (laughs) [S2] Try it now on Git hub or Hugging Face."
```