---
title: Irodori-TTS-500M-4bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/Irodori-TTS-500M-4bit"
md_url: "https://www.modelscope.cn/models/mlx-community/Irodori-TTS-500M-4bit.md"
repository: mlx-community/Irodori-TTS-500M-4bit
last_updated: 2026-03-22
license: mit
pipeline_tag: text-to-speech
tasks:
  - text-to-speech
model_type:
  - irodori_tts
parameters: 141.3M
tensor_type:
  - F16
  - U32
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - ja
downloads: 8
stars: 0
tags:
  - speech
  - voice
  - tts
  - mlx
  - text-to-speech
  - "speech generation"
  - "voice cloning"
  - mlx-audio
---

# Irodori-TTS-500M-4bit

> Irodori-TTS-500M-4bit - mlx-community 在 ModelScope 开源的模型。mlx-community/Irodori-TTS-500M-4bit

mlx-community/Irodori-TTS-500M-4bit 是 ModelScope 魔搭社区上的 141.3M 参数text-to-speech模型，采用 mit 许可。

- **Repository**: mlx-community/Irodori-TTS-500M-4bit
- **License**: mit
- **Tasks**: text-to-speech
- **Parameters**: 141.3M
- **Tags**: speech, voice, tts, mlx, text-to-speech, speech generation, voice cloning, mlx-audio
- **Downloads**: 8
- **Stars**: 0
- **Last updated**: 2026-03-22

Source: https://www.modelscope.cn/models/mlx-community/Irodori-TTS-500M-4bit

---

# mlx-community/Irodori-TTS-500M-4bit

This model was converted to MLX format from [`Aratako/Irodori-TTS-500M`](https://huggingface.co/Aratako/Irodori-TTS-500M) using mlx-audio version **0.4.1**.

Refer to the [original model card](https://huggingface.co/Aratako/Irodori-TTS-500M) 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/Irodori-TTS-500M-4bit --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/Irodori-TTS-500M-4bit")
generate_audio(
    model=model,
    text="Hello, this is a test.",
    ref_audio="path_to_audio.wav",
    file_prefix="test_audio",
)

```