---
title: Irodori-TTS-500M-v2-VoiceDesign-4bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/Irodori-TTS-500M-v2-VoiceDesign-4bit"
md_url: "https://www.modelscope.cn/models/mlx-community/Irodori-TTS-500M-v2-VoiceDesign-4bit.md"
repository: mlx-community/Irodori-TTS-500M-v2-VoiceDesign-4bit
last_updated: 2026-04-20
license: mit
pipeline_tag: text-to-speech
tasks:
  - text-to-speech
model_type:
  - irodori_tts
parameters: 332.7M
tensor_type:
  - F32
  - F16
  - U32
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - ja
downloads: 18
stars: 0
tags:
  - speech
  - tts
  - voice-design
  - mlx
  - mlx-audio
---

# Irodori-TTS-500M-v2-VoiceDesign-4bit

> Irodori-TTS-500M-v2-VoiceDesign-4bit - mlx-community 在 ModelScope 开源的模型。mlx-community/Irodori-TTS-500M-v2-VoiceDesign-4bit

mlx-community/Irodori-TTS-500M-v2-VoiceDesign-4bit 是 ModelScope 魔搭社区上的 332.7M 参数text-to-speech模型，采用 mit 许可。

- **Repository**: mlx-community/Irodori-TTS-500M-v2-VoiceDesign-4bit
- **License**: mit
- **Tasks**: text-to-speech
- **Parameters**: 332.7M
- **Tags**: speech, tts, voice-design, mlx, mlx-audio
- **Downloads**: 18
- **Stars**: 0
- **Last updated**: 2026-04-20

Source: https://www.modelscope.cn/models/mlx-community/Irodori-TTS-500M-v2-VoiceDesign-4bit

---

# mlx-community/Irodori-TTS-500M-v2-VoiceDesign-4bit

This model was converted to MLX format from [`Aratako/Irodori-TTS-500M-v2-VoiceDesign`](https://huggingface.co/Aratako/Irodori-TTS-500M-v2-VoiceDesign) using mlx-audio version **0.4.3**.

Refer to the [original model card](https://huggingface.co/Aratako/Irodori-TTS-500M-v2-VoiceDesign) for more details on the model.

The VoiceDesign variant generates speech conditioned on a text description of the desired voice instead of a reference audio clip.

## 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-v2-VoiceDesign-4bit \
  --text "こんにちは、テストです。" \
  --instruct "穏やかで落ち着いた女性の声。ゆっくりと話す。"
```

### Python Example

```python
from mlx_audio.tts.generate import generate_audio

generate_audio(
    model="mlx-community/Irodori-TTS-500M-v2-VoiceDesign-4bit",
    text="こんにちは、テストです。",
    instruct="穏やかで落ち着いた女性の声。ゆっくりと話す。",
    file_prefix="output",
)
```