---
title: kanitts-2
canonical_url: "https://www.modelscope.cn/models/mlx-community/kanitts-2"
md_url: "https://www.modelscope.cn/models/mlx-community/kanitts-2.md"
repository: mlx-community/kanitts-2
last_updated: 2026-04-05
license: other
pipeline_tag: text-to-speech
tasks:
  - text-to-speech
model_type:
  - kanitts
architectures:
  - Lfm2ForCausalLM
base_model:
  - nineninesix/kani-tts-400m-0.3-pt
base_model_relation: finetune
parameters: 474.0M
tensor_type:
  - F32
  - BF16
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
downloads: 9
stars: 0
tags:
  - mlx
  - text-to-speech
  - speech
  - "speech generation"
  - "voice cloning"
  - tts
  - mlx-audio
---

# kanitts-2

> kanitts-2 - mlx-community 在 ModelScope 开源的模型。mlx-community/kanitts-2

mlx-community/kanitts-2 是 ModelScope 魔搭社区上的 474.0M 参数text-to-speech模型，采用 other 许可，基于 nineninesix/kani-tts-400m-0.3-pt 构建。

- **Repository**: mlx-community/kanitts-2
- **License**: other
- **Tasks**: text-to-speech
- **Parameters**: 474.0M
- **Base model**: nineninesix/kani-tts-400m-0.3-pt
- **Tags**: mlx, text-to-speech, speech, speech generation, voice cloning, tts, mlx-audio
- **Downloads**: 9
- **Stars**: 0
- **Last updated**: 2026-04-05

Source: https://www.modelscope.cn/models/mlx-community/kanitts-2

---

# mlx-community/kanitts-2

This model was converted to MLX format from [`nineninesix/kani-tts-400m-en`](https://huggingface.co/nineninesix/kani-tts-400m-en) using mlx-audio version **0.2.8**.

Refer to the [original model card](https://huggingface.co/nineninesix/kani-tts-400m-en) 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/kanitts-2 --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/kanitts-2")
generate_audio(
    model=model,
    text="Hello, this is a test.",
    ref_audio="path_to_audio.wav",
    file_prefix="test_audio",
)

```