https://github.com/thewh1teagle/kokoro-onnx

TTS with kokoro and onnx runtime
https://github.com/thewh1teagle/kokoro-onnx

kokoro onnxruntime python tts

Last synced: 22 days ago
JSON representation

TTS with kokoro and onnx runtime

• Host: GitHub
• URL: https://github.com/thewh1teagle/kokoro-onnx
• Owner: thewh1teagle
• License: mit
• Created: 2025-01-03T14:59:41.000Z (4 months ago)
• Default Branch: main
• Last Pushed: 2025-04-05T21:37:01.000Z (29 days ago)
• Last Synced: 2025-04-05T22:24:46.861Z (29 days ago)
• Topics: kokoro, onnxruntime, python, tts
• Language: Python
• Homepage: https://pypi.org/project/kokoro-onnx
• Size: 497 KB
• Stars: 1,850
• Watchers: 14
• Forks: 176
• Open Issues: 61
• Metadata Files:
  • Readme: README.md
  • Funding: .github/FUNDING.yml
  • License: LICENSE

Awesome Lists containing this project

• StarryDivineSky - thewh1teagle/kokoro-onnx - onnx项目是一个使用kokoro模型和ONNX Runtime进行文本到语音转换（TTS）的项目。它允许用户利用kokoro模型生成语音，并利用ONNX Runtime加速推理过程。该项目的主要特色在于结合了kokoro模型的高质量语音合成能力和ONNX Runtime的高效执行效率。项目的工作原理是首先将文本输入kokoro模型，模型输出语音特征，然后这些特征被传递给声码器，最终生成语音。用户可以通过该项目体验快速且高质量的TTS服务。项目可能包含模型转换、推理代码和相关配置文件等。 (语音合成 / 资源传输下载)

README

        
# kokoro-onnx

![Python Version](https://img.shields.io/badge/python-3.10%20%7C%203.11%20%7C%203.12%20%7C%203.13-blue)

[![PyPI Release](https://img.shields.io/pypi/v/kokoro-onnx.svg)](https://pypi.org/project/kokoro-onnx/)

[![Github Model Releases](https://img.shields.io/github/v/release/thewh1teagle/kokoro-onnx)](https://github.com/thewh1teagle/kokoro-onnx/releases)

[![License](https://img.shields.io/github/license/thewh1teagle/kokoro-onnx)](https://github.com/thewh1teagle/kokoro-onnx/blob/main/LICENSE)

[![GitHub stars](https://img.shields.io/github/stars/thewh1teagle/kokoro-onnx?style=social)](https://github.com/thewh1teagle/kokoro-onnx/stargazers)

[![PyPI Downloads](https://img.shields.io/pypi/dm/kokoro-onnx?style=plastic)](https://pypi.org/project/kokoro-onnx/)

[![ONNX Runtime](https://img.shields.io/badge/ONNX%20Runtime-%E2%89%A51.20.1-blue)](https://github.com/microsoft/onnxruntime)

![CPU](https://img.shields.io/badge/CPU-supported-brightgreen)

![GPU](https://img.shields.io/badge/GPU-supported-brightgreen)

TTS with onnx runtime based on [Kokoro-TTS](https://huggingface.co/spaces/hexgrad/Kokoro-TTS)

🚀 Version 1.0 models are out now! 🎉

## Features

- Supports multiple languages

- Fast performance near real-time on macOS M1

- Offer multiple voices

- Lightweight: ~300MB (quantized: ~80MB)

## Setup

```console

pip install -U kokoro-onnx

```

Instructions

1. Install [uv](https://docs.astral.sh/uv/getting-started/installation) for isolated Python (Recommend).

Basically open the terminal (PowerShell / Bash) and run the command listed in their website.

_Note: you don't have to use `uv`. but it just make things much simpler. You can use regular Python as well._

2. Create new project folder (you name it)

3. Run in the project folder

```console

uv init -p 3.12

uv add kokoro-onnx soundfile

```

4. Paste the contents of [`examples/save.py`](https://github.com/thewh1teagle/kokoro-onnx/blob/main/examples/save.py) in `hello.py`

5. Download the files [`kokoro-v1.0.onnx`](https://github.com/thewh1teagle/kokoro-onnx/releases/download/model-files-v1.0/kokoro-v1.0.onnx), and [`voices-v1.0.bin`](https://github.com/thewh1teagle/kokoro-onnx/releases/download/model-files-v1.0/voices-v1.0.bin) and place them in the same directory.

6. Run

```console

uv run hello.py

```

You can edit the text in `hello.py`

That's it! `audio.wav` should be created.

## Examples

See [examples](examples)

## Voices

See the latest voices and languages in [Kokoro-82M/VOICES.md](https://huggingface.co/hexgrad/Kokoro-82M/blob/main/VOICES.md)

Note: It's recommend to use misaki g2p package from v1.0, see [examples](examples)

## Contribute

See [CONTRIBUTE.md](CONTRIBUTE.md)

## License

- kokoro-onnx: MIT

- kokoro model: Apache 2.0