kokoro-onnx

TTS with onnx runtime based on Kokoro-TTS

Features

• Support English, French, Japanse, Korean, and Chinese
• 4X Faster than realtime (macOS M1)
• Support multiple voices including whispering

Setup

pip install -U kokoro-onnx

• You also need to place the files kokoro-v0_19.onnx, and voices.json in the project folder.
• We recommend use uv for Python.
• Python 3.12 is recommended. (uv init -p 3.12)
• Please see examples.

Instructions

1. Install uv 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.

1. Create new project folder (you name it)
2. Prepare the environment and run in the project folder

uv init -p 3.12
uv add kokoro-onnx soundfile

4. Paste the contents of examples/save.py in hello.py
5. Downloads the files kokoro-v0_19.onnx, and voices.json and place them in the same directory.
6. Run

uv run hello.py

You can edit the text in hello.py

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

Examples

See examples

Voices

Available voices are af, af_bella, af_nicole, af_sarah, af_sky, am_adam, am_michael, bf_emma, bf_isabella, bm_george, bm_lewis

kokoro-onnx.mp4