thewh1teagle/kokoro-onnx

TTS with kokoro and onnx runtime

70
/ 100
Verified

Leverages ONNX Runtime for CPU and GPU-accelerated inference with quantized models as small as 80MB, enabling near real-time synthesis on resource-constrained devices like M1 Macs. Supports 82+ voices across multiple languages with optional grapheme-to-phoneme conversion via the misaki package for improved pronunciation accuracy. Provides a lightweight, self-contained alternative to larger TTS systems while maintaining compatibility with standard audio output formats.

2,419 stars and 169,357 monthly downloads. Used by 2 other packages. Available on PyPI.

Maintenance 10 / 25
Adoption 22 / 25
Maturity 18 / 25
Community 20 / 25

How are scores calculated?

Stars

2,419

Forks

252

Language

Python

License

MIT

Last pushed

Jan 30, 2026

Monthly downloads

169,357

Commits (30d)

0

Dependencies

4

Reverse dependents

2

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/thewh1teagle/kokoro-onnx"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.