kokoro-onnx and kokoro-tts-addon
The ONNX runtime implementation provides the optimized inference engine that the browser addon wraps as a client-side interface, making them complements within a modular TTS pipeline rather than competitors.
About kokoro-onnx
thewh1teagle/kokoro-onnx
TTS with kokoro and onnx runtime
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.
About kokoro-tts-addon
pinguy/kokoro-tts-addon
Local neural TTS for Browsers: fast, expressive, and offline—runs on modest hardware.
Implements a Flask-based local server paired with the 82M-parameter Kokoro model, enabling multi-voice synthesis with support for nine languages and accents through a Firefox extension popup. The architecture separates the inference backend from the browser frontend via HTTP, supporting both CPU and GPU acceleration while maintaining real-time performance even on legacy hardware like 2013 Xeons.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work