kokoro-onnx and Kokoro-82M-Android
An optimized inference runtime implementation and a minimal mobile demonstration app are ecosystem siblings that serve different deployment targets—the former provides the core ONNX-based TTS engine while the latter showcases its application on Android devices.
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-82M-Android
puff-dayo/Kokoro-82M-Android
A minimal Android demo app for Kokoro-TTS
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work