kokoro-onnx and kokoro-ruslan
These are ecosystem siblings where one provides a lightweight inference runtime (ONNX) for Kokoro TTS, while the other extends the ecosystem to support training language-specific models like Russian.
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-ruslan
igorshmukler/kokoro-ruslan
Kokoro Language Model Training Script for Russian (Ruslan Corpus)
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work