kokoro-onnx and KokoroSharp
These are ecosystem siblings serving different platforms: the first is a Python-based ONNX inference implementation, while the second is a C#/.NET wrapper that enables the same Kokoro TTS model to be used in .NET applications.
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 KokoroSharp
Lyrcaxis/KokoroSharp
Fast local TTS inference engine in C# with ONNX runtime. Multi-speaker, multi-platform and multilingual. Integrate on your .NET projects using a plug-and-play NuGet package, complete with all voices.
Leverages the Kokoro 82M model with integrated eSpeak NG phonemization for automatic language detection across nine languages, and supports voice mixing with arbitrary speaker combinations. Features text-segment streaming for low-latency synthesis, linear job scheduling with background worker dispatch, and optional cross-platform audio playback with thread-safe queue handling. Supports both CPU and GPU inference via ONNX, with model auto-download (~320MB) and customizable phoneme input for platforms requiring external phonemization solutions.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work