kokoro-onnx and kokorodoki
The ONNX runtime implementation provides the core inference engine that the real-time TTS application uses as its underlying synthesis backend.
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 kokorodoki
eel-brah/kokorodoki
Natural-sounding Text-to-Speech App that fits anywhere. Fast, Real-Time and flexible.
Built on the lightweight Kokoro-82M model, it supports 8 languages and 54+ voices with optional CUDA GPU acceleration for low-latency synthesis. Four operational modes—Console, GUI, Daemon, and CLI—enable diverse integration patterns, including clipboard monitoring in Daemon mode and SRT subtitle synchronization for timed audio generation.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work