kokoro-onnx and StreamingKokoroJS
The ONNX runtime implementation provides the core TTS engine that the browser-based streaming client leverages to deliver local text-to-speech synthesis in JavaScript environments, making them complementary tools within the same ecosystem.
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 StreamingKokoroJS
sai9640nayak/StreamingKokoroJS
Unlimited text-to-speech in the Browser using Kokoro-JS, 100% local, 100% open source
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work