kokoro-onnx and kokoro-coreml
These are ecosystem siblings serving different deployment targets: the ONNX version enables cross-platform CPU/GPU inference while the CoreML version optimizes for Apple Neural Engine hardware acceleration, allowing developers to choose the runtime best suited to their deployment environment.
About kokoro-onnx
thewh1teagle/kokoro-onnx
TTS with kokoro and onnx runtime
This tool helps you convert written text into natural-sounding speech. You provide text and select from various voices and languages, and it produces an audio file of that text being spoken. It's ideal for developers who need to integrate high-quality text-to-speech capabilities into their applications.
About kokoro-coreml
mattmireles/kokoro-coreml
PyTorch → CoreML conversion pipeline for Kokoro TTS. Unlocks fast on-device text-to-speech on Apple Neural Engine.
This project helps macOS app developers integrate advanced text-to-speech capabilities directly into their applications. It takes text input and converts it into natural-sounding speech audio using the Kokoro TTS model, optimized for fast, on-device processing on Apple Silicon with Neural Engine acceleration. The primary users are macOS app developers looking to embed high-quality, efficient speech synthesis.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work