kokoro-onnx and kokoro-tts
The ONNX runtime implementation provides the optimized inference backend that the CLI tool uses to achieve multi-language TTS with voice blending across different input formats.
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-tts
nazdridoy/kokoro-tts
A CLI text-to-speech tool using the Kokoro model, supporting multiple languages, voices (with blending), and various input formats including EPUB books and PDF documents.
Builds on ONNX Runtime for efficient inference and leverages chunk-based processing with configurable speech speed and format output (WAV/MP3). The tool integrates stdin piping for workflow composition and intelligently extracts chapter structure from EPUB/PDF files, enabling organized batch processing of long-form content with optional per-chapter audio splitting.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work