audiblez and pdf-narrator
`santinic/audiblez` and `mateogon/pdf-narrator` are competitors, as both tools aim to convert ebooks (EPUBs and PDFs) into audiobooks using text-to-speech, offering similar core functionality.
About audiblez
santinic/audiblez
Generate audiobooks from e-books
Leverages the Kokoro-82M text-to-speech model (82M parameters, Apache-licensed) to synthesize natural-sounding speech across 9 languages with adjustable playback speed. Supports both CPU and CUDA GPU acceleration, with optional interactive chapter selection and a wxPython GUI, outputting standard m4b audiobook files compatible with standard players.
About pdf-narrator
mateogon/pdf-narrator
Convert your PDFs and EPUBs into audiobooks effortlessly. Features intelligent text extraction, customizable text-to-speech settings, and efficient processing for low-resource systems.
Leverages **Kokoro v1.0 TTS** with advanced phonemization and automatic chunk splitting (<510 tokens) to handle large documents while supporting multiple voicepacks. Built with **ttkbootstrap GUI**, it offers pause/resume controls, real-time voice testing across all available voices, and TOC-based chapter splitting for PDFs or HTML-structure extraction for EPUBs—all optimizable for low-VRAM systems via configurable chunk sizes and CPU fallback.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work