ebook2audiobook and runandread-audiobook
These are competitors—both are standalone ebook-to-audiobook converters that use TTS engines (voice cloning vs. model selection) to achieve the same end result, requiring users to choose between them rather than use them together.
About ebook2audiobook
DrewThomasson/ebook2audiobook
Generate audiobooks from e-books, voice cloning & 1158+ languages!
Leverages multiple TTS engines (XTTSv2, Bark, VITS, Tacotron2, etc.) with automatic chapter detection and metadata preservation, supporting SML tags for granular control over pauses and voice switching. Handles 20+ e-book formats including EPUB, PDF, and MOBI, with optional OCR for image-based text, and outputs to standard audiobook containers (M4B, MP3, FLAC, WAV). Deployable locally, via Docker, or remotely through Hugging Face Spaces and Google Colab with a Gradio web interface.
About runandread-audiobook
sergenes/runandread-audiobook
🚀 Open-source project for creating high-quality AI TTS-narrated audiobooks at home using models like Zonos, Kokoro-82M, or services like Deepgram and Eleven Labs. Tested on Apple Silicon M1 (32GB RAM). 📖🎧
# Technical Summary Implements an end-to-end pipeline that converts EPUB files to structured JSON, synthesizes audio using local models (Zonos, Kokoro via MLX) or cloud APIs (Deepgram, OpenAI), and supports voice cloning from MP3 samples before packaging into a RANDR ZIP format for the Run & Read mobile app. Features resumable batch processing (tolerates interruption), ffmpeg-based audio merging, and CLI playback with synchronized text display. Targets cross-platform deployment (macOS/Linux/Windows) with optimized inference on Apple Silicon via MLX framework.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work