ebook2audiobook and alexandria-audiobook

These are **competitors**: both convert e-books to audiobooks with voice cloning and multi-language support, but ebook2audiobook prioritizes simplicity and broad language coverage while alexandria-audiobook offers advanced features like per-line style control and LoRA training for users requiring fine-grained audio customization.

ebook2audiobook
84
Verified
alexandria-audiobook
50
Established
Maintenance 25/25
Adoption 15/25
Maturity 25/25
Community 19/25
Maintenance 13/25
Adoption 10/25
Maturity 11/25
Community 16/25
Stars: 18,503
Forks: 1,514
Downloads: 228
Commits (30d): 1139
Language: Python
License: Apache-2.0
Stars: 371
Forks: 37
Downloads:
Commits (30d): 0
Language: Python
License: MIT
No risk flags
No Package No Dependents

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 alexandria-audiobook

Finrandojin/alexandria-audiobook

AI-powered multi-voice audiobook generator — LLM script annotation, voice cloning, voice design, LoRA training, per-line style control, and export to MP3, chaptered M4B, or Audacity multi-track. Built on Qwen3-TTS.

Integrates with any OpenAI-compatible LLM API (LM Studio, Ollama, OpenAI) for automatic script annotation, runs Qwen3-TTS locally with optional batch compilation via `torch.compile`, and exports to MP3, chaptered M4B, or Audacity multi-track with per-speaker WAV separation. Features a browser-based editor with selective chunk regeneration, LoRA voice fine-tuning, and context-aware smart chunking (up to 500 chars per speaker, preserving character roster across segments).

Scores updated daily from GitHub, PyPI, and npm data. How scores work