Desktop and web app that converts EPUB, PDF, text and subtitle files into audio with synced subtitles, using Kokoro-82M TTS.
- Stars
- 20,391
- Forks
- 1,740
- Open issues
- 7
- Last commit
- 16 days ago
What is it?
ebook2audiobook (E2A) turns EPUB, MOBI, PDF, and many other e-book formats into audio files, with chapter detection for formats like EPUB and MOBI. It runs a web interface through Gradio or a headless command-line mode for batch conversion of a single file or a whole folder.
The project integrates several text-to-speech engines, including XTTSv2, Bark, Fairseq, VITS, Tacotron2, Tortoise, GlowTTS, and YourTTS. Users can clone a voice from their own audio sample, load custom or fine-tuned models, and add SML tags for pauses, breaks, and voice switches. OCR is available for scanned pages.
Output can be exported as m4b, mp3, m4a, flac, wav, and other audio formats. It runs on CPU, NVIDIA CUDA, AMD ROCm, Intel XPU, Apple MPS, and Jetson, and can be launched locally, through Docker, or via hosted Colab, Kaggle, and Hugging Face notebooks.
Key features
- 01Converts many e-book formats, including EPUB, MOBI, PDF, and TXT, into audio.
- 02Supports multiple TTS engines such as XTTSv2, Bark, VITS, and Tacotron2.
- 03Optional voice cloning from a user-provided voice sample.
- 04SML tags for pauses, breaks, and switching voices within a book.
- 05Exports to m4b, mp3, m4a, flac, wav, and other formats with chapter support.
- 06Runs headless from the command line or through a Gradio web interface.
Use cases
- Turning a personal library of legally acquired e-books into audiobooks for listening on the go.
- Batch converting a folder of documents or books in headless mode on a server.
- Experimenting with different TTS engines and cloned voices for narration projects.
- Creating audio versions of text content for accessibility purposes.
Topics
FAQ
- What is ebook2audiobook?
- Converts e-books into audiobooks with chapters and metadata, using multiple TTS engines and optional voice cloning. ebook2audiobook (E2A) turns EPUB, MOBI, PDF, and many other e-book formats into audio files, with chapter detection for formats like EPUB and MOBI. It runs a web interface through Gradio or a headless command-line mode for batch conversion of a single file or a whole folder.
- Is ebook2audiobook free to use? What license does it have?
- ebook2audiobook is open source under the Apache-2.0 license. Check the license terms before using it in commercial products.
- Is ebook2audiobook still maintained?
- Actively maintained. The last commit to ebook2audiobook was on Oct 6, 2026.
- What can I use ebook2audiobook for?
- Turning a personal library of legally acquired e-books into audiobooks for listening on the go. Batch converting a folder of documents or books in headless mode on a server. Experimenting with different TTS engines and cloned voices for narration projects. Creating audio versions of text content for accessibility purposes.
- Where can I get ebook2audiobook?
- The source code and installation instructions are on GitHub: https://github.com/DrewThomasson/ebook2audiobook
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
Windows-focused Gradio web app bundling text-to-speech, voice cloning, Whisper transcription, YouTube download, vocal separation and translation for dubbing.
Open-source text-to-speech system with voice cloning, natural-language emotion control and multi-speaker generation, built on LLM-style models.
A 0.1B-parameter multilingual text-to-speech model that runs in realtime on CPU, with voice cloning and 48 kHz stereo output.
Open-source, local-first voice studio for voice cloning, voice design, video dubbing, dictation, transcription and audiobook creation in 646 languages.
VoxCPM2 is an open-source, tokenizer-free text-to-speech model supporting 30 languages, voice design from text descriptions, and voice cloning from short reference clips.