ebook2audiobook: Turn Your E-Book Library into Audiobooks with Voice Cloning

ebook2audiobook is a free, open-source tool that converts your e-book collection — EPUB, PDF, TXT, MOBI and more — into high-quality audiobooks using state-of-the-art text-to-speech (TTS) models. With over 19,600 GitHub stars and an Apache-2.0 license, it has become one of the most popular self-hosted audiobook generators available.

🚀 Want to deploy ebook2audiobook yourself?

Docker configs, system requirements, and installation guides — all on one page.

View ebook2audiobook Tool Page →

Why ebook2audiobook stands out

Unlike simple TTS wrappers, ebook2audiobook was built around the real needs of audiobook listeners. It splits your book into chapters, generates natural-sounding narration, and even supports voice cloning so you can listen in a voice you know. The project supports an astonishing 1,158+ languages and dialects, making it one of the most language-complete TTS pipelines available.

Key features

Feature	Benefit
Voice cloning	Generate narration with a cloned voice of your choice
1,158+ languages	Huge dialect coverage for global libraries
Web GUI + Docker + Colab	Run it anywhere, with or without a GPU
Chapter-aware splitting	Audiobook files are organized by book chapters

How it works

You upload an e-book, and the tool extracts the text, cleans it up, and feeds it through a neural TTS model. The result is an audiobook in a standard audio format that you can copy to any device. Because everything runs locally, your reading data never leaves your machine.

Whether you are an audiobook superfan, a student who wants to study hands-free, or a developer looking for a production-grade TTS pipeline, ebook2audiobook is a compelling, fully open-source choice.

🚀 Ready to generate your first audiobook?

Get the Docker compose file, requirements, and setup guide.

View ebook2audiobook Tool Page →