selfhost.directory

The index of self-hostable projects — ranked, categorized and served with live updates.
Own your data and stop giving it to big tech.

GitHub
ebook2audiobook---Legacy logo

Self-host ebook2audiobook---Legacy

v26.11.22

Turn ebooks into audiobooks with TTS and voice cloning

ReleaseOpen SourceApache-2.0
docker run -v "./ebooks:/app/ebooks" -v "./audiobooks:/app/audiobooks" -v "./models:/app/models" -v "./voices:/app/voices" -v "./tmp:/app/tmp" --rm -it -p 7860:7860 athomasson2/ebook2audiobook:cpu
Updated4 minutes ago
LanguagePython
Setup difficultyModerate
Stars
20 639
RAM
2GB min, 8GB recommended
Port
7860 (Gradio web GUI / web app.)
Docker
athomasson2/ebook2audiobook
Gradio web GUI, main conversion screenGradio web GUI, second settings screenGradio web GUI, third settings screen

What is ebook2audiobook---Legacy?

ebook2audiobook (E2A) is an Apache-2.0 licensed converter that turns ebooks and PDFs into audiobooks, preserving chapter and metadata structure. Synthesis runs through a choice of TTS backends—XTTSv2, VITS and Fairseq among them, plus Bark, GlowTTS and Tortoise—and you can clone your own voice from a short reference recording, with noisy uploads cleaned automatically. Language coverage reaches 1158 tongues. A Gradio web interface runs locally, while headless flags make batch or scripted use easy. Further capabilities include OCR of scanned pages, translating an ebook before synthesis, SML tags that insert pauses or switch voices mid-book, optional MusicGen interludes, and pushing finished files to an Audiobookshelf library. Install via launcher scripts on Linux, macOS and Windows, or use the published Docker image and compose files with CUDA, ROCm, XPU and Jetson variants. CPU-only conversion is slow for the heavier engines, and the tool is meant solely for DRM-free books you own legally.

ebook2audiobook---Legacy alternatives

Should you self-host ebook2audiobook---Legacy?

ebook2audiobook---Legacy scores 74/100 on selfhost.directory (how scoring works) and ranks #2 of 9 in Text to Speech. It has 20 639 GitHub stars, +264 in the last 30 days.

It shipped 12 stable releases in the past year. The latest, v26.11.22, came out on 22 November 2026. New versions land roughly every 3 weeks.

Setup is moderate: expect some configuration beyond a single command. An official Docker image is available. It is Apache-2.0-licensed and written mostly in Python.

Its closest alternative on selfhost.directory is OmniVoice-Studio (90/100, 116 304 stars). It scores higher overall, so compare the two before you pick. See ebook2audiobook---Legacy vs OmniVoice-Studio side by side.

Features

  • Batch folder conversion
  • Custom / fine-tuned model upload
  • Direct text-to-speech of typed text
  • eBook to audiobook conversion
  • Ebook translation before synthesis
  • Gradio web GUI
  • Headless CLI mode
  • Multilingual TTS (1158 languages)
  • Multiple audio output formats
  • Multiple TTS engines
  • Music interludes
  • OCR of image pages
  • SML tags for pauses and voice switching
  • Voice Cloning
  • Wide eBook format input

ebook2audiobook---Legacy README

📚 ebook2audiobook (E2A)

DrewThomasson%2Febook2audiobook | Trendshift

CPU/GPU Converter from E-Book to audiobook with chapters and metadata
using advanced TTS engines and much more.
Supports voice cloning and 1696 languages!

How to install ebook2audiobook---Legacy

Install ebook2audiobook---Legacy with Docker

        CPU:
          docker run -v "./ebooks:/app/ebooks" -v "./audiobooks:/app/audiobooks" -v "./models:/app/models" -v "./voices:/app/voices" -v "./tmp:/app/tmp" --rm -it -p 7860:7860 athomasson2/ebook2audiobook:cpu
        CUDA:
          docker run -v "./ebooks:/app/ebooks" -v "./audiobooks:/app/audiobooks" -v "./models:/app/models" -v "./voices:/app/voices" -v "./tmp:/app/tmp" --gpus all --rm -it -p 7860:7860 athomasson2/ebook2audiobook:cu[118/122/124/126 etc..]

ROCM, XPU and JETSON run commands also documented; MPS is not exposed in Docker.

How to configure ebook2audiobook---Legacy

  • --headlessRun the script in headless mode (no Gradio GUI).
  • --ebookPath to the ebook file for conversion. Cannot be used when --ebooks_dir is present.
  • --ebooks_dirDirectory containing ebook files to convert (batch).
  • --textRaw text for conversion.
  • --voicePath to the voice cloning file for the TTS engine; default voice used if absent.

ebook2audiobook---Legacy releases & version history

@ Every self-hosted release, weekly

One Monday email with the week's stable releases across the directory.

More in Text to Speech

Rate this project

Click to rate — no account needed.

0 comments

Posting as guest
Loading comments…