OpenViSTAI · Agents · Blockchain · Crypto
Menu
Audio & Voice AI

Epub2Tts

Epub2Tts is an open-source Python command-line application that converts DRM-free EPUB books or text files into M4B audiobooks using text-to-speech. It detects chapter breaks and can add cover art; supported engine choices include Coqui TTS, OpenAI, Microsoft Edge TTS, and Kokoro.

Independent OpenViST project profile, based on linked sources.

Epub2Tts — OpenViST project profile in Audio & Voice AI.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Epub2Tts when you have a DRM-free EPUB or text document and want a command-line workflow for producing an audiobook, especially if you need chapter detection, voice selection, or editable text preparation.

Who it is for

  • Readers who want to turn DRM-free EPUB books into audiobooks.
  • People preparing text documents for spoken playback.
  • Users who want to select a TTS engine, speaker, or voice-cloning input from a command line.

Documented uses

  • Convert an EPUB or text file into an M4B audiobook.
  • Export an EPUB to text to edit chapter headings or remove sections before audio generation.
  • Choose a TTS engine and speaker, or provide audio samples for XTTS voice cloning.
  • Add cover art and select a chapter range for conversion.
Before you choose

Requirements & limits

The project is described as free and open source under the Apache-2.0 license. The README identifies Microsoft Edge TTS as a cloud-based option and the default VITS example as requiring no GPU.

  • EPUB input must be DRM-free.
  • The application is a CLI, so its documented workflow uses terminal commands.
  • Engine choice affects setup: OpenAI requires an API key, while XTTS voice cloning takes one or more audio samples.
  • The README says thread counts for Coqui TTS or XTTS may need adjustment to suit the user's system.
  • The Kokoro example includes a speed option but notes that speed configuration is ignored.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Export and prepare an EPUB as editable text

Extract an EPUB's contents to a text file and prepare chapter structure before audio generation.

Before you start

  • A DRM-free EPUB
  • Epub2Tts available as a command-line application

Steps

  1. Run epub2tts mybook.epub --export txt.

  2. Edit the resulting mybook.txt, renaming chapter headings and removing front matter or other material that should not be read.

  3. If including audiobook metadata, put Title: and Author: on the first two lines; begin the book text after them with a chapter or section heading starting with #.

Expected outcome

A text version of the EPUB with editable chapter headings and optional title and author metadata, ready for a subsequent audiobook command.

Guide limitations

  • The EPUB must be DRM-free.
  • The instructions document text export; they do not specify the export of other formats.
Source-based practical guide

Create an audiobook from an EPUB with the default VITS setup

Generate an audiobook from a DRM-free EPUB using the documented default VITS settings.

Before you start

  • A DRM-free EPUB
  • Epub2Tts available as a command-line application

Steps

  1. Run epub2tts mybook.epub to use the documented default VITS model.

  2. To choose a different Coqui speaker, add a documented speaker option, such as --speaker p307.

Expected outcome

An M4B audiobook generated with the default VITS setup; chapter breaks are detected automatically.

Guide limitations

  • The README's default VITS example says no GPU is required.
  • This recipe uses default settings and does not describe advanced editing or engine-specific configuration.
Evidence and transparency

Sources & review

Source record details
Source availability
Active
Sources checked
17 October 2026
Original website title
aedocw/epub2tts · Official homepage title · retained in its source language

Related options

epub2tts-edge — A lighter-weight, engine-specific variant that uses Microsoft Edge TTS.

epub2tts-kokoro — A lighter-weight, engine-specific variant for the Kokoro TTS engine.

epub2tts-chatterbox — A separate project recommended in the README for Coqui voice-cloning use; the README says it requires a GPU.

epub2tts-vibevoice — A separate project using Microsoft VibeVoice, which the README highlights for handling long text.