Drop a DRM-free EPUB and start listening within seconds. Chapters are kept, front matter is skipped, and you choose the narrator.
What happens to your EPUB
EPUB is the best-case input for AI narration because it is structured text. Book2Speech reads the package metadata (title, author, language), walks the spine in reading order and turns every chapter into its own narrated section, so the player’s chapter list matches the book’s table of contents.
Images are skipped and headings become chapter markers. Front matter (title page, copyright, dedication, contents), part dividers and back matter (notes, index, about the author) are classified separately, so the player can suggest where the story actually begins.
Where EPUBs usually trip up text-to-speech
•
Front matter first: many EPUBs open with a copyright page, dedication and contents. Book2Speech marks those as front matter and suggests starting at the first real chapter.
•
One giant chapter: some conversions pack the whole book into a single file. Book2Speech splits on headings so you still get chapter navigation.
•
Table-of-contents pages that repeat every chapter title are recognised as a contents list rather than narrated as headings.
•
Kobo KEPUB files are accepted as EPUB.
•
DRM: files bought from stores that apply DRM (most Kindle and some Kobo titles) are rejected with a message asking for a DRM-free copy. See the guide on DRM-free ebooks for legitimate sources.
Narration built for whole books, not snippets
Generic text-to-speech reads one paragraph at a time. Book2Speech is tuned for long-form listening: chapters are detected and kept in order, front matter (title pages, copyright notices, tables of contents) is recognised so you can start at chapter one, and playback streams ahead so the narrator never stalls mid-sentence.
Pick from 260+ narrators in 40+ languages. Every narrator has a sample, and you can switch voices on a book you have already started.
Listen where you read
•
Web: listen in the browser on any laptop or desktop, with read-along highlighting of the sentence being spoken.
•
iPhone and iPad: the Book2Speech app plays in the background, supports a sleep timer and speed control, and accepts files from the share sheet or the Files app.
•
Your listening position syncs across devices, so a chapter started on the laptop continues on the phone.
Your files, your rights
Upload files you own or have the right to use, up to 5 MB, without DRM. Books stay in your private library until you delete them; deleting your account removes them. Book2Speech does not resell, publish or train voices on your uploads.
Questions people ask
Does the EPUB keep its chapters?
Yes. Chapters come from the EPUB spine and table of contents, so you can jump between them in the player exactly as in the ebook.
Can I convert a Kindle book?
Only if it is DRM-free. Book2Speech accepts MOBI and AZW3 files without DRM; protected purchases are rejected. Many publishers and libraries (Tor, Baen, Standard Ebooks, Project Gutenberg) sell or give away DRM-free EPUBs.
How long does it take?
Parsing a typical novel takes a few seconds. Narration is generated as you listen and streams ahead, so there is no wait for the whole book to render.
Can I download the audiobook as an MP3 or M4B?
Book2Speech is a listening app: narration streams in the web player and the iOS app. A full-book file can be requested from the book page; it is prepared on request rather than instantly.
Is it free?
The Free plan includes 5 minutes of narration to try any file; paid plans add hours of new narration every month (see Plans).