Why does it say my PDF has no text to read?

The PDF is a scan: each page is a picture of the paper, with no text inside for a voice to read. Run it through the OCR Toolkit first, which recognises the words and saves a searchable PDF, then open that here.

How long does it take to turn a book into MP3?

On most computers the voice is made about as fast as it plays, so an hour of speech takes roughly an hour; ticking Use the graphics card, where it is offered, is many times faster. The page shows how far it has got and how long is left. Keep the tab open until it finishes; Stop ends it at any point.

Are headers, footers and page numbers read out?

Whatever text is on the page is read, in the order the PDF stores it, so running headers and page numbers can be read too, and a page laid out in columns or with many boxes may come out in an odd order. Picking the pages you want avoids covers, contents and indexes. EPUB and Word files have no page furniture, so they read more cleanly.

The speech is saved at 96 kb/s, about 43 MB an hour, which is plenty for a voice. A long book comes out as a large single file, so one MP3 per chapter can be easier to handle and to resume on a phone.

Is my PDF uploaded to make the MP3?

No. The PDF is opened and read in this browser tab, and the voice is made on your own device; only the voice model and dictionaries are downloaded, the first time.

Stays on your computer Downloads the Kokoro voice model from huggingface.co the first time (92 MB, or 326 MB to use the graphics card) and the English pronunciation dictionaries (about 6 MB) from jsDelivr; Japanese and Chinese download their own dictionaries the first time they are chosen (about 18 MB and 5 MB)How this works

Free PDF to MP3: listen to a PDF as audio

Turn a PDF, e-book or Word document into spoken audio with natural AI voices, read aloud in the page or saved as MP3, chapter by chapter if you like. Made in your browser, so the document is never uploaded

Open a document to read aloud: drop it here or browseTap to open a document to read aloudPDF, EPUB, Word (.docx) or text (.txt) · nothing is uploaded

Or type or paste text

190 / 60,000 characters · about 13 seconds

LanguageVoiceSpeed 1.0×

The first time, the voice model (92 MB) and the pronunciation dictionary (about 6 MB) are downloaded; your browser keeps them.

Pronunciation

A name or word read wrongly can be respelled the way it sounds - "Siobhan" as "shiv awn" - and is read that way everywhere in the text.

About this PDF to MP3 converter

A report to get through on the commute, lecture notes to go over on a walk, a novel without an audiobook: open the PDF and listen. The page reads the PDF's text, page by page, and a natural-sounding AI voice speaks it. Choose the pages to read, a voice and a speed, then press Play to listen straight away, or save the speech as an MP3 to play on your phone or in the car. EPUB e-books, Word documents and text files work the same way, split into chapters.

The voices are Kokoro, an open speech model that runs in this page; the model (about 92 MB) is downloaded the first time and kept by your browser. The PDF's text is taken out with pdf.js and the MP3 is written as the speech is made, so a long book never has to fit in memory as raw sound. It is free to use, with no account and no upload limit, and it runs entirely in your browser: nothing is uploaded, and while the page stays open, a feature you have already used keeps working offline.

What you can do

Convert a PDF to MP3, or listen to it in the page as it is read
Choose the pages to read, from one page to the whole document
Open EPUB e-books (without DRM), Word .docx files and text files, split into chapters
Save one MP3 for the whole selection, or one MP3 per page or chapter in a ZIP
Pick from 48 voices in English, Spanish, Italian, Portuguese, Hindi, Japanese and Chinese, and set the speed
Stop at any time; progress and the time left are shown as it goes
Respell a name or word the voice says wrongly

How to convert a PDF to MP3

Drop the PDF on the box, or click it to choose it.
Tap the box and choose the PDF.
Choose the first and last page to read; the length of the speech is shown.
Choose a language, a voice and a speed.
Press Play to listen, or Save as MP3. Tick One MP3 per page to get separate files in a ZIP.

Questions

Why does it say my PDF has no text to read?: The PDF is a scan: each page is a picture of the paper, with no text inside for a voice to read. Run it through the OCR Toolkit first, which recognises the words and saves a searchable PDF, then open that here.
How long does it take to turn a book into MP3?: On most computers the voice is made about as fast as it plays, so an hour of speech takes roughly an hour; ticking Use the graphics card, where it is offered, is many times faster. The page shows how far it has got and how long is left. Keep the tab open until it finishes; Stop ends it at any point.
Are headers, footers and page numbers read out?: Whatever text is on the page is read, in the order the PDF stores it, so running headers and page numbers can be read too, and a page laid out in columns or with many boxes may come out in an odd order. Picking the pages you want avoids covers, contents and indexes. EPUB and Word files have no page furniture, so they read more cleanly.
How big is the MP3?: The speech is saved at 96 kb/s, about 43 MB an hour, which is plenty for a voice. A long book comes out as a large single file, so one MP3 per chapter can be easier to handle and to resume on a phone.
Is my PDF uploaded to make the MP3?: No. The PDF is opened and read in this browser tab, and the voice is made on your own device; only the voice model and dictionaries are downloaded, the first time.

To type or paste text instead, use Text to Speech. To turn speech into text, the other way round, use Audio to Text; to trim the MP3 afterwards, the MP3 Cutter.