Listen to any PDF, read by a neural voice

Drop in a report, paper or manual. The text is read out of it in your browser, and comes back as an MP3 with subtitles.

Drop a PDF here, or choose a file

Read in your browser - the file is never uploaded

Script

0 words · 0 / 7,000 chars

Turn a PDF into a spoken MP3

Reports, papers, manuals and drafts are easier to get through when you can listen to them. Drop a PDF above and ReadAnyText reads the text out of it, hands it to a neural voice, and gives you back an MP3 you can keep - free, no credit card.

How it works

  1. 1

    Drop in your PDF

    Text is pulled straight out of the document in your browser. Hyphenated line breaks are rejoined, paragraphs are restored from the page layout, and page numbers are dropped so nothing odd gets read aloud.

  2. 2

    Edit and cast it

    The extracted text lands in the editor. Trim what you don't need, pick one of 300+ neural voices, set the pace, and add pauses where you want them to land.

  3. 3

    Download the MP3

    Generate once and take away a single MP3, plus matching SRT and WebVTT subtitles if you're pairing the audio with video.

Questions

Is my PDF uploaded anywhere?
No. The PDF is opened and read inside your browser, so the file itself never leaves your device. Only the extracted text is sent to be spoken.
How long can the PDF be?
You get 7,000 free characters per allowance - a solid chapter or report section - refilling two minutes after you use it up. Within a render, the text is split into parts, synthesized in parallel and stitched into a single MP3.
Does it work on scanned PDFs?
Not yet. A scan is a picture of text, so there is nothing to extract. If you can select the text in a normal PDF reader, it will work here.
Can I get subtitles as well?
Yes. Every render produces word-accurate SRT and WebVTT files alongside the MP3, timed to the individual word.
Why does the text need editing first?
PDFs store glyphs at positions rather than sentences, so headers, footnotes and captions can land mid-paragraph. The editor lets you cut those before generating.
Can I listen to only part of a document?
Yes. Everything lands in the editor as plain text, so delete what you don't want or paste in just the section you care about.

More ways to listen

Sign in to generate your voiceover

It's free. Your script and settings stay right here - you'll come straight back to them.

  • Free - 7,000 characters per voiceover
  • No credit card
  • We never see your Drive, Gmail or contacts

We use your name and email only to keep you signed in. Privacy policy