How to use InboxToAudio

Upload a document or photos of a page

Forwarding email is not the only way to get audio out of InboxToAudio. You can also hand it a file directly — a PDF, a Word document, plain text, or photos of a printed page — and it reads the text back to you the same way. This covers both paths: uploading a document and uploading photos of text.

What you can upload

• Documents. Any PDF — including scanned and image-based PDFs — plus Word documents (.doc or .docx). Up to 15 MB per file.
• Photos of printed pages. A book chapter, a letter, a printout, a whiteboard, a magazine article — anything with text you can photograph. Up to 10 photos at a time, 15 MB each (24 MB combined), in JPEG, PNG, HEIC, WEBP, GIF, TIFF, or BMP.
• Pasted text. Plain text, HTML, or markdown pasted straight into the box also works, if you already have the text somewhere.

Upload a PDF, Word, or text file

On the web

1. Go to Listen and click the + button (“Paste content to create audio”) to open the Paste content screen.
2. Under Have a document?, click Upload file and choose your PDF, DOC, or DOCX.
3. We pull the text out of the file. If it is a PDF, you can also turn on Create audio automatically to skip the review step below and send it straight to your library while it renders.
4. Check the extracted title and text, edit anything you want changed, then click Create Audio.

On iPhone or iPad

1. Open the file in Files, Mail, or another app, tap Share, choose Inbox to Audio (tap More if you don’t see it), then tap Open in Inbox To Audio.
2. Review the extracted title and text, then tap Create audio.

By email

A PDF, .doc, or .docx attached to an email you forward to your listening address (up to 15 MB) is read and narrated automatically, the same as the message body — there is no review step for those. If you want to check the extracted text before it becomes audio, upload the file instead of forwarding it.

Upload photos of text

No PDF or file on hand? Photograph the pages instead and InboxToAudio reads the text off the pictures.

On the web

1. On the Paste content screen (see above), find Have photos of it? and click Add photos to pick images from your computer, or Take a photo to use your camera.
2. Add every page — up to 10 at a time. Photos are read in the order you added them, so drag a thumbnail (or use the ‹ › arrows) to put the pages in the right sequence.
3. Click Read photos. If you need to add or reorder pages afterward, do it and click Read photos again — it replaces the extracted text.
4. Check the extracted title and text, edit anything you want changed, then click Create Audio.

On iPhone or iPad

1. Open Inbox to Audio and start a New Audio Article.
2. Add pages with Photos (your library), Camera (shoot them now), or Files (existing image files).
3. Put the pages in order, then tap Read photos.
4. Review the extracted title and text, then tap Create audio.

Why there’s a review step

Anything you upload — a document, photos of pages, or pasted text — stops at a review screen before it becomes audio. You see the extracted title and text and can edit either one before you press Create Audio. That is your chance to cut a cover page, fix a garbled scan, or drop a section you don’t want read aloud. Forwarded email skips this step and converts automatically, which is the point of forwarding — it’s hands-free.

Troubleshooting

“Only PDF, DOC, and DOCX files are supported”

Other file types are not readable as documents yet. Convert the file to PDF first, or use photos instead if it’s a scan or an image.

“That file is larger than 15 MB”

Compress the PDF or split it into smaller files. A scanned document with high-resolution images is usually the cause.

“We could not read any text from that file”

This usually means the PDF is a blank or corrupted scan. Try re-scanning it, or photograph the pages instead — photo text extraction can succeed where a broken PDF fails.

“Only JPEG, PNG, HEIC, WEBP, GIF, TIFF, and BMP photos are supported”

Re-export or re-save the image in one of those formats and try again.

“We could not find any readable text in those photos”

Retake the photos with more light and the page filling the frame, and make sure the text is in focus and not at a steep angle.

The pages came out in the wrong order

Drag the thumbnails (or use the ‹ › arrows) into the correct order before clicking Read photos. If you already read them, reorder and click Read photos again — it replaces the extracted text with the new order.

Still stuck? See Individual (listener) plans for the full walkthrough, or reach us at support@inboxtoaudio.app.