Skip to content

Need personal help? We reply quickly.

Reach our team directly — we can help with your private listening inbox.

InboxToAudio help center

How to use InboxToAudio

A plain-English guide for turning newsletters, reports, and emails into private audio you can listen to anywhere.

Individual (listener) plans

The Individual plan is for readers. You forward newsletters, articles, reports, or any other email you already receive to a private address and get back a clean audio version you can listen to anywhere — on a walk, a commute, or while doing the dishes.

You can try it once for free — forward a single newsletter, article, or any other email (up to about 2,000 words) during onboarding and hear it back, no credit card required. After that, forwarding and audio generation require a paid plan.

The three plans

Every plan gives you a personal listening inbox, 28 narration voices, and rendering in 10 languages: English, Spanish, French, German, Italian, Portuguese, Russian, Korean, Mandarin, and Japanese. Plans differ by the number of minutes of audio included each month.

  • Individual — $9/month (or $90/year): personal listening inbox, all 28 voices and 10 languages, up to 300 minutes per month.
  • Individual Plus — $16/month (or $160/year): up to 700 minutes per month.
  • Individual Pro — $30/month (or $300/year): up to 1,500 minutes per month, plus two-speaker podcast-style narration for a conversational listen.

Minutes, not emails

Your monthly limit is measured in minutes of generated audio. Annual billing includes two months free. Re-listening to audio you have already generated is free and does not use your minutes.

1. Subscribe and sign in

Choose a plan on the subscribe page and complete checkout. Once your payment is confirmed, your listener dashboard unlocks the inbox and (on Individual Plus) the voice picker.

2. Create your private listening inbox

On your dashboard, open the listening inbox card and click Create my inbox. We generate a private email address that belongs only to you. It looks like:

alpha.beta.12345@inbox.inboxtoaudio.app

Treat this address like a password — anyone who has it can send content to your inbox. You can replace it at any time (see “Regenerate your inbox” below).

3. Forward an email or subscribe a newsletter

  1. Open a newsletter, report, article, or other email in your normal inbox.
  2. Forward it to your private listening address (word.word.12345@inbox.inboxtoaudio.app).
  3. We strip out personal details (greetings, unsubscribe footers, tracking), clean up the text for listening, generate the audio in your chosen voice, and email you back a private link.

Tip

Forwarding works from any email app — Gmail, Outlook, Apple Mail, your phone. You can forward several items in a row; each one becomes its own audio item. For hands-free delivery, subscribe your private address to a newsletter and every new issue is narrated automatically.

Save the address as a contact

So you never have to type it, save your listening address as a contact in your mail app (for example, a contact called “🎧 Inbox to Audio”). Then just start typing the name in the To: field. In the iOS app you can do this in one tap from Settings → Forwarding address → Add to contacts. If you ever regenerate your address, update the saved contact too.

Want every issue, hands-free?

Forwarding is best for one-off articles. For a newsletter you follow regularly, subscribe your listening address to it directly so every new issue becomes audio automatically — see Subscribe your inbox to newsletters.

4. Share an article from Safari

Send the article you are reading straight to the Inbox to Audio iOS app:

  1. Open the article in Safari and tap Share.
  2. Choose Inbox to Audio. If it is not visible, tap More to find it.
  3. Tap Open in Inbox To Audio, review the extracted title and text, then tap Create audio.

5. Upload a PDF, Word file, or photos of the pages

Email is not the only way in. You can also hand InboxToAudio a file and get audio from it:

  • Documents. Any PDF — including scanned and image-based PDFs — plus Word documents (.doc or .docx), HTML, and plain text. Up to 15 MB per file.
  • Photos of printed pages. Snap a book chapter, a letter, a printout, or a magazine article and we read the text off the pictures. Up to 10 photos at a time, 15 MB each, in JPEG, PNG, HEIC, WEBP, GIF, TIFF, or BMP.
  • Text you paste. Paste plain text, HTML, or markdown straight into the box.

On the web

  1. Go to Listen and click the + button (“Paste content to create audio”) to open the Paste content screen.
  2. Click Upload file for a document, or Add photos for pictures of the pages.
  3. Photos are read in the order you added them. Drag a thumbnail (or use the arrows) to reorder them so the pages come out in the right sequence, then click Read photos.
  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 or another app, tap Share, choose Inbox to Audio, then tap Open in Inbox To Audio.
  2. Or open New Audio Article in the app and add pages with Photos (your library), Camera (shoot them now), or Files (image files), then tap Read photos.
  3. Review the extracted title and text, then tap Create audio.

PDFs of every kind

PDF rendering uses document understanding to read text-based, scanned, and image-based pages, then turns the extracted content into a clean audio article. If a document is very long, only the first part is imported and we tell you so before you create the audio.

Review before you generate — uploads only

There is one important difference between the two ways of sending content in:

  • Anything you upload — a document, photos of pages, an article shared from Safari, or text you paste — stops at a review step. You see the extracted title and text, you can edit it, and nothing is narrated until 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.
  • Anything you email to your listening address is converted automatically. There is no review step: we clean the message up and start generating audio as soon as it arrives. That is the point of forwarding — it is hands-free.

Forwarded attachments count as email

A PDF, .doc, or .docx attached to an email you forward (up to 15 MB) is read and narrated automatically, same as the message body — you don’t get to review it first. If you want to check the text before it becomes audio, upload the file instead of forwarding it. Photos can’t be emailed in; add those through Paste content.

If a forwarded item comes out wrong, delete it and re-add the same content as an upload or a paste, where you can fix the text first.

6. Picking a voice

InboxToAudio has 28 narration voices. Every one of them can read in all 10 supported languages: English, Spanish, French, German, Italian, Portuguese, Russian, Korean, Mandarin, and Japanese.

Your single narration voice

  1. On the web, open Voice from the listener navigation (the Narration voice picker). In the iOS app, go to Settings → Voice.
  2. Tap Preview next to any voice to hear a sample. You can switch the preview language to hear a voice in the language you actually listen in.
  3. Click or tap the voice itself to select it. Your choice saves automatically — there is no separate save button.

The voice you pick applies to the next item you forward, paste, or upload. Audio you already generated keeps the voice it was made with.

Two-speaker, podcast-style narration (Individual Pro)

On Individual Pro you can also have your reading narrated as a conversation between two voices, the way a two-host podcast sounds. Find it under Settings on the web, or Settings → Two Speaker Audio in the iOS app. Setting it up takes two decisions, in this order:

  1. Pick a voice set. The 28 voices come in two sets, labelled Voice Set 1 and Voice Set 2. They are built on different narration technology, so the two speakers have to come from the same set — you can’t pair a voice from Set 1 with one from Set 2. Switch between the sets to hear what each one offers before you commit.
  2. Pick two voices from that set. Choose Speaker 1, pick a voice, then switch to Speaker 2 and pick another. They have to be two different voices, or the hosts would be indistinguishable. Preview each one first.

Save the pair and we create your two-speaker forwarding address (see below). You can come back and change the pair whenever you like with Change voices — your address stays the same, and future items use the new pair.

Switching sets keeps your picks

If you choose two voices in one set, look at the other set, then switch back, your original pair is still selected. Nothing is lost by browsing.

Your two listening addresses

Once two-speaker audio is set up you have two private addresses, and the one you send to decides how the audio sounds:

  • Your single-voice address (word.word.12345@inbox.inboxtoaudio.app) — one narrator reads the whole piece, in the voice you selected above.
  • Your two-speaker address — a different address, created when you save your voice pair. Anything sent here comes back as a podcast-style conversation between your two chosen voices.

Both addresses accept forwarded email and both can be used to subscribe to newsletters, so you can route a dense report to one and your daily news brief to the other. Everything lands in the same library either way.

Save both as contacts

Give them names you can tell apart in your mail app — for example “🎧 Inbox to Audio” and “🎙 Inbox to Audio Two Speaker”. Both cards can be downloaded with the Add as contact button next to each address.

Pro only

The two-speaker address only produces audio while your Individual Pro subscription is active. On a lower plan, mail sent to it is not turned into audio.

7. Listen

When your audio is ready you get a reply email with a private link. You can also play every item directly from your dashboard with chapters, a transcript, adjustable speed, and saved listening position. Generated audio stays in your library and remains playable for future listening.

8. Share an episode

Use Share on an episode to copy a link for someone else to listen. Creator-backed episodes keep the creator’s public listening link. Your forwarded emails, shared articles, and imported files use a no-login link at inboxtoaudio.app/s/....

You can turn a share link off

A recipient does not need an account to listen, so treat a share link as public. When you want it to stop working, use Revoke sharing on the episode — every copy of that link you handed out stops working immediately. Deleting the episode has the same effect. Creator-published episodes are the exception: they use the creator’s own public listen page, which you can’t revoke.

Settings worth knowing

Where we send your audio links

By default the “your audio is ready” email goes back to whichever address you forwarded from. You can switch it to your account email instead from the inbox card.

Approved senders (optional)

If you want to lock things down, turn on Only accept forwards from approved senders and list the addresses you forward from (one per line). When this is on but the list is empty, all forwards are blocked — so add at least your own address.

Regenerate your inbox

If your address ever leaks or you just want a fresh one, click Regenerate (then confirm). The old address stops working immediately and a new one is issued. This requires an active subscription.

Retry a failed item

If an item shows a Failed badge, click Retry to re-run it. Retries need an active subscription; completed items can’t be retried.

Your library and plan minutes

  • Generated audio stays playable in your library.
  • New rendering uses the minutes in your active monthly plan.
  • Re-listening to generated audio is free and does not use minutes.
  • Choose a larger plan or resubscribe whenever you want to keep rendering.

Still stuck? Send us a message

Use the form below and we’ll get back to you, usually the same business day. Prefer email? Write to support@inboxtoaudio.app. Include the newsletter you forwarded and the address you sent it from so we can find it quickly.