Create audio from plain text

Use our Text-to-Speech Editor to create audio from plain text.

This guide explains how to convert plain text into audio using our Text-to-Speech Editor. The instructions differ slightly depending on whether you have or have not connected a CMS.

💡

Did you know? You can Import text from a URL.

If you've connected a CMS

  1. Go to the 'Content (Audios)' section of your project dashboard

  2. Select 'Create an audio'

  3. Start typing, or copy and paste your text into the Editor — consider making edits to ensure optimal text-to-speech conversion

  1. Insert audio snippets (optional)

    1. Select '+' ('Add paragraph') then 'Upload audio'

    2. Upload the mp3 file from your device

  1. Change voice selections (optional) — the Text-to-Speech Editor will have automatically applied the default voices you selected for your integration

    💡

    You can change default voices in the 'Settings (General)' section of your project dashboard, but this will also affect content created via CMS integration.

    1. Go to the title or paragraph you would like to edit the voice for

    2. Select the voice name then select a new voice from the list (press the play icon to hear a preview

  1. Select 'Publish'

  2. Enter the author's name (optional — this will be stored as metadata)

  3. Enter the corresponding URL (optional — necessary if you would like to automatically embed the audio onto the page using our automatic Player)

  4. Select 'Schedule for later' (optional) — delay any automatic distributions by picking a date and time for your audio to be processed

    🕙 You can change your project time zone in 'Settings (General)'. You will need to manually update your time zone to account for switches between daylight saving time (DST).

  1. Select 'Publish'

Your text will be processed into audio now or at the scheduled time, with each conversion using one audio credit. Processing should only take a few minutes — you can check the audio's status in the 'Content (Audios)' section of your project dashboard.

If you haven't connected a CMS

💡

Before you create audio for the first time, it's a good idea to set your default voices in 'Settings (General)'.

  1. Go to the 'Content (Audios)' section of your project dashboard (don't have one? Create a project)

  2. Select 'Text-to-Speech Editor' under 'Create an audio'

  3. Start typing, or copy and paste your text into the Editor — consider making edits to ensure optimal text-to-speech conversion

  1. Insert audio snippets (optional)

    1. Select '+' ('Add paragraph') then 'Upload audio'

    2. Upload the mp3 file from your device

  1. Change voice selections (optional)

    ️ If you haven't set default voices in 'Settings (General)', you will need to manually set a voice for every title and paragraph. Select the microphone icon to see your options.

    1. Go to the title or paragraph you would like to edit the voice for

    2. Select the voice name then select a new voice from the list (press the play icon to hear a preview)

  1. Select 'Publish'

  2. Enter the author's name (optional — this will be stored as metadata)

  3. Enter the corresponding URL (optional — necessary if you would like to automatically embed the audio onto the page using our automatic Player)

  4. Select 'Schedule for later' (optional) — delay any automatic distributions by picking a date and time for your audio to be processed

    🕙 You can change your project time zone in 'Settings (General)'. You will need to manually update your time zone to account for switches between daylight saving time (DST).

  1. Select 'Publish'

Your text will be processed into audio now or at the scheduled time, with each conversion using one audio credit. Processing should only take a few minutes — you can check the audio's status in the 'Content (Audios)' section of your project dashboard.

FAQs

Can I save my draft and come back to it later?

Yes, you can save your draft anytime. Scroll to the bottom and select 'Save draft'.

To continue working on your draft:

  1. Go to the 'Content (Audios)' section of your project dashboard

  2. Hover on the draft you would like to reopen and select '⋮' to open the submenu

  3. Select 'Edit text'


Can I edit my text and reprocess the audio?

Yes, you can edit your text and reprocess the audio:

  1. Go to the 'Content (Audios)' section of your project dashboard

  2. Hover on the draft you would like to reopen and select '⋮' to open the submenu

  3. Select 'Edit text'

  1. Make edits then publish or schedule like usual — this will trigger audio reprocessing

Can I automatically embed audio into my website or app?

Yes, you can automatically embed audio created via the Text-to-Speech Editor into a corresponding page on your website or app.

You will need to set up the automatic Player and enter a URL when publishing your audio. The automatic Player will fetch this URL to determine whether an audio version of each page is available and, if so, embed it automatically.