Links

TTS Editor

Use our Text-to-Speech Editor to create audio from plain text.
This guide explains how to create audio from text using the Text-to-Speech Editor (TTS Editor) in your BeyondWords dashboard. This is ideal if you are unable to create audio automatically.
You can also edit audio in the TTS Editor, even if it was created automatically.
  1. 1.
    Go to the 'Content (Audios)' section of your project dashboard (don't have one? Create a project)
  2. 2.
    Select 'Text-to-Speech Editor' or 'Create audio'
  3. 3.
    Type or paste your title and body content into the TTS Editor (consider optimizing your text for a spoken format) — your default voices will be applied automatically
  4. 4.
    Change voice selections (optional)
    1. 1.
      Go to the title or paragraph you would like to edit the voice for
    2. 2.
      Select the voice name then select a replacement voice from the list (press the play icon to hear a preview)
  5. 5.
    Insert audio (optional)
    1. 1.
      Select '+' then 'Upload audio'
    2. 2.
      Upload the mp3 file from your device
  6. 6.
    1. 1.
      Highlight the word or phrase you would like to be read differently
    2. 2.
      Select 'Add alias'
    3. 3.
      Enter your alias
    4. 4.
      Select 'Apply to all instances in this audio only' or 'Apply to all instances in this project'
    5. 5.
      Select 'Save changes'
  7. 7.
    Select 'Process audio'
  8. 8.
    You will be presented with a pop-up:
    1. 1.
      Enter the author's name (optional — this will be stored as metadata)
    2. 2.
      Enter the corresponding URL (optional — necessary if you would like to automatically embed the audio onto the page)
    3. 3.
      Select 'Schedule for later' then enter a date and time (optional — scheduling means that your audio will not be published until the scheduled time)
  9. 9.
    Select 'Process audio'
Your text will now be processed into audio. This will use characters. 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 insert my own audio into my text-to-speech audio?
Yes, you can upload audio files to the TTS Editor, as long as they are in an mp3 format. This allows you to insert sound effects, audio clips, and more. Simply select the '+' icon wherever you would like to insert audio, select 'Upload audio', then select your file.
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'. The audio status will be 'Draft'.
To continue working on your draft:
  1. 1.
    Go to the 'Content (Audios)' section of your project dashboard
  2. 2.
    Hover on the draft you would like to reopen and select '⋮' to open the submenu
  3. 3.
    Select 'Edit text'
Can I edit my text and reprocess the audio?
Yes, you can edit your audio anytime:
  1. 1.
    Go to the 'Content (Audios)' section of your project dashboard and hover on the audio you'd like to edit
  2. 2.
    Select the '⋮' (Other actions) icon then 'Edit text'
  3. 3.
    Make changes in the TTS Editor, then select 'Update audio'
  4. 4.
    Make any changes in the pop-up, then select 'Update audio'
The audio will then be reprocessed. Only new paragraphs or paragraphs with new voices will use characters.
Can I automatically embed audio into my website or app?
Yes, you can automatically embed audio created via the TTS Editor into the corresponding page on your website or app.
You will need to set up automatic embedding and provide the URL metadata when creating your audio. The code will fetch this URL to determine whether an audio version of each page is available and, if so, embed the audio player.
Are there any size limits?
There is a limit of 600 paragraphs per audio and 1,000 characters per paragraph. Please email [email protected] if you would like to request a larger limit.