Edit audio

Learn how to edit text that has been processed into audio.

You can edit text that has been processed into audio to change what is read aloud. When editing via SpeechKit, you can also change the voice associated with each title/paragraph and insert your own audio files.

Editing text via SpeechKit's Text-to-Speech Editor

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

  2. Hover on the audio you would like to edit

  3. Select '⋮' to open the submenu, then select 'Edit text'

  1. You will be taken to our Text-to-Speech Editor, where you can:

    • Edit text: You can change, add, or delete text to change what is read aloud.

    • Change voices: Go to the title or paragraph you would like to edit the voice for, select the voice name, then select a new voice from the list (press the play icon to hear a preview).

    • Upload your own audio clips: Select '+' ('Add paragraph') in the desired location, select 'Upload audio', then upload the mp3 file from your device.

  2. When you have finished making changes, select 'Update audio'

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

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

  3. If you are updating text imported via CMS, you will be presented with the option to enable or disable CMS updates via a toggle switch:

    • CMS updates enabled: Changes to the source page will trigger automatic reprocessing, meaning that your edits may be overwritten.

    • CMS updates disabled: Changes to the source page will not trigger automatic reprocessing. This means that your edited version cannot be automatically overwritten. If you wish to update the audio, you will need to do so via SpeechKit.

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

    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).

  2. Select 'Update audio'

Your text will be reprocessed now or at the scheduled time. Processing should only take a few minutes — you can check the audio's status in the 'Content (Audios)' section of your project dashboard.

Editing content via your CMS

By default, if you create audio via CMS integration and then update the source page, this will trigger automatic reprocessing. This means that you can edit an article via your CMS and the audio will be automatically updated to match.

If you wish to prevent automatic reprocessing for a particular audio, you can do so by following the steps above and selecting 'CMS updates disabled' in step 9. This means that you can differentiate the audio version from the text version without the risk of accidentally overwriting your changes.

FAQs

Will I need to update my distributions after editing audio?

In most cases, it is not necessary to update your distributions after editing audio.

Audio that is embedded automatically, embedded manually, shared via URL, or distributed via podcast feed is streamed directly from SpeechKit. This means that the latest version of the audio will always be played (although it may take a little time for changes to be reflected on podcast platforms).

Audio that was downloaded from SpeechKit will not update automatically and so should be replaced if necessary.


Will editing audio use an audio credit?

No, editing an audio will not use an additional audio credit.


How do I optimize my text for text-to-speech?

SpeechKit uses natural language processing (NLP) to automatically optimize your text input for text-to-speech. After your text is imported, our customizable algorithms remove any unwanted elements, such as image captions, and apply speech synthesis markup language (SSML) tags. This verison is then processed by the AI voice, ensuring the best possible output.

As a result, it is not usually necessary to write or edit your text with text-to-speech in mind. You can automatically import content from your CMS and automatically embed it into the page, confident that the audio will be accurate and engaging.

However, if you would like to invest time into perfecting your audio script, here are a few tips:

  • Sense-check your content — for example, where your text version says "keep reading", your audio script should say "keep listening"

  • Use punctuation and paragraphs to improve flow — punctuation and paragraph spaces determine where pauses should go in synthetic speech and how long they should be, so you may wish to tweak these for optimal flow

  • Add audio descriptions — where your text version has visual assets, such as illustrations and charts, you may wish to provide audio descriptions instead

💡

If you are experiencing any problems with your audio, please report a voice issue.



What’s Next