This guide explains how to use AI voices when creating audio with BeyondWords.
You can change these voices in the 'Settings (General)' section of your project dashboard (please note this will also affect default voices for the API and Text-to-Speech Editor). Press the play icon next to any voice option to hear a preview.
Audio created using our API will use a maximum of two voices by default: one to read the title, and one to read the body content. Default voices can be changed in the 'Settings (General)' section of your project dashboard (please note this will also affect default voices for other CMS integrations and the Text-to-Speech Editor). Press the play icon next to any voice option to hear a preview.
When using HTML, you can manually set voices at a title or paragraph level by adding a
data-speechkit-voice=* data attribute to the
<p> element, where
* is the voice ID from our list of voices.
When creating audio from plain text, the default voices for titles and body content (paragraphs) will be used. These can be changed in the 'Settings (General)' section of your project dashboard.
If you haven't set default voices beforehand, you will be prompted to set your default voices when using the Text-to-Speech Editor for the first time:
When creating or editing audio in the Editor, you can change the voice associated with any title or paragraph by selecting the voice name then selecting a new voice from the menu. Press the play icon next to any voice option to hear a preview.
Why am I not seeing a full list of voices?
The voice selection in your dashboard will be limited by the language (and sometimes locale) chosen for your project. You can change your project language in the 'Settings (General)' section of your project dashboard.
How can I preview voices before choosing?
When choosing a voice from a dropdown list (in settings or the Text-to-Speech Editor), you can press the play button next to any option to hear a preview. For longer demos, you may wish to experiment in the Text-to-Speech Editor.
Can I use multiple AI voices per audio?
You can also use multiple voices per audio using our API.
Please see the corresponding sections above for more information.
If I change voice settings, will my old audios be updated?
New voice settings will apply to newly generated audio only. This includes audio that is automatically or manually reprocessed.
This means that pre-existing audios will not be automatically updated when voice settings are changed. However, you can manually reprocess the audio:
Go to the 'Content (Audios)' section of your project dashboard
Hover on the audio that you would like to update the voice(s) on
Select '⋮' then 'Reprocess audio' — the audio should be processed within a few minutes
Where do BeyondWords voices come from?
Our AI voice library includes the latest AI voices from Google Cloud, Amazon Web Services, Microsoft Azure, and Yandex. These are enhanced by our NLP algorithms — visit our blog to learn more about why AI voices sound better on BeyondWords.
Can I create a custom voice?
Yes, with our voice cloning service, you can create a custom AI voice with as little as two hours of recordings. You can use your own voice or work with a voice artist to create a custom voice that truly resonates with your target audience.
Email [email protected] to learn more.
Updated 6 days ago