We support pauses only to voices that are not Human voices. We support SSML. You can send Speech Synthesis Markup Language (SSML) in your Text-to-Speech request to allow for more customization in your audio response by providing details on pauses, and audio formatting for acronyms, dates, times, abbreviations, or text that should be censored.
Here is an example of SSML script: https://prnt.sc/13iewcz
For adjust speed in voices, users can use SSML in script area. For example:
<speak>
Step 1, take a deep breath. <break time="200ms"/>
<speak>
Step 1, take a deep breath. <break time="200ms"/>
More details here: https://cloud.google.com/text-to-speech/docs/ssml
Note: This will work if you will add the script <speak> at the beginning and </speak> at the end of the sentence.
For example:
<speak> JOIN US FOR THE MASSIVE LAUNCH OF <break time="5s"/> HUMAN SYNTHESYS STUDIO AND IN BIG COMMISSIONS! </speak>
But remember, not all voices support SSML. Only the non human voices support SSML.
Was this article helpful?
That’s Great!
Thank you for your feedback
Sorry! We couldn't be helpful
Thank you for your feedback
Feedback sent
We appreciate your effort and will try to fix the article