AI Speaker usage guidelines

For now, AI Speakers are only available in English.

  • You can use AI Speakers in Descript with any subscription, but the usage changes depending on your plan:
    • Free Plan: 5 minutes of text-to-speech, 5 regenerates per month.
    • Hobbyist Plan: 30 minutes of text-to-speech, 10 regenerates per month.
    • Creator Plan: 120 minutes of text-to-speech, 100 regenerates per month.
    • Pro Plan: 300 minutes of text-to-speech, unlimited regenerates.
    • Enterprise Plan: Unlimited text-to-speech and regenerates.
  • If you have multiple drives, create or move your project to the Creator drive to access the Creator-level AI Speaker vocabulary and limits.
  • Voice clip limits:
    • A voice clip is considered to be any string of typed characters (250 characters or less) with a pause of 2 seconds or greater between typing, a sentence (250 characters or less) that is separated by sentence-ending punctuation, or a string of 250 characters or less that is NOT separated by ending punctuation.
  • For text-to-speech generation, paragraphs can be up to 1800 characters long. Since text-to-speech generation will happen faster for users with shorter paragraphs, it is recommended to break up paragraphs accordingly. 

After reaching the specified voice clip limit for your plan, generated speech will include "jibber jabber" in place of normal speech.