Skip to main content
Speakers is getting a UI update!This is rolling out progressively. Your app may look slightly different in the meantime.
Select voice dialog with a selected voice, preview buttons, filters, and Save.

​
Choose a stock voice

  1. Click the Add speaker button.
  2. Select New speaker.
  3. Click create or choose voice.
  4. Select a voice:
    • Recommended speakers: Descript’s curated library of stock voices.
    • Additional results: available ElevenLabs community voices*
  5. Click the play button to preview the voice. Click the list result to apply the voice to the Speaker.
  6. Click Save.
Descript will use this voice to generate text-to-speech audio.
*Community voices are owned by individual contributorsVoice owners can remove them from the shared ElevenLabs community voice catalog at any time, making them unavailable for future use.For a voice you plan to use across projects, choose one from Descript’s short list of Recommended voices.

​
Language compatibility and non-English voices

Descript offers stock voices in a variety of languages. To get the best results, use a voice whose tagged language matches the language of your script. Some voices are designed for a specific language. Audio may still generate if the languages don’t match, but it may sound less natural or lose the intended tone. See supported text-to-speech languages