Add high-quality voiceover to your videos—no recording required. Just assign one of Descript's stock AI speakers to your script, and Descript will generate natural-sounding audio using the voice you choose.
This article covers:
- How to assign an AI stock speaker to your script
- How stock voices work with different languages
- Tips for previewing, swapping, and using speakers
- Limitations (legacy voices, English-only options, etc.)
This article focuses on how to assign and use stock speakers. While you can use Write mode to create a script from scratch, we only cover the steps for assigning an AI speaker here. For more info, see our articles on Write mode and Generating text-to-speech.
Add a stock speaker to your script
To generate audio with a stock voice, you’ll first need to have some script content—either by pasting it in, typing directly in the script, or using Write mode.
- Click into the script where you want to assign a speaker.
- Click the Add speaker label at the top of the paragraph (or use the
@shortcut). - Select Browse stock AI speakers from the dropdown menu.
- Choose a speaker from the list — preview the voice by clicking the play button.
Once assigned, Descript will automatically generate audio for the selected text using the chosen voice.
Language compatibility and non-English voices
Descript offers AI stock speakers in a variety of languages. To get the best results, use a speaker whose tagged language matches the language of your script.
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
To view non-English speakers, click the filter icon in the speaker list and select Show non-English speakers.
Understanding speaker characteristics
Each stock speaker is labeled with descriptive tags to help you choose the right voice for your content:
- Soothing and narrative: Ideal for calm, educational, or meditative content
- Assertive and inspirational: Great for energetic or promotional content
- Conversational or formal: Helpful for matching your brand tone or audience style
These tags help you quickly find a speaker that fits—without having to preview every voice.
Legacy stock speakers
Some older voices have been moved to a Legacy category as Descript’s AI models improve. These voices still work, but may sound less natural.
To view available legacy speakers
- Click Add speaker to open the speaker selection list
- Click the additional options icon
- Change the Legacy speakers option from Hide to Show
If you created your Descript account after a voice was moved to the Legacy list, you won’t have access to it.
Tips and limitations
- Text-to-speech usage is limited by plan. Learn how usage is calculated and what’s included in your plan →
- Stock speakers are only for generating text-to-speech. They cannot be used for regenerating audio or replacing recorded content.
- To change the speaker for a section: Click the speaker name above any text block and choose a different stock speaker. The audio will regenerate automatically using the new voice.