When you record a conversation with multiple speakers in a single audio or video file, labeling who said what can be tedious. Descript can automatically detect different speakers in your transcript and help you label them. You’ll identify each speaker once, and Descript will apply those labels throughout your project.
This article covers
- How speaker detection works
- Speaker detection modes (automatic vs. manual)
- Detect and identify speakers
- Label speakers after transcription
How speaker detection works
Speaker detection works in two steps:
- Detect — Descript’s AI identifies different speakers in your recording.
- Identify — You assign a name to each speaker.
By default, automatic speaker detection is enabled in your App Settings. Descript will detect speakers automatically when you import and transcribe a file. Once detection finishes, you’ll identify each speaker by name, and Descript will apply those labels throughout your transcript.
Speaker detection modes
Speaker detection works differently depending on your selected mode (automatic or manual). This App setting can be different between web and desktop apps, so check your settings in both Descript for Web and the desktop app.
| Automatic detection (default) | Manual detection |
|---|---|
| Runs automatically without asking for the number of speakers | Prompts you to select the number of speakers first |
| Up to 5 hours | Up to 3 hours |
| Always ask before detecting speakers is OFF | Always ask before detecting speakers is ON |
If your file exceeds these limits, the Detect speakers option will be disabled. You can check this by right-clicking the file — a tooltip will explain the time restriction.
Detect and identify speakers
Once you’ve imported your file into a project, use these steps to have Descript automatically label your speakers.
- When detection is complete, you’ll get a notification. Click Identify speakers.
- The Identify speakers modal will open. Add the speaker’s name, or select an existing name from the list.
- When you’ve listened to all the samples, click Close.
- Add the file to your script panel — the speaker labels will appear automatically in your transcript.
After you add speaker labels, Descript remembers them and applies them intelligently as you edit — even when you cut, copy, and paste among compositions.
Label speakers after transcription
If you have automatic speaker detection disabled, you can still run detection manually from the Project File actions menu. Click the ellipsis next to your file in the Project panel and select Detect speakers.