Quick summary
Descript's speaker detection feature automatically identifies distinct voices in your audio after transcription, letting you label each speaker directly in the transcript. You can trigger detection manually via audio settings and assign names to each speaker to keep your project organized.
Steps
- Open an existing project or start a new one by clicking "New Project".
- After transcription, Descript will automatically detect speakers if the audio is clear and has distinct voices.
- Go to the "Project" tab and click on the audio file you uploaded.
- Navigate to the audio settings, click "Detect Speakers," and choose the number of speakers in the audio.
- Wait for Descript to finish the speaker detection process.
- Alternatively, click "Identify Speakers" to manually trigger speaker identification.
- Add each speaker's name or select an existing name from the list, then click "Next."
- Click Close when finished — speaker labels will appear throughout your transcript.
