Automatic transcripts are great, but manually adding speaker labels was a drag. So, we created the Speaker Detective — speaker labels powered by AI.
Using Speaker Detective
Drag a file into a Composition and a transcription confirmation window will appear. Click the Enter Speaker Name text box, then mouse over Detect Speakers and select the number of speakers on the track.
The Speaker Detective will run as your file is automatically transcribed. Typically, a 60-minute file takes 2–3 minutes. A notification will alert you when it’s done.
Speaker Detective is officially supported with files less than 2 hours long, and requires a minimum file length of 30 seconds
When the notification appears, click Identify speakers.
When prompted, click the Get started button and then listen through the audio prompts to identify who’s speaking. Add the speaker's name, or select an existing name from the list.
When you’ve listened to all of the clips, click Close and the Speaker labels will appear in your transcript.
Your speakers are now labelled! Once you add labels, Descript will remember them and apply them intelligently even as you cut, copy, and paste among compositions.
To learn more about adjusting and making corrections to your speaker labels, check out our Speaker Labels article for helpful tips.
How to initiate speaker detective after transcribing a file
If you didn't identify speakers when initially transcribing your file, you can still do it afterwards.
To do so, click on the Project Sidebar icon in the top-left corner of the screen and click to open the Project Files folder. Right-click on the file in question, then select Detect Speakers to begin the process. If Speaker Detection has already been processed on your files, choose Identify speakers instead.
Speaker Detective and Transcription limits
Running Speaker Detective does not use up any of your transcription time, so it won't get you closer to your monthly limit.