Andy Anderegg
Jul 12 · 2 min read

Automatic transcription is fast, cheap, and 95% accurate — but manually adding speaker labels is a drag. With Descript’s new AI Speaker Detective, we do it automatically.

To get the new version, open or restart Descript and you’ll be prompted to update, or download it here.

How it works

Add a file and check the box.

Import a file into Descript and select Detect multiple speakers
Import a file into Descript and select Detect multiple speakers

In a minute or two, Descript will let you know how many speakers it’s detected — 2, 5, 12! Your job is to name who’s who.

Run the Speaker Detective to quickly name each speaker. Use Enter
to continue and your hands will never leave the keyboard.

Like any detective, the Speaker Detective isn’t perfect — that’s why we’ve made it easy to make corrections. If a label is off by a word or two, just drag it to the correct boundary and your script will update.

Edit away! Once you add labels, Descript remembers and intelligently applies them even as you cut, copy, paste, cut, paste, delete, copy, paste across compositions.

Try it. The Detective runs as your file is transcribed, so you’ll still get an automatic transcription in minutes, now with smart speaker labels.

🎉No more manual labelling!

New to Descript? Sign up now and transcribe 30 minutes for free.

Descript

The Descript Blog

Andy Anderegg

Written by

Head of Content at Descript

Descript

Descript

The Descript Blog

Welcome to a place where words matter. On Medium, smart voices and original ideas take center stage - with no ads in sight. Watch
Follow all the topics you care about, and we’ll deliver the best stories for you to your homepage and inbox. Explore
Get unlimited access to the best stories on Medium — and support writers while you’re at it. Just $5/month. Upgrade