Set up Descript for Analysing Health Podcasts in 8 minutes

This guide configures Descript to create a searchable transcript of any health podcast, making research fast and precise.

8 minutes start to finish
Descript setup — Set up Descript for Analysing Health Podcasts in 8 minutes

Listening to health and science podcasts keeps you informed, but finding a specific data point later is difficult. Manually scrubbing audio is slow and imprecise. This setup uses Descript to create a searchable transcript, letting you extract key protocols or study references in seconds.

Before you start

  • A Descript account
  • An audio or video file of a podcast episode
  • 8 minutes for setup and transcription

The steps

  1. 01

    Create a New Project

    In your Descript workspace, select `New` and then `Classic Project`. Name it after the podcast episode you're analysing, for example, "Peter Attia Drive - Exercise & Longevity".

  2. 02

    Upload and Transcribe Your Audio

    Drag your podcast audio file into the new project. Descript automatically starts transcribing; you can accept the prompt to identify speakers, which aids analysis later.

  3. 03

    Correct Key Health Terms

    Once the transcript appears, scan it for misspellings of medical or scientific terms (e.g., "lipopolysaccharide," "NAD+"). Use the `Find and replace` function to fix these across the entire transcript for more accurate searches.

  4. 04

    Search for Key Information

    Use the top search bar (Cmd/Ctrl+F) to find topics, supplements, or protocols. This turns the episode into a personal "Ledger" of information, part of the 3-Layer Method, letting you find every mention of "creatine" or "sauna" without re-listening.

  5. 05

    Highlight and Extract Insights

    When you find a useful section—like a specific dosage recommendation or a summary of a study—highlight the text. You can copy the text directly or right-click to export the selection as a shareable audio/video clip.

Honest note

Descript's AI transcription is strong but not flawless, especially with non-English accents or highly technical jargon; always double-check critical details like dosages or chemical names. The tool is for research and content creation, not for diagnosis or clinical interpretation.

Want the whole stack, not just one tool?

The free 10-Day Challenge wires these together. Or join the free 45-min live workshop and watch me build it end-to-end.

Want the whole method, not just one tool?

The free 10-day email challenge installs Research → Ledger → Protocol on whatever data you already collect.

More for people setting up their stack

Based on what you've been reading — always learning.

See all →