FeynmanLM Docs

Appearance

Podcasts ​

FeynmanLM can extract transcripts from Apple Podcasts episodes and turn them into flashcard proposals — so your podcast listening actually sticks.

Apple Podcasts only

Transcript extraction currently only works with Apple Podcasts. Other podcast apps (Spotify, Overcast, Pocket Casts, etc.) are not supported. Apple Podcasts stores transcripts locally on your Mac, which FeynmanLM reads directly — no third-party API or scraping involved.

How Episodes Are Discovered ​

FeynmanLM finds episodes through your Apple Podcasts listening history. It queries the local Podcasts database for episodes you've recently played (last 90 days) and checks whether a transcript is available.

This requires Full Disk Access in macOS System Settings → Privacy & Security → Full Disk Access (toggle FeynmanLM on).

Transcript Availability ​

Apple Podcasts downloads transcripts on demand — they are not available by default. To make a transcript available:

  1. Open Apple Podcasts on your Mac.
  2. Navigate to the episode.
  3. Click Transcript in the episode detail view. This triggers Apple to download and cache the TTML transcript file locally.

Once the transcript is cached, FeynmanLM can extract it. Episodes without a cached transcript are skipped.

Generating Flashcards ​

Once transcripts are available:

  1. Extract — The app reads the cached TTML file and converts it to plaintext with speaker labels.
  2. Generate — The AI reads the transcript and proposes flashcards focused on specific mechanisms, numbers, and trade-offs discussed in the episode.
  3. Review — Each card appears as a proposal. Accept, edit, or skip cards one at a time.
  4. Deck routing — Accepted cards are placed in the Podcasts deck, under a sub-deck named after the podcast (e.g., Podcasts → Dwarkesh Podcast).

Tips ​

  • Episodes with long-form interviews and technical discussions generate the best cards. Short news-style episodes tend to produce lower-quality proposals.
  • Make sure to open the transcript view in Apple Podcasts before trying to extract — the transcript won't be available otherwise.
  • Podcast cards always use local file paths as their source, never web URLs. This ensures cards remain tied to the actual transcript you listened to.