Field note

Lexicap at home

The instinct to transcribe a whole podcast archive is not new. Karpathy did it by hand in 2022. What changed is that you can now do it overnight, on your own machine, for every show you follow.

What Karpathy did by hand

In 2022 Andrej Karpathy downloaded all ~322 episodes of the Lex Fridman podcast, ran them through Whisper, and published the transcripts as a site he called Lexicap - raw VTT included for anyone else who wanted them. [1]

The point was not the site. The point was the instinct: a podcast locked in audio is not searchable, not quotable, not linkable. Transcribe the whole thing and it becomes text you can actually work with.

The effort was the problem

Lexicap took a cloud pipeline and a lot of manual work to convert one show. That is fine for a one-off by someone who wanted to prove a point.

It does not scale to the ten shows you actually follow. Nobody hand-runs a back-catalogue through a cloud transcriber every week - the effort, and the per-minute bill, stop you before you start.

Batch it on your Mac

Vocateca does the same audio-to-text step on-device. Subscribe to a show by its Apple, Spotify or RSS address and it transcribes new episodes as they publish, and backfills the archive behind them.

A whole back-catalogue is just disk space and a night of compute - no upload, no per-minute fee. Timestamps and speakers survive, and the output exports straight to Markdown, SRT, VTT or JSON.

Own the archive

Karpathy named the underlying problem in the same breath: so much information is locked up in opaque audio files. [2] A local transcript library answers that - accessible, searchable, and yours.

Audio behind an app can be taken down or moved. A folder of plain-text transcripts you own does not rot, greps in a second, and is the substrate everything downstream - a knowledge network, an LLM query, a citation - is built from.

Andrej Karpathy is not affiliated with Vocateca and does not endorse it. The references above are cited for commentary; Lexicap is his own independent project.

Sources

  1. [1]Andrej Karpathy, X post announcing Lexicap, 26 September 2022. https://x.com/karpathy/status/1574474950416617472 Accessed 11 July 2026.
  2. [2]Andrej Karpathy, X post on audio being opaque, 26 September 2022. https://x.com/karpathy/status/1574474952446615552 Accessed 11 July 2026.