I don't like podcasts. I tune out after about 30 seconds of chit chat and intros and blah blah blah and end up missing stuff and can't search for it or copy and paste it.
Agreed. It's so annoying having good content buried in audio. For interviews of note on youtube, last week I cracked and spent 2 hours writing a yt-dl based ripper that converts the whole thing in to an html linkified webpage via intermedia VTT, opening the resulting subtitles based transcript file in the browser so you can easily scan and click anywhere you want to see the video and it will open in a new window at exactly that point. Not perfect but saves AGES.
I run MacWhisper on my laptop, and often dump podcast MP3s into it, extract the Whisper transcript and then feed that through a long context model like Claude 3 Haiku/Opus or Gemini Pro 1.5/Gemini Flash using my https://llm.datasette.io/ tool to answer questions against that transcript.
I don't like podcasts. I tune out after about 30 seconds of chit chat and intros and blah blah blah and end up missing stuff and can't search for it or copy and paste it.