Yesterday I wrote a piece that required some transcripts from a podcast. Unfortunately, the Ringer doesn’t seem to publish transcripts. I could have pulled subtitles from YouTube, but a) I didn’t think of that and b) I was in a series of online meetings with moments of free time.

Seemed like a perfect time for an AI to help!

From partial attention to a transcript

Despite Anthropic having a rough month, I keep finding Claude Code to be the fastest way to whip up quick experiments. Here was the process.

Try to get any of the frontier models to just get me a transcript.

I need a transcript of https://www.theringer.com/podcasts/the-press-box/2025/09/18/jimmy-kimmel-is-suspended-molly-qerim-leaves-espn-and-ivan-maisel-on-the-cult-of-the-college-football-coach can you help me?

Gemini’s Deep Research response was a very complete description of the show, sections, speakers, and guests, but no transcript.

Bummer.

ChatGPT’s response was quite clear about what would happen I’m sorry, but I can’t provide a full transcript of that podcast episode. Would you like me to give you a summary of the key points instead?

Hmm.

Can you download it from rss and transcribe it?

No, but useful response.

I can’t directly fetch and download the audio from The Ringer’s RSS feed for you, but here’s how you can do it yourself:

1. Get the RSS Feed
	•	The Press Box feed is public: RSS link.
	•	You can open that in any podcast app, or in a browser to see episode entries.

2. Find the Episode
	•	Look for the entry dated Sept 18, 2025:
“Jimmy Kimmel Is Suspended, Molly Qerim Leaves ESPN, and Ivan Maisel on the Cult of the College Football Coach.”
	•	Inside the <enclosure> tag of the RSS item you’ll see a direct .mp3 link.

3. Download the Audio
	•	Copy that .mp3 URL into your browser → right-click → “Save As.”
	•	Or, use a podcast app (Apple Podcasts, Pocket Casts, Overcast, etc.) that lets you download episodes offline.

4. Transcribe

Once you have the .mp3, you can upload it here and I can generate a transcript for you.

Lies. While RSS got me the direct link to the .mp3, trying to upload the file directly to the models failed, likely because it was too big.

Build a tool

Spun up Claude Code. Started with my usual approach of having a discussion. I didn’t record all of this, which was a mistake but it was roughly:

“I’d like to make a node tool that can transcribe a podcast into a well structured markdown document”
Back and forth about technology, converge on ffmpeg to chunk up audio, use gemini for transcription
Argument with Claude about using the right Gemini SDK
Demonstrate transcription worked but realize it needs clear speakers
Adjust prompt and generate chunks with overlaps to preserve speakers, plus a final Gemini call to clean up speaker attribution
Add caching so when it hits bugs we’re not splitting or converting sections already complete

And kapow, a transcript!

Total time was a few minutes of typing during breaks between calls. Then about 10 minutes of cleanup work at the end to get it ready to open source. While writing this, I realized a good experiment would be to ask Claude to add some test coverage and in it went.

Would an AI browser have been even easier?

Probably, but until the lethal trifecta is closed for good, AI browsing terrifies me.