How to transcribe a podcast to text

Transcribe Video to Text · 4 min read

You heard something good in an hour-long episode and now you need the exact words. Here's how to turn a podcast into readable text with speaker labels and timestamps, straight in your browser, on Spotify, Apple Podcasts, SoundCloud or the show's own page.

Podcasts are built for listening, not for reading. Some shows publish a transcript, some platforms generate one, but coverage is patchy and the text is usually stuck inside the player: no speaker separation, no timestamps you can copy, no export. If you want to quote an episode, search it for a name, or feed it to an AI for a summary, you need the text as a file.

The fastest way: transcribe it while it plays

Transcribe Video to Text is a free Chrome extension that listens to the tab you're playing and writes the transcript as the episode runs.

1. Add the extension to Chrome.
2. Open the episode in the browser: Spotify Web Player, Apple Podcasts on the web, SoundCloud, or the podcast's own site. Press play.
3. Click the extension icon. A side panel opens next to the page.
4. Press Transcribe. Text starts appearing within a few seconds, split by speaker and stamped with the time.
5. Copy what you need, or export the whole episode to Word, TXT or SRT.

Nothing is uploaded from your computer and there's no file to prepare. The audio is read from the tab that's already playing.

Platform by platform

• Spotify: use the Web Player at open.spotify.com, not the desktop app. The extension works on pages inside the browser.
• Apple Podcasts: episodes play on the web at podcasts.apple.com. Add /us/ in the address if you want the English interface.
• SoundCloud: plays in the browser by default, so it works as-is.
• The show's own site: most podcast pages embed a plain web player, which is the easiest case of all.
• Phone apps: not covered. This is a Chrome extension, so the episode has to play in a browser tab on a computer.

Two honest limits

Length. One session runs up to 40 minutes. Plenty of shows fit inside that; a two-hour interview does not, so you transcribe it in parts and stitch the exports together.

What it costs. Podcast platforms carry no captions, so the episode is transcribed by AI, and that draws on the free monthly allowance included with the extension. YouTube and Vimeo are different: they have their own captions, so transcripts there are free and unlimited. If you're deciding what to run through the allowance, this is the difference worth knowing.

What you get out of it

• Search the episode. Ctrl+F for a name, a company, a number, instead of scrubbing the timeline.
• Quote it exactly, with the timestamp already attached.
• Know who said what. Interviews come out labelled speaker by speaker.
• Summarize it. Paste the transcript into ChatGPT or Claude and ask for the key points, the text is what those tools actually need.
• Keep notes that last. Word or TXT sits in your own files, not in someone's player.

Works beyond podcasts

The same extension transcribes video across most of the web. See getting a YouTube transcript, a Vimeo transcript, or a Zoom recording for the same steps elsewhere.