Podcast Transcripts

Get the transcript of podcast episodes as clean text, or as timestamped segments, from any of:

• Apple Podcasts URLs: a show (podcasts.apple.com/.../id1200361736) for its latest episodes, or an episode (with ?i=...).
• Podcast names: found on Apple Podcasts, as its search finds them.
• RSS feeds: any podcast's feed, Apple-listed or not, which covers Spotify's too when the show has a public feed.
• Audio files: a direct .mp3 or .m4a URL.
• Episode search: words searched across Apple Podcasts' episodes.

The speech-to-text runs inside the actor: OpenAI's Whisper model, open source, on Apify's servers. Nothing is sent to an outside AI service. It detects the language spoken in each episode, among about 100. Long episodes are transcribed in full, ten minutes at a time.

Every result also carries the episode's title, date, duration, show notes, season and number, image and audio link, and the podcast's title, author, categories, website, feed and Apple IDs.

It costs $0.003 per minute of audio on Apify's paid plans ($0.006 on the free plan) with Whisper base, and $0.008 ($0.016) with Whisper small, counted in started minutes: a 40-minute episode is $0.12. Episodes without speech are free.

What people use it for

• AI and LLM pipelines: summaries, RAG over a show's back catalogue, training data.
• Research and monitoring: what's said about a company, product or topic across podcasts.
• Repurposing: show notes, blog posts, newsletters, quotes and subtitles from episodes.
• Accessibility and search: a searchable text archive of a show.

How to transcribe podcasts

1. Click Try for free; Apify's free plan covers a first run.
2. Fill in Podcasts and episodes, Search episodes or both, and how many episodes you want from each.
3. Click Start, then download the results as JSON, CSV, Excel or HTML, or read them through the API.

Published after keeps only newer episodes. Max minutes per episode transcribes and charges only each episode's first minutes. Speech-to-text model picks between Whisper base, fast and good on clear speech, and Whisper small, more accurate on accents, crosstalk, names and languages other than English, and about three times slower. Language fixes the language spoken when you know it; otherwise each episode's is detected. Turn on Include timestamps for segments, each line with its start and end.

{
  "podcasts": [
    "https://podcasts.apple.com/us/podcast/the-daily/id1200361736",
    "Huberman Lab",
    "https://feeds.npr.org/500005/podcast.xml"
  ],
  "searchTerms": ["interest rates"],
  "maxEpisodes": 5,
  "publishedAfter": "2026-10-01",
  "model": "base",
  "includeTimestamps": true
}

Output

{
  "podcastTitle": "The Daily",
  "podcastAuthor": "The New York Times",
  "podcastAppleId": "1200361736",
  "podcastAppleUrl": "https://podcasts.apple.com/us/podcast/the-daily/id1200361736",
  "feedUrl": "https://feeds.simplecast.com/Sl5CSM3S",
  "categories": ["Daily News", "News"],
  "podcastWebsite": "https://www.nytimes.com/the-daily",
  "podcastLanguage": "en",
  "episodeTitle": "Want to Enjoy Music More? Go For a Run.",
  "publishedAt": "2026-11-01T11:00:00Z",
  "durationSeconds": 2384,
  "episodeType": "full",
  "explicit": false,
  "description": "Ben Ratliff, a music critic and avid runner, always ran in silence. …",
  "guid": "92c4c6cb-4077-4a0e-bf32-12a44d1dd1f2",
  "audioUrl": "https://dts.podtrac.com/redirect.mp3/…/default.mp3",
  "imageUrl": "https://image.simplecastcdn.com/images/…/3000x3000/….jpg",
  "episodeAppleId": "1000799212333",
  "episodeAppleUrl": "https://podcasts.apple.com/us/podcast/want-to-enjoy-music-more-go-for-a-run/id1200361736?i=1000799212333",
  "input": "https://podcasts.apple.com/us/podcast/the-daily/id1200361736",
  "language": "en",
  "languageProbability": 0.99,
  "text": "There's rewarding, and then there's remarkably rewarding with Chase Sapphire Reserve. …",
  "transcribedSeconds": 2384,
  "isComplete": true,
  "billedMinutes": 40,
  "segments": [{"start": 0.82, "end": 6.44, "text": "There's rewarding, and then there's remarkably rewarding with Chase Sapphire Reserve."}]
}

An episode stopped short by Max minutes per episode, the run's spending limit or its timeout comes with what was transcribed, isComplete: false, its transcribedSeconds and a stoppedBecause, and is charged only for those minutes. An episode without speech, or whose audio can't be fetched, comes with its details and a noTranscriptReason, and costs nothing.

Use it as an API

Apify's API starts a run and returns its dataset as JSON; its Python and JavaScript clients, and its Make, Zapier and n8n integrations, work the same way. Long episodes take minutes, so start a run and read its dataset when it ends.

curl -X POST "https://api.apify.com/v2/acts/pikoulas~podcast-transcripts/runs?token=YOUR_APIFY_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"podcasts": ["https://podcasts.apple.com/us/podcast/the-daily/id1200361736"], "maxEpisodes": 1}'

AI agents can call it as a tool through Apify's MCP server: https://mcp.apify.com?tools=pikoulas/podcast-transcripts.

How much does it cost to transcribe a podcast?

With Whisper base you pay $0.003 per started minute of audio on Apify's paid plans, and $0.006 on the free plan: an hour-long episode is $0.18 ($0.36 on the free plan). Whisper small, which takes about three times the computing, is $0.008 per started minute ($0.016 on the free plan). billedMinutes shows each episode's. Episodes without speech are free, and so is everything else the run fetches. The only other charge is traffic through Apify's residential proxy, at $0.0012 per 100 KB, only when you set it yourself; audio files never go through it. There are no monthly fees.

The run stops at the spending limit you set, mid-episode if need be, and charges only what it transcribed.

Good to know

• Whisper writes what it hears: names, jargon and crosstalk can come out wrong, and Whisper small gets more of them right. Speakers aren't told apart.
• A run transcribes about 20 minutes of audio a minute with Whisper base at the default 8 GB of memory, and about 7 with Whisper small. More memory is faster, at the same price per minute. The default timeout of an hour covers about 20 hours of audio with base; raise it for more.
• Ads in the episode are transcribed with the rest, as they're part of the audio.
• A podcast's episodes come from its feed, newest first, as far back as the feed goes; Apple's latest 200 when the feed fails.
• An episode found twice in one run, by URL and in its show say, is given once.
• Paid, subscriber-only episodes can't be read.

FAQ

Is it legal to transcribe podcasts?

It reads only what podcasts publish openly in their feeds, without logging in. Episodes are their creators' copyrighted work: a transcript for your own research, analysis or accessibility is often allowed, depending on your country's copyright law, but republishing it may need the rights holder's permission, and personal data in it is protected by laws such as the GDPR and the CCPA. If you're unsure, ask a lawyer; Apify's Is web scraping legal? is a good start.

Something missing or not working?

Open an issue on the Issues tab with the input you used, or ask there for a field you need.