Podcast Transcript Scraper: Any Podcast to Text & SRT

What does Podcast Transcript Scraper do?

Podcast Transcript Scraper turns any podcast into text. Type the podcast's name, or paste its Apple Podcasts link or RSS feed, and get the newest episodes transcribed: full transcript, timestamped segments, Markdown with timestamps and SRT/VTT subtitles, together with the podcast name, episode title and publish date.

It finds the podcast's public RSS feed automatically and transcribes the audio with open-source Whisper in 99 languages, so there is no OpenAI key and no subscription. Schedule it daily and it transcribes only new episodes. You pay per minute of audio, and failed episodes are never billed.

It runs on the Apify platform, so you also get an API, scheduling, integrations (Google Sheets, Make, Zapier, n8n, Notion via webhooks) and access for AI agents through the Apify MCP server.

Why use it?

• 📰 Monitor podcasts in your industry: get every new episode of 10 or 50 shows as searchable text each morning.
• ✍️ Content repurposing: turn your own episodes into blog posts, show notes, newsletters and social clips.
• 🔎 Research and media monitoring: search what guests said about your company, competitors or a topic.
• 🤖 RAG and AI assistants: chunks output with timestamps, ready for a vector database.
• 🧠 Optional AI insights: summary, key points, chapters with start times and action items for each episode (Claude, with your own Anthropic key).

How to get a podcast transcript

1. Click Try for free.
2. In Podcasts, type a podcast name (e.g. Lex Fridman Podcast) or paste its Apple Podcasts link or RSS feed.
3. Choose how many of the newest episodes to transcribe in Episodes per feed.
4. Click Start, then download the transcripts as JSON, CSV or Excel, or as .txt / .srt files with Also save downloadable files.
5. To get new episodes automatically, create a schedule (for example daily). With Only new episodes on, each run transcribes and bills only episodes it has not seen before.

Input

Field	Description	Default
podcastFeeds	Podcast names, Apple Podcasts links or RSS feed URLs	required
maxEpisodesPerFeed	How many of the newest episodes per podcast	3
onlyNewEpisodes	Skip episodes transcribed by previous runs	true
model	base (recommended), small (most accurate) or tiny	base
language	Spoken language code or auto	auto
outputs	text, markdown, segments, srt, vtt, chunks	text, segments
vocabulary	Names and jargon to recognise better (hosts, guests, products)	-
aiInsights + anthropicApiKey	AI summary, chapters and action items	off
maxDurationMinutes	Transcribe (and bill) at most N minutes per episode	240

{
  "podcastFeeds": ["Lex Fridman Podcast", "https://feeds.npr.org/500005/podcast.xml"],
  "maxEpisodesPerFeed": 2,
  "outputs": ["text", "srt"]
}

Output

One row per episode. You can download the dataset in various formats such as JSON, HTML, CSV, or Excel.

{
  "podcast": "NPR News Now",
  "episodeTitle": "NPR News: 09-24-2026 8AM EDT",
  "published": "2026-09-24T12:00:00+00:00",
  "audioUrl": "https://play.podtrac.com/npr-500005/...mp3",
  "feed": "https://feeds.npr.org/500005/podcast.xml",
  "status": "ok",
  "language": "en",
  "durationSeconds": 297.1,
  "billedMinutes": 5,
  "text": "Live from NPR News in Washington, I'm ...",
  "markdown": "**[00:00:00]** Live from NPR News in Washington ..."
}

Data fields

Field	Description
podcast, episodeTitle, published	Episode metadata from the RSS feed
audioUrl, feed	Episode audio file and its feed
text / markdown	Full transcript, plain or with timestamps
segments	Timestamped segments (optionally word-level)
srt / vtt	Subtitle files
chunks	RAG-ready passages with start/end times
insights	AI title, summary, key points, chapters, action items (optional)
durationSeconds, billedMinutes	Episode length and minutes charged

How much does a podcast transcript cost?

Event	Price
Run start (per GB of memory, default 4 GB)	$0.0005
Audio minute, base or tiny model	$0.006 ($0.36 per hour)
Audio minute, small model	$0.012 ($0.72 per hour)
AI insights per episode (optional; Claude usage billed to your own key)	$0.01

A 1-hour episode with the base model costs about $0.36. Failed episodes and episodes with no speech are free. Use maxDurationMinutes to cap long episodes, and Max cost per run to cap a whole run.

Use it with AI agents (MCP)

Add https://mcp.apify.com?tools=fguiraud/podcast-transcript-scraper to Claude, Cursor or any MCP client and ask: "Transcribe the latest episode of the Lex Fridman Podcast and summarise the main arguments."

Need to transcribe other audio or video?

For meetings, interviews, voice notes, MP4 videos and files sent as base64, use Audio & Video to Text Transcription, built on the same engine.

FAQ and limitations

• Which podcasts work? Any podcast with a public RSS feed, which covers almost every podcast on Apple Podcasts. Spotify-exclusive shows have no public feed and are not supported.
• The name matched the wrong podcast. Paste the Apple Podcasts link or the RSS feed instead of the name.
• Who is speaking? Speaker labels (diarization) are not included yet.
• Copyright: transcripts are for your own research, accessibility and analysis. Check the podcast's terms before republishing its content.
• Found a problem or need a feature? Open an issue on the Issues tab. Replies within 48 hours.