Podcast Transcriber (RSS or Apple Podcasts, timestamps)

Transcribe podcast episodes straight from the show's feed. Paste an RSS feed or an Apple Podcasts show link, choose how many episodes or a date range, and get timestamped text for each episode. The language is detected for you, and you can translate the speech into English. It runs on OpenAI's open-source Whisper model, so you need no API key and no account anywhere else.

Price: US$0.007 per audio minute, plus a US$0.001 run fee. A 30-minute episode costs US$0.211.

What people use it for

• Show notes and blog posts: turn every new episode into text for your website and SEO.
• Research and monitoring: search what was said across many shows, or follow a topic over time.
• AI pipelines: feed episodes to an LLM for summaries, chapters, quotes or Q&A.
• Accessibility: publish text versions of your own show.
• Back catalogues: transcribe a whole archive in one run with a date filter.

Schedule it daily with episodesPerFeed set to 1 to transcribe each new episode as it comes out.

Example output

Real output from the default input (the latest NPR News Now episode, text shortened here):

podcastTitle	episodeTitle	publishedAt	durationSec	billedMinutes	language
NPR News Now	11am ET, October 28 | The latest headlines from NPR	2026-10-28T15:09:52+00:00	286.69	5	en

{
  "podcastTitle": "NPR News Now",
  "episodeTitle": "11am ET, October 28 | The latest headlines from NPR",
  "publishedAt": "2026-10-28T15:09:52+00:00",
  "audioUrl": "https://prfx.byspotify.com/e/play.podtrac.com/npr-500005/...",
  "feedUrl": "https://feeds.npr.org/500005/podcast.xml",
  "durationSec": 286.69,
  "billedMinutes": 5,
  "language": "en",
  "model": "base",
  "text": "This is NPR News Now. The latest headlines every hour. ...",
  "segments": [
    {"start": 0.0, "end": 4.44, "text": "This is NPR News Now."},
    {"start": 4.44, "end": 7.28, "text": "The latest headlines every hour."}
  ],
  "transcribedAt": "2026-10-28T15:15:56+00:00"
}

Episodes that are skipped (too long, unreadable, over your cost limit) get a row with the reason and are not charged.

Input

Field	What it does	Default
feedUrls	RSS feed links or Apple Podcasts show links (like https://podcasts.apple.com/us/podcast/name/id1234567890). Up to 20.	1 sample feed
episodesPerFeed	How many episodes per feed, newest first, after the filters. Up to 500 per run.	1
publishedAfter	Only episodes published on or after this date.	none
titleContains	Only episodes whose title contains this text.	none
model	tiny (fast), base (balanced) or small (accurate).	base
language	auto, or a code such as en, es, de, hi, ja. Setting it improves accuracy.	auto
task	transcribe keeps the spoken language. translate outputs English.	transcribe
wordTimestamps	Add a start and end time for every word.	false
skipSilence	Skip silence and music-only parts. Faster, and fewer made-up words.	true
maxMinutesPerFile	Longer episodes are skipped without charge. A safety limit on cost.	180

Pricing

Event	Price
Run fee, once per run (per 2 GB of memory; the default is 2 GB)	US$0.001
Audio minute, fast or balanced model	US$0.007
Audio minute, accurate model	US$0.013

Minutes are counted per episode and rounded up. Examples: a 5-minute news bulletin costs US$0.036. A 60-minute episode costs US$0.421. Ten 45-minute episodes cost US$3.151.

Limits

• Public RSS feeds only. Paid, private and Apple-exclusive shows have no public feed and cannot be transcribed. Only process content you have the right to use.
• 20 feeds and 500 episodes per run, 1 GB and 600 minutes per episode.
• Speed at the default 2 GB memory: about 1 to 3 minutes of processing per 10 audio minutes on the balanced model. Raise the memory for faster runs. The run fee scales with memory.
• No speaker labels (who said what).

FAQ

Where do I find a show's RSS feed? Paste the Apple Podcasts link and the Actor finds the feed for you. Most podcast hosts also show the RSS link on the show's website.

Can I transcribe a single episode file? Use the Audio and Video Transcriber below with the direct file link.

Which languages work? Whisper supports about 99 languages. Accuracy is best for English, Spanish, German, French, Portuguese, Italian, Japanese and other widely spoken languages.

Is the audio stored? Each episode is downloaded to the run's temporary disk, transcribed and deleted. Transcripts are saved in your own Apify dataset.

Can an AI agent call it? Yes. Pass a feed, get compact JSON back, and pay per minute.

More tools from the same developer

Same style: clean JSON output, pay only for results, no charge on failed items.

Tool	What it does
Bulk Keyword Search Volume	Google Ads search volume, CPC, competition and 12-month trend for up to 10,000 keywords
Google Trends API	Interest over time, by region, and rising queries and topics for up to 500 keywords
Google SERP Results	Organic results, featured snippets and People Also Ask for any keyword, country and device
Google AI Overview Tracker	Which keywords show an AI Overview, what it says, and whether it cites your site
Audio and Video Transcriber	Timestamped transcripts from audio and video files in 90+ languages
Subtitle Generator	Ready-to-use SRT and WebVTT subtitles from audio and video files
Image OCR	Text from images in 20 languages, with confidence scores
PDF to Text and Markdown	Clean text and Markdown from PDFs, with OCR for scanned pages
Bulk PageSpeed Insights Audit	Core Web Vitals and Lighthouse scores for many pages, mobile and desktop