Podcast Transcription - RSS Feed to Text, SRT & VTT

✅ Tested daily with its default input (Apify's automated QA plus our own smoke test before every release).

Podcast transcription straight from an RSS feed: paste one or more podcast RSS feed URLs and this Actor transcribes the newest episodes with Whisper AI speech recognition. Each episode comes back with the full transcript, SRT and VTT subtitles with timestamps and the episode metadata, for $0.0059 per audio minute (under a cent).

How it works

1. Reads the RSS feed and sorts episodes newest first.
2. Takes the audio file the publisher lists for each episode (the <enclosure> in the feed).
3. Transcribes it with Whisper (base for speed, small for higher accuracy). 99 languages, automatic language detection.
4. Writes one dataset row per episode.

Input

Field	Description
feedUrls	Public podcast RSS feed URLs (not Spotify/Apple/YouTube page links). The audio file in each episode's
maxEpisodes	Number of episodes per feed, newest first. Cost scales with total audio minutes, so start with 1.
model	Whisper model: base = fast, $0.0059 per audio minute; small = more accurate, $0.0155 per audio minute.
language	Optional ISO 639-1 code of the spoken language, e.g. 'en', 'de', 'nl'. Empty = auto-detect.
maxMinutesPerEpisode	Transcribe only the first N minutes of each episode (0 = whole episode). You pay only for the minutes transcribed, so this caps cost per episode.

Output (one row per episode)

{
  "feed_title": "NPR News Now",
  "episode_title": "1pm ET, October 23 | The latest headlines from NPR",
  "pub_date": "Fri, 23 Oct 2026 17:34:40 +0000",
  "audio_url": "https://.../default.mp3",
  "duration_s": 317.7,
  "language": "en",
  "text": "This is NPR News Now. The latest headlines every hour ...",
  "srt": "1\n00:00:00,000 --> 00:00:04,400\nThis is NPR News Now.\n...",
  "vtt": "WEBVTT\n\n00:00:00.000 --> 00:00:04.400\n...",
  "model": "base",
  "billed_minutes": 6
}

Pricing (pay per event)

Event	Price
Transcription with Whisper base	$0.0059 per audio minute
Premium transcription with Whisper small	$0.0155 per audio minute

Billing is per started minute of audio that was actually transcribed (with maxMinutesPerEpisode you pay only for the capped part). Episodes that fail to download or transcribe are not charged. Higher Apify plans get lower prices.

Use cases

• Searchable archives and show notes for podcasters
• Subtitles for audiograms and video clips
• Monitoring what is said in industry or news podcasts
• Feeding podcast content into search, summaries or LLM pipelines

Notes

• Only the audio files published in the RSS feed are used. Pages of video or streaming platforms (YouTube, Spotify, SoundCloud ...) are not supported.
• Make sure your use of the transcripts respects the podcast's copyright and terms.
• Speech recognition: Whisper (OpenAI, MIT license) via faster-whisper.

Use with AI agents (MCP)

This Actor can be used as a tool by AI agents (Claude, Cursor, VS Code, other MCP clients) through the official Apify MCP server:

• Add only this Actor as a tool: https://mcp.apify.com?tools=admirala/podcast-rss-transcriber (sign in with OAuth or an Apify API token).
• Or connect https://mcp.apify.com and let the agent find it with search-actors (e.g. "podcast transcription"), read the input schema with fetch-actor-details and run it with call-actor.

Example input an agent can pass:

{
  "feedUrls": [
    "https://feeds.npr.org/500005/podcast.xml"
  ],
  "maxEpisodes": 1,
  "model": "base"
}

Cost per call: $0.0059 per transcribed audio minute (base) or $0.0155 (small). Use maxMinutesPerEpisode to cap cost; failed episodes are free. Results come back as dataset items (get-dataset-items).

FAQ

How do I transcribe a podcast episode to text? Paste the show's RSS feed in feedUrls and set maxEpisodes. The audio file listed in the feed is transcribed with Whisper.

How much does podcast transcription cost? $0.0059 per audio minute with the base model, so a 30-minute episode is about $0.18. The small model costs $0.0155 per minute.

Can I get SRT or VTT subtitles for a podcast? Yes, every episode row includes srt and vtt with timestamps besides the plain text.

Does it work with Spotify or YouTube podcast links? No, only public RSS feeds and the audio files they publish.

Related actors

• RSS Feed Reader - RSS & Atom to JSON (bulk, auto-discovery) (coming soon to Apify Store)
• YouTube Transcript & Audio to Text (Whisper) - SRT/VTT
• YouTube Transcript Scraper - Text, Timestamps & SRT (coming soon to Apify Store)

More examples

Ready-to-run Python, curl and MCP examples with real sample output: https://github.com/AdmiraalA/apify-scrapers-examples