Transcribe a whole podcast from its feed

Paste a show link — RSS feed, Apple Podcasts show, or Spotify show — and Podskrift lists the episodes. Pick one, get the transcript, then come back for the next. Jobs keep running if you close the page; finished transcripts sit in History.

How it works

  1. Paste the show link

    An RSS feed URL, an Apple Podcasts show link, or a Spotify show link. Podskrift opens the episode list with titles, dates and lengths.

  2. Pick an episode

    Choose one episode at a time and start the transcript. There is no “transcribe all” button — each job is one episode.

  3. Collect transcripts in History

    Each job keeps running if you close the page. Download .txt or .srt per episode from History when it finishes.

Questions

Can I transcribe every episode of a show?

Yes, episode by episode. Paste the show or feed link, pick an episode, start the job, then pick the next. There is no single bulk button that queues the whole catalogue at once.

What does it cost for a whole show?

Minutes are charged per episode length — a two-hour episode uses about two hours of minutes. Start free, no card needed. After that, minutes are a one-time purchase: from $1.50 for 60 minutes, cheaper per minute the more you buy (1,200 min for $11), or just the minutes one episode needs. No subscription. You can also add your own OpenAI API key and pay OpenAI directly instead; that is optional. Minutes never expire.

Can ChatGPT or Claude fetch several episodes for me?

Yes. Connect Podskrift as an MCP connector, then ask for episodes one after another (list_episodes, then get_transcript). Setup is on the AI page.

Does this work for my own podcast?

Yes. Paste your public feed and transcribe episodes for show notes or captions. The RSS landing page covers creator workflows in more detail.

What about private or subscriber-only feeds?

Private feeds that need a separate login, password-protected feeds, and Spotify exclusives without a public RSS feed cannot be transcribed. Only public feed audio works.

Which languages work?

28 languages in the picker. Choosing the spoken language yourself usually beats auto-detect on short or accented audio.

Is there speaker labelling?

Not yet. You get one continuous transcript with timestamps, not named speakers.

Do I need an OpenAI API key?

No. An API key is optional; you can use free minutes or buy minutes instead.