Podcast Show Notes Generator — AI Transcription & Chapters

Pricing

Rating

Developer

Actor stats

Categories

Share

Submit any podcast episode URL — mp3, m4a, RSS feed link — and get back a full transcript, structured show notes, timestamped chapters, speaker-attributed guest quotes, and SRT/VTT subtitle files saved to your Apify Dataset.

The Podcast Show Notes Generator uses the Wisprs API to transcribe audio directly from episode URLs using Whisper-based speech-to-text. Unlike tools that rely on pre-existing transcripts, Wisprs transcribes the actual audio — which means it works for every episode, whether or not the host has published a transcript. Accuracy is excellent on clear audio; results vary by language, accent, and recording quality.

What does this Actor do?

The dirty secret of podcasting is that the episode itself is the easy part. A typical post-production workflow takes 3–5 hours of mechanical work after recording. This Actor collapses that entire workflow into two API calls.

1. Submit episode URLs from your input
2. Queue each for async transcription (handles episodes of any length — no timeout)
3. Generate structured show notes including:
   • Summary — 2–4 sentences capturing the episode's core argument
   • Chapters — timestamped chapter markers with titles and descriptions
   • Quotes — top verbatim guest quotes with speaker attribution and timestamps
   • Show notes markdown — ready to paste directly into your CMS or podcast host
4. Export the transcript in your chosen formats: TXT, SRT, VTT, JSON, Markdown
5. Save everything to your Apify Dataset — one row per episode

How do I generate podcast show notes automatically?

Enable repurposeMode: "show-notes" and diarize: true for speaker-labeled output:

{
"startUrls":[{"url":"https://your-podcast-host.com/episode.mp3"}],
"language":"auto",
"diarize":true,
"exportFormats":["txt","srt"],
"repurposeMode":"show-notes"
}

The dataset row will contain structured show notes in repurposed_show-notes, the full transcript in transcript_txt, and SRT subtitles in transcript_srt.

How do I transcribe a podcast back-catalog in bulk?

Add all episode URLs to startUrls. The Actor processes them sequentially with no timeout — ideal for batch-transcribing an entire show archive:

{
"startUrls":[
{"url":"https://feeds.buzzsprout.com/.../episode-1.mp3"},
{"url":"https://feeds.buzzsprout.com/.../episode-2.mp3"},
{"url":"https://feeds.buzzsprout.com/.../episode-3.mp3"}
],
"diarize":false,
"exportFormats":["txt","md","srt","vtt"]
}

Each episode saves as one row with the full CMS-ready transcript. A 100-episode back-catalog at 45 minutes each costs approximately $75.50 with show notes.

How do I build an RSS-to-CMS automation?

Pass a webhookUrl to receive results as each episode completes. Combine with an RSS monitoring Actor to trigger transcription on new episode publish:

{
"startUrls":[{"url":"https://your-podcast-host.com/new-episode.mp3"}],
"diarize":true,
"exportFormats":["txt","srt"],
"repurposeMode":"show-notes",
"webhookUrl":"https://your-n8n-instance.com/webhook/podcast-complete"
}

Every episode gets show notes posted to your CMS on publish — zero manual work.

How do I build a guest quote library from my podcast archive?

The quotes array in each repurposed_show-notes result includes the speaker name, exact quote text, and timestamp. Pipe all episodes through this Actor and accumulate the quotes arrays into a database — every notable thing every guest has ever said, searchable by speaker and timestamp.

Using with AI agents (MCP)

This Actor is published on the Apify Store and automatically available as an MCP tool. AI agents using Claude Desktop, LangChain, CrewAI, or any MCP-compatible framework can discover and call this Actor directly — no custom integration required.

Show notes output example

{
"summary":"Sarah Chen joins us to explain why her team consolidated 47 microservices back into a modular monolith — and what the deployment numbers looked like on the other side.",
"chapters":[
{
"title":"Introduction",
"startSeconds":0,
"description":"Host introduces Sarah Chen, VP Engineering at Acme Corp."
},
{
"title":"The Microservices Trap",
"startSeconds":312,
"description":"How 47 services became impossible to debug."
},
{
"title":"The Great Consolidation",
"startSeconds":894,
"description":"Moving back to a monolith in 6 weeks."
}
],
"quotes":[
{
"speaker":"Sarah Chen",
"text":"We had 47 services and nobody could tell you what half of them did. That's not a microservices problem — that's an organizational problem we tried to solve with infrastructure.",
"startSeconds":318
}
],
"showNotes":"**Episode 42: Why We Killed Our Microservices**\n\nSarah Chen, VP of Engineering at Acme Corp, shares the real story...\n\n**Chapters:**\n- [0:00] Introduction\n- [5:12] The Microservices Trap\n- [14:54] The Great Consolidation"
}

What data does the Actor return?

Wisprs vs manual podcast workflow

How much does it cost?

Pricing is pay-per-event:

• $0.005 per episode submitted
• $0.015 per audio minute (45-min episode = $0.675)
• $0.075 per show notes result generated

Example: 10 × 45-minute episodes with show notes

• Submit: 10 × $0.005 = $0.05
• Audio: 10 × 45 × $0.015 = $6.75
• Show notes: 10 × $0.075 = $0.75
• Total: ~$7.55

The Apify free plan includes $5/month in credits — enough to test 5–6 episodes.

What can I automate with this?

RSS-to-CMS pipeline — monitor your podcast RSS feed, submit new episode URLs as they publish, and write the generated show notes directly back to your CMS via webhook. Every episode gets show notes on publish with zero manual work.

Guest quote library — the quotes array includes speaker attribution and timestamps for every notable thing every guest has ever said. Pipe this into a database and you have a searchable quote library across your entire back-catalog — perfect for social media clip selection.

Transcript SEO pages — publish the transcript_txt or transcript_md export as a dedicated page for each episode. Long-tail podcast transcripts drive search traffic without any additional writing effort.

Chapter markers for Podcast Namespace — the chapters array maps directly to the Podcasting 2.0 chapter format used by Fountain, Overcast, and Pocket Casts. Inject chapters automatically on every episode.

Multi-show network dashboard — submit episodes from all shows in your network concurrently. The async job model handles parallel processing — one run covers an entire network.

Supported URL formats

• Direct audio: mp3, wav, m4a, ogg, flac
• RSS feed episode URLs (standard podcast hosting platforms)
• Buzzsprout, Transistor, Simplecast, Anchor, Captivate, RSS.com, Podbean
• YouTube podcast episodes
• Spotify episode audio links (public)

Language support

100+ languages with automatic detection. Speaker diarization (host vs guest labeling) works best on clear two-speaker recordings. For episodes with more participants, speakers are labeled "Speaker 1", "Speaker 2", etc.

Related Actors

• Wisprs — Audio & Video Transcription — universal transcription for any URL
• Wisprs — YouTube Content Repurposer — YouTube → thread, blog, chapters
• Wisprs — Social Media Transcriber — TikTok, Reels, Shorts

FAQ

Does this work for podcasts without published transcripts? Yes. Wisprs transcribes the audio directly using Whisper — it does not rely on pre-existing transcript files or RSS transcript tags.

How long does a 60-minute episode take to process? Typically 3–8 minutes, depending on server load. The Actor polls automatically and saves results when complete.

Can I process an entire podcast back-catalog? Yes. Add all episode URLs to startUrls. The Actor processes them sequentially, saving each result to the Dataset as it completes.

Does speaker diarization work in languages other than English? Speaker detection works across all supported languages. Accuracy on non-English content is excellent on clear recordings.

Support

• Documentation: wisprs.co/docs
• Email: tosh@belvadigital.com

Two API calls. One polished episode. Ship faster.