# n8n: Podcast Episode to Blog Post + Clips

> Drop an MP3 in Dropbox — get a transcript (Whisper), a blog post (Claude), three short-form clips (with timestamps), and a Notion draft.

**Platform:** n8n  
**Category:** n8n  
**Difficulty:** Advanced  
**Tags:** n8n, podcast, whisper, content  
**Updated:** 2026-06-18  
**Source:** https://promptfoo.tech/workflows/n8n-podcast-repurposing-pipeline

## Overview
A single podcast episode should power a week of content. This n8n workflow watches Dropbox for new audio, transcribes with Whisper, extracts the best 60-90 second moments for social clips, writes a long-form blog post from the transcript, and stages everything as a Notion page ready for review.

## How it works
1. Dropbox trigger on new MP3.
2. OpenAI Whisper node for transcription with timestamps.
3. Claude extracts 3 highlight clips (best hooks, self-contained, 60-90s).
4. Second Claude call writes a 1200-word blog post from the full transcript.
5. Notion page created with sections: transcript, blog draft, clip timestamps + hooks, cover-image prompt.

## Benefits
- Every episode yields 4-5 deliverables instead of 1.
- Clip timestamps mean your editor spends time cutting, not scrubbing.
- Blog draft becomes an SEO play from an audio asset.

## Use cases
- Solo podcasters without a producer.
- Agencies packaging content for client shows.
- Internal 'lunch and learn' recordings turned into knowledge base pages.

## Step-by-step
### Step 1: Watch Dropbox
Trigger on new file in /podcast/episodes. Filter to .mp3/.wav/.m4a.

### Step 2: Chunk long files for Whisper
Whisper's file limit is 25MB. Split with ffmpeg (n8n Execute Command node) if larger.

### Step 3: Transcribe with timestamps
response_format=verbose_json for per-word timestamps. Reassemble into paragraphs for the blog step.

### Step 4: Clip extraction prompt
System: 'Return 3 clips as JSON: start, end, hook, why_it_works.'

### Step 5: Blog post from transcript
Ask for a 1200-word post with an H1, 5 sections, and 3 tweetable quotes at the top.

### Step 6: Notion assembly
Single page with structured sections; owner assigned; status=Draft. Editor takes it from there.

## Example
```
Clip output: {start:'00:14:20', end:'00:15:42', hook:'The real bottleneck isn't compute, it's judgement', why:'Reframes a common assumption in 8 seconds.'}
```

## FAQs
**Alternatives to Whisper?**

AssemblyAI has better diarization; Deepgram is faster. Whisper via OpenAI is the cheapest and simplest to wire.

**Cost per episode?**

About $0.30-0.60 for a 60-minute episode across transcription and generation.

**Video?**

Add ffmpeg extraction of vertical crops keyed to the clip timestamps for TikTok/Reels-ready output.

---
Licensed under CC-BY-4.0. Attribution: PromptFoo.tech