I write 2-3 blog posts per week. I've been doing this consistently for months. People ask how I keep up the pace without burning out.
The answer: I don't write from scratch. I start with YouTube transcripts.
Here's my full workflow, including the exact AI prompts I use.
Why Transcripts Are the Best Starting Material
YouTube is the world's second-largest search engine. Millions of experts share knowledge on camera every day. That knowledge is trapped in video format — you can't search it, skim it, or copy-paste from it.
Unless you extract the transcript.
I use ScripTube (scriptube.me) to grab transcripts from any YouTube video. Paste the URL, get clean text in seconds. What used to take me 20 minutes of manual copying now takes 3 seconds.
The Workflow
Step 1: Topic Research on YouTube
I search my target keyword on YouTube. I look for videos with:
- High view counts (proven demand)
- Good engagement (comments, likes)
- Expert creators (not just aggregators)
I pick 2-3 videos that cover different angles of the same topic.
Step 2: Extract Transcripts
I run each URL through ScripTube and save the transcripts in a working doc. For a typical blog post, I'm working with 15-30 pages of raw transcript text from multiple sources.
Step 3: AI-Assisted Outline
I feed the transcripts to ChatGPT (GPT-4) with this prompt:
I have transcripts from 3 YouTube videos on [TOPIC].
Read all three and create a comprehensive blog post outline that:
1. Synthesizes the best insights from all sources
2. Identifies where they agree and disagree
3. Suggests sections I should expand with my own research
4. Proposes an engaging title and subtitle
Here are the transcripts:
[PASTE TRANSCRIPTS]
The key word is "synthesizes." I'm not rewriting one video — I'm combining multiple expert perspectives into something more comprehensive than any single source.
Step 4: AI-Assisted First Draft
With the outline approved, I go section by section:
Using the outline above and the transcript material,
write section 2: [SECTION TITLE].
Requirements:
- Use insights from the transcripts as a foundation
- Add transitional sentences between ideas
- Keep a conversational but authoritative tone
- Include a specific example or analogy
- 200-300 words
I do this for each section, reviewing and editing as I go.
Step 5: The Human Pass
This is non-negotiable. The AI draft is maybe 70% there. My editing pass adds:
- My own opinions and hot takes. AI doesn't have opinions. Readers want perspective.
- Personal anecdotes. "Last week I tried this and here's what happened" — AI can't write these.
- Fact-checking. AI confidently states things that are wrong. I verify every claim.
- Voice and personality. I rewrite sentences that sound generic or corporate.
- Additional research. I add stats, links, and context the transcripts didn't cover.
Time Comparison
| Method | Time per post |
|---|---|
| Writing from scratch | 4-5 hours |
| Transcript + manual writing | 2-3 hours |
| Transcript + AI assist + editing | 1-1.5 hours |
The quality hasn't dropped. If anything, posts are better because they're synthesized from multiple expert sources instead of just my perspective.
Ethical Considerations
Some people ask: "Isn't this just copying?"
No. Here's why:
- I use multiple sources, not one
- I add original analysis and opinion
- I credit and link to original videos
- The final product is a different format (text vs. video) for a different audience
- I'm doing what every journalist, researcher, and non-fiction writer does — synthesizing sources
The transcripts are raw material. The blog post is a new creation.
The Tools
- ScripTube (scriptube.me) — transcript extraction
- ChatGPT / Claude — AI assistance
- Google Docs — editing
- Grammarly — final polish
- WordPress — publishing
Total cost: $20/month (ChatGPT subscription). Everything else is free.
Tips for Better Results
- Always use multiple video sources. Single-source posts feel thin.
- Don't skip the human editing pass. AI-only content is detectable and mediocre.
- Let the AI handle structure, you handle substance. AI is great at organizing. Humans are great at insight.
- Verify everything. Transcripts have ASR errors. AI hallucinates. Trust but verify.
This workflow has turned content creation from my biggest bottleneck into my most scalable process. Give it a try.
Top comments (0)