How I Built an Edge AI Pipeline to Automate Podcast Admin

Description and use

Post‑production time dropped from two hours to fifteen minutes using an Edge‑AI pipeline on Cloudflare Workers with Llama‑3‑8b‑instruct for generating show notes, titles, and SEO tags.

Problem

Post‑recording administrative tasks consumed 80% of the creator’s time, causing burnout and inconsistent episode quality.

Outcome

The pipeline reduced post‑production time from two hours to about fifteen minutes, improving consistency and allowing the creator to focus on content creation.

Workflow

• 1. Record episode
• 2. Transcribe audio
• 3. Send transcript to Cloudflare Worker for show‑notes generation via Llama‑3‑8b‑instruct
• 4. Receive structured JSON with summary, takeaways, timestamps, resources
• 5. Review and adjust timestamps
• 6. Generate episode title using prompt‑engineered title generator
• 7. Retrieve SEO keyword suggestions
• 8. Publish episode metadata

Evidence

I would spend two hours writing show notes, agonizing over the episode title, and trying to extract SEO keywords from the conversation.

Source

The results have been a massive improvement for my own workflow. What used to take me two hours of post‑recording admin now takes about 15 minutes.

Source

By explicitly banning clickbait that overpromises and enforcing a word count, the output quality jumped significantly.

Source