Building Edge AI Inference to Automate Podcast Show Notes

Description and use

Automating podcast show‑note and title creation with Edge‑AI on Cloudflare Workers cuts manual effort to minutes, improving timestamp accuracy and title appeal.

Problem

Post‑production admin for podcasts consumes hours, causing creator fatigue and poor discoverability due to weak titles and messy show notes.

Outcome

Edge AI inference delivers near‑instant show‑note generation and more accurate timestamps, while constrained prompt engineering yields better podcast titles, reducing manual effort from three hours to minutes.

Workflow

• 1. Record podcast and obtain transcript
• 2. Enable AI binding in wrangler.toml
• 3. Use prompt engineering to generate titles with constraints
• 4. Send transcript to Cloudflare Workers AI endpoint using @cf/meta/llama-3-8b-instruct
• 5. Receive structured show notes (summary, takeaways, timestamps, resources)
• 6. Optionally chunk long transcripts to stay within max_tokens=800
• 7. Review and publish show notes and titles

Evidence

I was spending three hours per episode just on administrative text.

Source

By capping max_tokens at 800, I ensure the response remains concise and prevents the model from rambling, which is crucial for show notes.

Source

Moving the AI inference to the edge was the most impactful decision I made. The show notes generation feels nearly instant, which keeps the creator in a state of flow rather than waiting on a loading spinner.

Source