How I Built an Edge AI Pipeline to Automate Podcast Notes

Описание и применение

Создана система на Cloudflare Workers, автоматически генерирующая заметки и заголовки для подкастов, сокращая ручную работу с часами до минут.

Задача

Creating episode titles and show notes for a podcast was time‑consuming and mentally exhausting, creating a bottleneck after recording.

Результат

The pipeline delivers instant, structured show notes and title options, cutting manual writing time from hours to minutes and improving SEO potential.

Рабочий процесс

• 1. Record podcast and generate transcript
• 2. Send transcript to Cloudflare Worker via JSON request
• 3. Worker calls Cloudflare AI endpoint with system prompt defining markdown structure
• 4. AI returns structured show notes (summary, bullet points, timestamps, resources)
• 5. Worker returns JSON to client
• 6. Separate title generator uses similar prompt for title options

Доказательства

I was wrong. The real bottleneck happened long after I hit "stop recording."

Источник

I decided to build PodCrisp using Cloudflare Workers.

Источник

We use a system prompt to set strict rules. Instead of just saying "write notes," we explicitly define the markdown structure we want: a short summary, bullet points for takeaways, estimated timestamps, and resources.

Источник

Because the inference happens on Cloudflare's network, the tool feels instantaneous to the user.

Источник