Building an Edge AI Pipeline to Automate Podcast Post-Production

Описание и применение

Создана система Edge‑AI для автоматизации пост‑продакшена подкастов: генерация заметок, заголовков и SEO‑ключевых слов за секунды, что сократило ручную работу с 45 минут до 10 с.

Задача

Podcast post‑production consumes nearly three hours per episode, draining creative energy and causing burnout.

Результат

Structured show‑notes generation cut manual effort from 45 min to ~10 s generation, while title generation improved quality through prompt constraints.

Рабочий процесс

• 1. Record episode and upload audio
• 2. Transcribe audio (external tool)
• 3. Send transcript to Cloudflare Worker
• 4. Worker calls Llama 3 8B with structured system prompt to generate show notes, timestamps, resources, and SEO keywords
• 5. Receive JSON response and paste into CMS
• 6. Use separate title generator endpoint with prompt engineering for compelling titles
• 7. Review and edit brief outputs

Доказательства

Transcribing the audio, writing structured show notes, brainstorming clickable (but honest) titles, and pulling SEO keywords was taking me nearly three hours per episode.

Источник

I decided to build PodCrisp, a suite of AI podcast tools. For the architecture, I chose Cloudflare Workers.

Источник

By explicitly defining the rules in the system prompt—like enforcing a 5-10 word limit and banning overpromising clickbait—the output quality improves dramatically.

Источник

What worked exceptionally well was the structured show notes generator. It completely changed my workflow. What used to take 45 minutes of re-listening to the audio and typing out bullet points now takes about 10 seconds of generation and 5 minutes of light editing.

Источник

I also added SEO keyword suggestions and an episode script outline generator to the suite, using similar structured prompting techniques to ensure the output is immediately actionable.

Источник