I Was Drowning in Podcast Admin, So I Built an Edge AI Tool

Описание и применение

Создатель подкастов избавился от трат времени на ручную работу после выпуска эпизода, создав инструмент PodCrisp, который в режиме реального времени генерирует заголовки, заметки и SEO‑ключевые слова с помощью Llama‑3 на Cloudflare Workers.

Задача

Podcast creators spent up to three hours per episode on manual admin tasks such as title creation, transcript summarization, and SEO-friendly descriptions, draining time and joy from content creation.

Результат

The edge AI pipeline reduced post‑production admin from up to three hours to a few minutes, delivering instant, structured metadata and improving discoverability while preserving creator joy.

Рабочий процесс

• 1. Record episode and generate transcript.
• 2. Send transcript to Cloudflare Worker endpoint.
• 3. Worker calls Llama‑3‑8b‑instruct via Cloudflare AI with a structured system prompt to produce show notes, title options, and SEO keywords.
• 4. Receive JSON response with formatted metadata.
• 5. Publish episode with generated titles and notes.
• 6. Optionally iterate with streaming response for real‑time rendering.

Доказательства

I was spending upwards of three hours after every single episode just doing admin work.

Источник

The post‑production admin for podcasts is a hidden tax on creators.

Источник

I decided to build something.

Источник

I named the project PodCrisp. My main technical goal was to keep things incredibly fast and lightweight.

Источник

Using Llama 3 at the edge via Cloudflare was a practical choice. It’s fast enough to handle the 800‑token limit for show notes without timing out.

Источник