Duarte O.Carmo's articles

#63 Limpa: Ad-Free podcasts powered by LLMs


Listen Later

I built Limpa, a simple Django and htmx-powered web app that generates ad-free podcast feeds by transcribing the latest episode, using a large language model to detect ad segments, and cutting them out with ffmpeg. It runs on Modal with NVIDIA’s Parakeet v3 for transcription and uses Django’s new Tasks framework for background jobs. I’m not hosting it as a service, but the project is documented so you can run it yourself.

Relevant links:

  • Original article
  • Limpa (GitHub)
  • Pi-hole
  • uBlock Origin
  • SponsorBlock
  • RSS feed finder
  • Django
  • htmx
  • NVIDIA Parakeet v3 model
  • Modal
  • Transcript with timestamps (code)
  • LLM ad extraction prompt (code)
  • ffmpeg
  • Django Tasks framework
  • Celery (Django first steps)
  • Flower
  • OpenCode.ai
  • ...more
    View all episodesView all episodes
    Download on the App Store

    Duarte O.Carmo's articlesBy Duarte O.Carmo