A Self-Hosted NotebookLM for Audio Overviews

You want NotebookLM's two-AI-hosts-discussing-your-content trick, but on your own infrastructure — your API keys, your storage, no Google account in the loop. That's exactly the shape of this project.

What self-hosting changes

Hardware requirements: none

Unlike self-hosting an LLM, this pipeline is glue, not inference — the heavy lifting is API calls. It runs happily on GitHub Actions' free tier or any $0 leftover machine; there's no GPU, database, or always-on server. npm run setup provisions storage, deploys the player, and prints your private podcast feed URL.

Honest limits vs. NotebookLM

No interactive mode (you can't interrupt the hosts to ask questions), and no multi-document research grounding. What you get instead is automation: a daily audio digest of your sources and full audiobooks of your epubs, delivered to a normal podcast app.

listenwhilerunning is open source (AGPL-3.0) and runs on your own free-tier accounts.

Get it on GitHub → Live demo Hosted version waitlist

FAQ

Does it need a GPU or local LLM?

No. It's an orchestration pipeline: TTS and LLM are API calls. You can point it at a local model if you run one, but it's optional.

Where does the audio live?

In your own object-storage bucket with a private feed URL. Delete the bucket and every trace is gone — it's your data in the most literal sense.

What's the actual monthly cost?

Storage and compute fit in free tiers; LLM rewriting costs a few cents a day and is optional. Effectively $0.