Is the a private fronteng or alternative to NotebookLM ?

Very interesting, thanks for sharing https://github.com/theaiautomators/insights-lm-local-package

Honestly though it might take 15min to configure, 1hr to let it run so that it get all images, dependencies, etc, 30min to debug GPU passthrough with the right driver version, 10min to try by getting the right endpoint... then 1min to realize that sure you can get give a PDF and "chat" with it but nothing particularly interesting or actually insightful will come out of this, especially if the paper itself if well written, namely has a proper introduction, structure, etc.

So... I'm leaving this comment here to maybe try one day, updated my list of local AI services but most likely I won't bother anymore.