Simon Willison’s Weblog

New in NotebookLM: Customizing your Audio Overviews. The most requested feature for Google's NotebookLM "audio overviews" (aka automatically generated podcast conversations) has been the ability to provide direction to those artificial podcast hosts - setting their expertise level or asking them to focus on specific topics.

Today's update adds exactly that:

Now you can provide instructions before you generate a "Deep Dive" Audio Overview. For example, you can focus on specific topics or adjust the expertise level to suit your audience. Think of it like slipping the AI hosts a quick note right before they go on the air, which will change how they cover your material.

I pasted in a link to my post about video scraping and prompted it like this:

You are both pelicans who work as data journalist at a pelican news service. Discuss this from the perspective of pelican data journalists, being sure to inject as many pelican related anecdotes as possible

Here's the resulting 7m40s MP3, and the transcript.

It starts off strong!

You ever find yourself wading through mountains of data trying to pluck out the juicy bits? It's like hunting for a single shrimp in a whole kelp forest, am I right?

Then later:

Think of those facial recognition systems they have for humans. We could have something similar for our finned friends. Although, gotta say, the ethical implications of that kind of tech are a whole other kettle of fish. We pelicans gotta use these tools responsibly and be transparent about it.

And when brainstorming some potential use-cases:

Imagine a pelican citizen journalist being able to analyze footage of a local council meeting, you know, really hold those pelicans in power accountable, or a pelican historian using video scraping to analyze old film reels, uncovering lost details about our pelican ancestors.

Plus this delightful conclusion:

The future of data journalism is looking brighter than a school of silversides reflecting the morning sun. Until next time, keep those wings spread, those eyes sharp, and those minds open. There's a whole ocean of data out there just waiting to be explored.

And yes, people on Reddit have got them to swear.