How I Created a Full, Co-hosted Podcast in Just 4 Hours with NotebookLM

and why it matters for creators

Last week, I read an article by friend and Canadian podcaster, Al Grego, titled “I Think… I’m Done”. In it, Al shared his frustration / admiration / fear / thoughts around Google’s NotebookLM, an AI tool from the giants of the web. This was inspired by an example from James Cridland, founder of leading industry publication Podnews.

Now, primarily, NotebookLM is a note taking and research assistant powered by AI. In Google’s own words:

Use the power of AI for quick summarization and note taking, NotebookLM is your powerful virtual research assistant rooted in information you can trust.

However, while it’s aimed at research and maybe academia, there’s also a component that should make podcasters and creators sit up and take notice (as it did Al), and that’s their Audio Overview feature.

Because this is where NotebookLM moves from a note taking tool into a podcast creation tool. Essentially, NotebookLM takes a look at the “source” you’ve provided - which can be a web page, a document, a PDF upload, or even copy pasted text - and then creates an audio file where two people talk about the source in question, but with their own viewpoints.

And this is where things get interesting, since those two “people” aren’t real - they’re AI generated voices that have been created by Google to talk about the content you’ve just uploaded. But listening to the results, you’d be forgiven if you did actually think they were real, that’s how good the results are.

After experimenting with it for a bit, I was curious how well NotebookLM would cope if I tried to create a brand new co-hosted podcast, and how long it’d take from ideation to completion. The answer on both fronts was super impressive.

AI is No Longer Super Easy to Spot

As I mentioned earlier, NotebookLM takes a source and then creates notes around that. However, if you use the Audio Overview feature, it creates a conversation between two AI-powered “co-hosts”, if using podcasting vernacular. And it was this feature I was really curious about.

So I came up with an idea - let’s create a brand new co-hosted podcast, using this publication as “the source”, and see what happens. So I looked at some of my most popular articles, and used those as the starting point for the podcast, with each article being a singular episode of this fledgling podcast.

And it was equally scary and impressive at how well the result came out. But before looking at that, here’s the flow on how each episode was created.

• find an article on my publication

• copy the text part into Google Docs

• create a new “notebook”

• add sources (Google Drive, a link, or copy paste text) - I used Google Drive/Docs

• click “insert source”

Once done, NotebookLM will display your “Notebook Guide”, which gives you an overview of the note you’re creating, as well as what you’d like to create from it:

• FAQ

• study guide

• table of contents

• timeline

• briefing doc

Now, while all that is fun and relevant to someone needing notes and study guides, etc, as a podcaster you want the audio conversation. So you’ll click the Generate button on the Audio Interview option:

After clicking that, you’ll have a short wait until the voices and conversation have been generated. And this is where it gets really good.

At first, I wasn’t really sure what to expect, since most AI conversations and attempts at replicating the human voice that I’ve tried, and all the inflections, tone, and emotion that contains, have fallen flat. Not so with NotebookLM.

Listening to the result, this actually sounds like two people talking to each other. Sure, if you’re an audio person and listen closely enough, there are minor tell-tale signs - occasional breaths between talking that don’t sound “quite human”, and the odd word that is missing as the AI co-hosts look to fill space.

But overall, it’s really damn good. Here’s an example - to create the trailer for the show, I prompted NotebookLM with this:

Create a trailer for this: the podcast aims to assist aspiring podcasters by providing tips, tricks, and insights on enhancing content, optimizing audio quality, selecting the right equipment, and interpreting data. It promises to make even the most technical aspects of podcasting easy to understand and fun.

And here’s the result:

I mean - come on, that’s pretty impressive right there, no? Taking just a paragraph of prompts, NotebookLM came up with a more expansive overview, with some concrete examples, and also referenced the fact that both co-hosts aren’t real, and what that means for content creators. Not bad at all.

So that’s the audio part out of the way, but as I mentioned (and as the title states), how did that go from an audio experiment into a fully-fledged podcast, published on all the main podcast apps and platforms, with a podcast website to boot, in just over 4 hours?

Creating the Podcast and Going Live

This was also pretty easy and smooth sailing For my hosting, I use Captivate (aff. link), which makes sense since I’m Head of Podcaster Support & Experience there. And this made it super easy to not only create the podcast, but also get it submitted and approved within an hour or so.

• used the Create a New Podcast option in Captivate

• completed all the relevant info (name, description, artwork, type of show, etc)

• uploaded the audio files for the trailer and first two episodes

• used Captivate’s AMIE tool (dynamic content insertion tool) to add a pre-roll to each episode with the disclaimer about this being fully AI-powered

• create each new episode and add show notes, references, etc.

• published the trailer and first two episodes

• submitted to Apple, Spotify, etc, for approval

While approval was happening, I created the podcast website for the show using the free site tool that Captivate offers every podcast. This ensured I had a “home base” for the show, and added to the overall presentation.

As I was creating this, the show was being approved on various podcast apps and platforms, so by the time the site was done, Be a Better Podcaster was live on Apple, Spotify, Amazon, Pocket Casts, iHeart, and all the places you’d expect to find a podcast.

Which meant, all told, it had taken me just over 4 hours to create a podcast, upload and publish two episodes with co-hosts, submit it, have it approved, create a website, and make everything available for new listeners. Which is pretty damned impressive, when I think of how much longer it’s taken me to do this from scratch.

So what does this mean for podcasters and creators?

The Human Touch is Still Very Much Needed

While AI can be looked at in a negative way - replacing human voices, creating content, publishing written word, etc - I see it as more of an opportunity. I posted over on Twitter about reframing AI from “artificial intelligence” to “additional intelligence” - make it work for you, as opposed to against you.

While there’s no doubt the results in my experiment are impressive, they still need human input. For Be a Better Podcaster, this means:

• pasting resources of mine into the “idea box”

• ensuring the context of the discussion makes sense

• adding intro and outro music on my editing software, Hindenburg

• uploading to my podcast hosting platform and creating the episode

• promoting and recommending to my audience

And these are the basics - depending on the type of podcast you have, you may actually need more input by you for it to work, which then negates AI even more.

But, there’s also a lot of positives. As any indie podcaster will attest to, creating and growing a podcast is hard. NotebookLM has the potential to make this a lot easier, and time and cost effective:

• a small business that wants to get into podcasting but can’t afford time or resources

• a non-profit with limited funds but wants to use podcasting to share their story

• a podcaster that wants to offer additional content as a premium offering, but is hindered by time

• a local student newspaper that wants to expand an audience

These are just some examples where NotebookLM can really help. There are no doubt numerous more - and if the quality can equal the results I’ve seen, then NotebookLM could be an unintentional tool in helping podcasts reach a wider audience.

And that’s never a bad thing.

Check out the full podcast: