Is Google’s NotebookLM Going to Disrupt the Podcasting Industry? | by Dr. Varshita Sher | Oct, 2024

Generative AI

For many who could not know, NotebookLM is a personalised AI analysis assistant powered by Gemini 1.5 Professional, designed to make sense of complicated info. Along with answering questions primarily based in your uploaded sources (paperwork, slides, charts, and so forth.), it may possibly additionally create customized examine supplies by routinely producing issues like a desk of contents, examine guides, briefing paperwork, FAQs, and extra. Whereas it formulates solutions primarily based on the uploaded sources, it additionally offers inline citations, highlighting the precise textual content blocks within the supply paperwork used to generate the response.

The uploaded content material can vary from analysis papers and assembly transcripts to quotes from attention-grabbing books, chapters of a novel you’re writing, company paperwork, and extra. These sources can embrace Google Docs, Slides, PDFs, textual content recordsdata, copied textual content, and even internet pages.

Now, to the principle motive for this text: Final month, NotebookLM announced a new feature — Audio Overviews — which has been making headlines. This characteristic presents a brand new approach to work together together with your supply paperwork. With only one click on, it generates partaking “deep dive” discussions that summarize the important thing subjects in your sources.

What’s much more spectacular is the way it transforms any piece of content material, regardless of how dry, by producing two AI hosts (one male and one feminine) who talk about the doc’s contents in a podcast-style format.

If you happen to’re questioning what “podcast-style format” means, think about the pleasant banter, the little jokes, the back-and-forth conversations, the laughs, interruptions, “umms,” and “you is aware of’”— primarily all of the hallmarks of a terrific podcast listening expertise.

These podcast-style conversations create pure connections and segues out of your textual content, leading to a fascinating dialogue.

To try it out, I made a decision to repurpose considered one of my old Medium articles and create a podcast from it to cater to a extra audio-loving viewers.

The arrange for a similar was fairly simple.

• Go to NotebookLM. You’ll must register together with your Google ID should you aren’t already. If it’s your first go to, you’ll see a number of pattern notebooks and you’ll create a brand new one with the “Create” button.
• Subsequent, add content material to your pocket book. I used the web site supply to feed in my Medium article. Alternatively, you’ll be able to paste textual content or fetch from Google Drive.

• Lastly, click on the “Generate” button contained in the Pocket book information (see picture under) to create the audio. And go seize a ☕️ as it’d take a couple of minutes relying on the content material size.

P.S. It took round 4 minutes to generate a 13 minute audio from my 1100-word article. You may play and pay attention right here.

P.S. I ended up making an attempt Audio Overview with numerous sources, resembling podcast transcripts, analysis papers, and knowledge science blogs. The next takeaways are an amalgamation of my experiences throughout all these sources.

Let’s begin with the great things:

• It’s exceptional that we will rapidly create a podcast episode in simply minutes, permitting many people to have a aspect gig as podcasters (do you have to select to). It is a wonderful means for writers to repurpose their content material and for others to interact with comparatively complicated subjects in a enjoyable and accessible method.
• Using analogies all through the audio is really exceptional and fascinating. Within the case of my Medium article, it was capable of take a comparatively area of interest (learn:boring) subject (scaling challenges with Gen AI may not attraction to everybody outdoors the quick area) and make connections to on a regular basis issues.
  For example, at one level the hosts talk about Gen AI token prices and supply a way more relatable instance, evaluating how these prices can add as much as micro-transactions in a cellular recreation. Equally, they clarify immediate engineering with an instance of offering a whole recipe with measurements, somewhat than merely saying “make me a scrumptious meal”. Additionally they use the analogy of a automotive remembering a standard route to clarify LLM caching.
• The best way the 2 hosts construct on one another’s sentences feels very pure, and the segues circulate seamlessly. For instance, utilizing phrases like “talking of…” to introduce a brand new subject feels natural and never compelled in any respect.
• Emphasis on sure phrases at simply the proper moments helps maintain the listeners’ consideration. Expressions like “oh wow”, “oops”, and “aah” convey real shock at what the opposite host simply stated. Pure pauses to think about the proper phrase make the dialog really feel spontaneous somewhat than rehearsed.
• After testing this on a number of deep studying papers, I can confidently say will probably be a recreation changer for explaining complicated analysis that advantages from analogies and “clarify like I’m 5” (ELI5) examples. In truth, the rules in considered one of their pre-prepared instance notebooks, titled Introduction to NotebookLM, state that it’s designed for researchers, journalists, college students, and enterprise professionals.

Having seemed on the key benefits, there are additionally a couple of limitations to think about:

• Generally, the dialog between the 2 hosts doesn’t really feel actual. Fairly often, they end one another’s sentences, even when the primary host has simply requested the second host to clarify a brand new idea and some seconds later, Host 1 finally ends up answering their very own query.
• Not all enter sources generate audio of equal high quality. As a part of stress testing, I attempted inputting the transcript from one other podcast, and the hosts appeared extra inclined to make humorous noises at one another — ‘yayaya,’ ‘oh yeah,’ ‘hmm,’ ‘uh-huh,’ ‘proper,’ ‘gotcha,’ and so forth.!
• The one draw back to having a whole lot of analogies whereas discussing a subject is that typically the AI can get the analogies flawed. For example, whereas discussing a weblog on forecasting metrics, it used the analogy of “similar to in colleges a decrease rating is mostly higher, it means your forecast is nearer to actuality”.
  Such hallucinations are frequent throughout completely different generative AI fashions and have been included as a disclaimer of their device as properly. These is perhaps extra pronounced if we offer a really area of interest, extremely specialised subject, such because the function of microRNAs in gene regulation (the subject that received the Nobel Prize in 2024 this week). In such instances, it could begin hallucinating with analogies used attributable to an absence of related inherent information🤷‍♀.
• For very massive texts, the podcast can typically finish abruptly. This implies that there could also be a cutoff level for the coaching knowledge, past which the audio can not adapt to offer a easy, pure ending.
• (Very minor however) A few of the phrases, principally abbreviations, are garbled within the audio. For some motive RAG is pronounced as ArrrR-G as an alternative of particular person alphabets like R-A-G.
• At occasions, hosts overly agree with each other, utilizing filler phrases like ‘proper’ and ‘precisely’ whereas the opposite host remains to be speaking. This could really feel like compelled responses; I imply, let the poor man end!

Now that we’ve coated the great and the dangerous, let’s transfer on to the million-dollar query: is that this new tech sufficient to present podcasters a critical competitors?

My easy reply is — not but. The explanation? All of the aforementioned points we’ve mentioned. And I do know a few of you would possibly disagree and say these issues are minor, and also you’d be proper. If you happen to take heed to only one podcast, you might not even discover them, however should you constantly take heed to a number of episodes, particularly on a day by day or weekly foundation, the sheer variety of analogies and “exactlys” can turn out to be overwhelming. For these causes, maybe Google by no means positioned it as a podcasting device of their preliminary launch.

That stated, it’s going to undoubtedly decrease the barrier to entry for a lot of who wish to discover this area however could not wish to use their very own voice for numerous causes. Extra importantly, I see its use as a approach to eat complicated subjects in digestible codecs.