Like nearly everybody, we have been impressed by the power of NotebookLM to generate podcasts: Two digital individuals holding a dialogue. You can provide it some hyperlinks, and it’ll generate a podcast based mostly on the hyperlinks. The podcasts have been fascinating and fascinating. However additionally they had some limitations.
The issue with NotebookLM is that, whilst you can provide it a immediate, it largely does what it’s going to do. It generates a podcast with two voices—one male, one feminine—and provides you little management over the end result. There’s an optionally available immediate to customise the dialog, however that single immediate doesn’t assist you to do a lot. Particularly, you may’t inform it which subjects to debate or in what order to debate them. You’ll be able to attempt, but it surely received’t hear. It additionally isn’t conversational, which is one thing of a shock now that we’ve all gotten used to chatting with AIs. You’ll be able to’t inform it to iterate by saying “That was good, however please generate a brand new model altering these particulars” like you may with ChatGPT or Gemini.
Can we do higher? Can we combine our information of books and know-how with AI’s potential to summarize? We’ve argued (and can proceed to argue) that merely studying how you can use AI isn’t sufficient; it is advisable discover ways to do one thing with AI that’s higher than what the AI may do by itself. It’s essential combine synthetic intelligence with human intelligence. To see what that might appear like in observe, we constructed our personal toolchain that offers us rather more management over the outcomes. It’s a multistage pipeline:
- We use AI to generate a abstract for every chapter of a e book, ensuring that every one the essential subjects are coated.
- We use AI to assemble the chapter summaries right into a single abstract. This step primarily offers us an prolonged define.
- We use AI to generate a two-person dialogue that turns into the podcast script.
- We edit the script by hand, once more ensuring that the summaries cowl the best subjects in the best order. That is additionally a possibility to appropriate errors and hallucinations.
- We use Google’s speech-to-text multispeaker API (nonetheless in preview) to generate a abstract podcast with two contributors.
Why are we specializing in summaries? Summaries curiosity us for a number of causes. First, let’s face it: Having two nonexistent individuals focus on one thing you wrote is fascinating—particularly since they sound genuinely and excited. Listening to the voices of nonexistent cyberpeople focus on your work makes you are feeling such as you’re residing in a sci-fi fantasy. Extra virtually: Generative AI is definitely good at summarization. There are few errors and virtually no outright hallucinations. Lastly, our customers need summarization. On O’Reilly Solutions, our clients often ask for summaries: summarize this e book, summarize this chapter. They need to discover the data they want. They need to discover out whether or not they actually need to learn the e book—and if that’s the case, what components. A abstract helps them try this whereas saving time. It lets them uncover shortly whether or not the e book shall be useful, and does so higher than the again cowl copy or a blurb on Amazon.
With that in thoughts, we needed to actually suppose via what essentially the most helpful abstract can be for our members. Ought to there be a single speaker or two? When a single synthesized voice summarized the e book, my eyes (ears?) glazed over shortly. It was a lot simpler to take heed to a podcast-style abstract the place the digital contributors have been excited and enthusiastic, like those on NotebookLM, than to a lecture. The give and take of a dialogue, even when simulated, gave the podcasts power {that a} single speaker didn’t have.
How lengthy ought to the abstract be? That’s an essential query. Sooner or later, the listener loses curiosity. We may feed a e book’s total textual content right into a speech synthesis mannequin and get an audio model—we could but try this; it’s a product some individuals need. However on the entire, we count on summaries to be minutes lengthy slightly than hours. I would hear for 10 minutes, possibly 30 if it’s a subject or a speaker that I discover fascinating. However I’m notably impatient after I take heed to podcasts, and I don’t have a commute or different downtime for listening. Your preferences and your scenario could also be a lot totally different.
What precisely do listeners count on from these podcasts? Do customers count on to be taught, or do they solely need to discover out whether or not the e book has what they’re in search of? That relies on the subject. I can’t see somebody studying Go from a abstract—possibly extra to the purpose, I don’t see somebody who’s fluent in Go studying how you can program with AI. Summaries are helpful for presenting the important thing concepts introduced within the e book: For instance, the summaries of Cloud Native Go gave a superb overview of how Go might be used to handle the problems confronted by individuals writing software program that runs within the cloud. However actually studying this materials requires examples, writing code, and working towards—one thing that’s out of bounds in a medium that’s restricted to audio. I’ve heard AIs learn out supply code listings in Python; it’s terrible and ineffective. Studying is extra probably with a e book like Facilitating Software program Structure, which is extra about ideas and concepts than code. Somebody may come away from the dialogue with some helpful concepts and probably put them into observe. However once more, the podcast abstract is barely an summary. To get all the worth and element, you want the e book. In a latest article, Ethan Mollick writes, “Asking for a abstract will not be the identical as studying for your self. Asking AI to resolve an issue for you will not be an efficient option to be taught, even when it feels prefer it ought to be. To be taught one thing new, you’re going to must do the studying and considering your self.”
One other distinction between the NotebookLM podcasts and ours could also be extra essential. The podcasts we generated from our toolchain are all about six minutes lengthy. The podcasts generated by NotebookLM are within the 10- to 25-minute vary. The longer size may permit the NotebookLM podcasts to be extra detailed, however in actuality that’s not what occurs. Fairly than discussing the e book itself, NotebookLM tends to make use of the e book as a leaping off level for a broader dialogue. The O’Reilly-generated podcasts are extra directed. They comply with the e book’s construction as a result of we offered a plan, a top level view, for the AI to comply with. The digital podcasters nonetheless categorical enthusiasm, nonetheless herald concepts from different sources, however they’re headed in a path. The longer NotebookLM podcasts, in distinction, can appear aimless, looping again round to choose up concepts they’ve already coated. To me, not less than, that looks like an essential level. Granted, utilizing the e book because the jumping-off level for a broader dialogue can be helpful, and there’s a steadiness that must be maintained. You don’t need it to really feel such as you’re listening to the desk of contents. However you additionally don’t need it to really feel unfocused. And if you would like a dialogue of a e book, you must get a dialogue of the e book.
None of those AI-generated podcasts are with out limitations. An AI-generated abstract isn’t good at detecting and reflecting on nuances within the unique writing. With NotebookLM, that clearly wasn’t underneath our management. With our personal toolchain, we may definitely edit the script to mirror no matter we needed, however the voices themselves weren’t underneath our management and wouldn’t essentially comply with the textual content’s lead. (It’s debatable that reflecting the nuances of a 250-page e book in a six-minute podcast is a dropping proposition.) Bias—a type of implied nuance—is a much bigger challenge. Our first experiments with NotebookLM tended to have the feminine voice asking the questions, with the male voice offering the solutions, although that appeared to enhance over time. Our toolchain gave us management, as a result of we offered the script. We received’t declare that we have been unbiased—no person ought to make claims like that—however not less than we managed how our digital individuals introduced themselves.
Our experiments are completed; it’s time to point out you what we created. We’ve taken 5 books, generated quick podcasts summarizing every with each NotebookLM and our toolchain, and posted each units on oreilly.com and in our studying platform. We’ll be including extra books in 2025. Take heed to them—see what works for you. And please tell us what you suppose!
