Like nearly everybody, we have been impressed by the flexibility of NotebookLM to generate podcasts: Two digital folks holding a dialogue. You can provide it some hyperlinks, and it’ll generate a podcast based mostly on the hyperlinks. The podcasts have been attention-grabbing and fascinating. However in addition they had some limitations.
The issue with NotebookLM is that, when 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 offers you little management over the outcome. There’s an non-obligatory immediate to customise the dialog, however that single immediate doesn’t permit you to do a lot. Particularly, you’ll be able to’t inform it which subjects to debate or in what order to debate them. You possibly can strive, however it gained’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 possibly can’t inform it to iterate by saying “That was good, however please generate a brand new model altering these particulars” like you’ll be able to with ChatGPT or Gemini.
Can we do higher? Can we combine our information of books and expertise 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; you’ll want to learn to do one thing with AI that’s higher than what the AI may do by itself. It is advisable combine synthetic intelligence with human intelligence. To see what that might appear like in observe, we constructed our personal toolchain that offers us way more management over the outcomes. It’s a multistage pipeline:
- We use AI to generate a abstract for every chapter of a ebook, ensuring that every one the necessary 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 precise subjects in the precise order. That is additionally a chance to appropriate errors and hallucinations.
- We use Google’s speech-to-text multispeaker API (nonetheless in preview) to generate a abstract podcast with two members.
Why are we specializing in summaries? Summaries curiosity us for a number of causes. First, let’s face it: Having two nonexistent folks 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 prospects ceaselessly ask for summaries: summarize this ebook, 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 ebook—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 ebook might be useful, and does so higher than the again cowl copy or a blurb on Amazon.
With that in thoughts, we needed to suppose via what probably 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 ebook, my eyes (ears?) glazed over shortly. It was a lot simpler to hearken to a podcast-style abstract the place the digital members 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 necessary query. Sooner or later, the listener loses curiosity. We may feed a ebook’s complete textual content right into a speech synthesis mannequin and get an audio model—we could but try this; it’s a product some folks need. However on the entire, we anticipate summaries to be minutes lengthy slightly than hours. I’d hear for 10 minutes, possibly 30 if it’s a subject or a speaker that I discover fascinating. However I’m notably impatient once I hearken 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 anticipate from these podcasts? Do customers anticipate to study, or do they solely need to discover out whether or not the ebook has what they’re in search of? That is determined by 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 offered within the ebook: For instance, the summaries of Cloud Native Go gave an excellent overview of how Go may very well be used to handle the problems confronted by folks writing software program that runs within the cloud. However actually studying this materials requires taking a look at 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 seemingly with a ebook 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 simply an outline. To get all the worth and element, you want the ebook. In a current article, Ethan Mollick writes, “Asking for a abstract isn’t the identical as studying for your self. Asking AI to resolve an issue for you isn’t an efficient solution to study, even when it feels prefer it must be. To study one thing new, you’ll should do the studying and pondering your self.”
One other distinction between the NotebookLM podcasts and ours could also be extra necessary. 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. Moderately than discussing the ebook itself, NotebookLM tends to make use of the ebook as a leaping off level for a broader dialogue. The O’Reilly-generated podcasts are extra directed. They observe the ebook’s construction as a result of we supplied a plan, an overview, for the AI to observe. The digital podcasters nonetheless specific enthusiasm, nonetheless usher in concepts from different sources, however they’re headed in a route. The longer NotebookLM podcasts, in distinction, can appear aimless, looping again round to choose up concepts they’ve already coated. To me, no less than, that seems like an necessary level. Granted, utilizing the ebook 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 ebook, you must get a dialogue of the ebook.
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 actually edit the script to replicate no matter we needed, however the voices themselves weren’t underneath our management and wouldn’t essentially observe the textual content’s lead. (It’s controversial that reflecting the nuances of a 250-page ebook in a six-minute podcast is a shedding proposition.) Bias—a type of implied nuance—is a much bigger subject. 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 supplied the script. We gained’t declare that we have been unbiased—no one ought to make claims like that—however no less than we managed how our digital folks offered themselves.
Our experiments are completed; it’s time to indicate 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. We’ll be including extra books in 2025. Take heed to them—see what works for you. And please tell us what you suppose!
