Live data from Hacker News

NotebookLM Audio Overviews are now available in over 50 languages

blog.google

51–60 of 108 posts

Re: NotebookLM Audio Overviews are now available in over 50 languages

#51
post #17

NotebookLM audio overviews/podcasts have been an absolute boon for my homeschooled kids. They devour audiobooks and podcasts, and they love learning by listening to these first. Then when we come together for class, we discuss what was covered, and can spend time diving into specifics or doing activities based on the content. It’s super nice to have another option for a learning medium here. To generate them, we’ve s…

I hope you encourage your kids to actually read as well.

Oh don’t worry, they make excellent use of their library cards. :)

Re: NotebookLM Audio Overviews are now available in over 50 languages

#52
post #6

Do people find NotebookLM useful? For my use case of converting papers into podcasts, the explanations are too general (which misses the important parts of the paper) and contain too much fluff. I suspect that changing the underlying model to Gemini 2.5 Pro would produce better transcripts, but right now there's no way of determining what model is being used.

I've found it very useful for providing accessible introductions to technical papers that are otherwise difficult for me to get started with understanding.

If I encounter a paper that is too difficult for me to digest just by reading, then I take a step back, feed it into NotebookLM, and listen to that summary. I've only done this a few times, but so far it hasn't failed to give me the overview and momentum that I need to take another stab and successfully dig into the paper and digest it on my own.

As others have noted, it can gloss over certain details and miss important points from time to time, but overall it does a fantastic job of giving me an introduction to a complex topic and making it far less indimidating / overwhelming.

Re: NotebookLM Audio Overviews are now available in over 50 languages

#53

I really don't understand why they went with this podcast style. Sure, it makes an impression the first few times, great for a showcase or an announcement. The problem though is that it soon becomes pretty annoying, especially because the hosts go back and forth between knowing nothing and knowing everything about the topic. They should at least choose randomly which one does the explaining to whom.

You should check new features - like asking questions as a listener.

I don't use it a lot, but it's useful when you want to have an engaging audio interface to long (50p+) reports, which you wouldn't normally read because it's not your area of expertise or you don't have time, but you can listen while doing some cardio or chores.

Re: NotebookLM Audio Overviews are now available in over 50 languages

#54

NotebookLM podcasts are like a caricature of a real podcast. Every little verbal technique or narrative style that might be used by a normal podcaster in a subtle way is taken to an extreme. The last one I listened to one host would repeat a keyword or phrase the other host had just said for emphasis — except they did incessantly — with multiple words in every sentence for many sentences in a row.

> NotebookLM podcasts are like a caricature of a real podcast. Every little verbal technique or narrative style that might be used by a normal podcaster in a subtle way is taken to an extreme.

So true.

Re: NotebookLM Audio Overviews are now available in over 50 languages

#55
post #47

I tried it with Japanese, and it sounded about as good as in English. Only at one point did it sound unnatural. Japanese two-person conversation uses a lot of backchannelling ( aizuchi ), that is, semilinguistic sounds made by the listener to indicate attention and emotional reaction. At one point, the female voice said very distinctly " fumu fumu, " which is how such aizuchi might be written in a script or manga. In…

Sometimes you actually say fumu fumu out loud in a conversation for comedic effect.

Re: NotebookLM Audio Overviews are now available in over 50 languages

#56
post #47

I tried it with Japanese, and it sounded about as good as in English. Only at one point did it sound unnatural. Japanese two-person conversation uses a lot of backchannelling ( aizuchi ), that is, semilinguistic sounds made by the listener to indicate attention and emotional reaction. At one point, the female voice said very distinctly " fumu fumu, " which is how such aizuchi might be written in a script or manga. In…

Sometimes you actually say fumu fumu out loud in a conversation for comedic effect.

Yes. In fact, I laughed when I heard the NotebookLM voice say that. It was comically out of place in the context.

Re: NotebookLM Audio Overviews are now available in over 50 languages

#57

NotebookLM podcasts are like a caricature of a real podcast. Every little verbal technique or narrative style that might be used by a normal podcaster in a subtle way is taken to an extreme. The last one I listened to one host would repeat a keyword or phrase the other host had just said for emphasis — except they did incessantly — with multiple words in every sentence for many sentences in a row.

Although I 100% agree, there is still a place for it. We place generated conversations with our case studies, and have receive good positive feedback so far, especially from the non-technical crowd. See example https://resonancy.io/case-studies/flava-process-digitization

Of course one can invest more in better authenticity but for what it is, I believe it is a good bang for effort..

Also, if you listen to it for a while, and get over the initial cringe, it becomes enjoyable, at least for me. Some visitors even asked if it was Ai generated. lol

Excited and frightened about the future where its more a real. This was a cool comparison I came across recently [2]

Interestingly I saw today the Descripts Avatars are made to sound and look non-realistic on purpose to avoid I guess all kind of issues, but they claim they want to leave something authentic on the table for real content. Which I think is a good move..

[1] - https://resonancy.io/case-studies/flava-process-digitization [2] - https://yummy-fir-7a4.notion.site/dia

Re: NotebookLM Audio Overviews are now available in over 50 languages

#58

Earlier quoted context omitted.

I've used them. They're very nifty. Google did good here. One thing I'll note is they only cover the "high level" aspects. No depth. I'd recommend them for someone who is either already very knowledgeable or for someone not at all knowledgeable who is looking for an overview before they plan to do deeper learning/studying through reading.

> or for someone not at all knowledgeable who is looking for an overview before they plan to do deeper learning/studying through reading Yep. This is what I have used them (sparingly) for — a scaffold to build the deeper learning onto. My brain struggles to retain information when it doesn’t have a high-level understanding of how/why a system works and how individual parts connect and interact, even if it is all even…

Very well said.

Re: NotebookLM Audio Overviews are now available in over 50 languages

#59

Earlier quoted context omitted.

There's a collapse feature (the [-] link at the top of the post)

It's still far too much for a HN comment. You have to scroll down a couple pages' worth before you even realize this might be SO long you need to collapse it. So then you've got to scroll back UP a couple pages, find the teensy [-] link... It's enough to just post the link to the list of languages. The list itself doesn't belong in a comment here, when it's that long.

not to mention most of us know how to click to a source to view the authoritative list. why repeat it here?

Re: NotebookLM Audio Overviews are now available in over 50 languages

#60

Earlier quoted context omitted.

For YouTube videos it's hard to beat (1) copy transcript to clipboard (from eg tactiq) (2) paste into LLM chat and ask for summary

Full disclosure, I work for Google opinions are my own etc etc The LLM built into YouTube is one of the few LLM chatbots bolted onto existing apps that I actually find useful. Not just for summaries but questions like "what is the timestamp in this 2 hour video where they talk about _____".

"LLM built into YouTube…" The what now? This is the first I've heard of this.
Post reply on HN