The 7800 Software Guide Podcast

[RevEng]

I've been playing around with Google's NotebookLM product. It's an AI tool intended to help you extract information to better understand the material contained in a set of documents. (could be research papers, school texts, audio lectures, etc.) It can generate information summaries, FAQs, Table of Contents, Timelines, you can interrogate the AI about the info in the documents, and... it can generate an AI two person podcast.

 

Naturally, I generated a podcast from the 7800 Software Guide. I think the description of holey DMA is lacking the right context, and they mispronounce "Maria" several times... but otherwise it's fun and pretty engaging! Check it out at the MARIA Documents section of the 7800 wiki!

[Eagle]

😂😂😂

Fantastic 

[+Muddyfunster]

When I heard "Mariah", I got very scared. It's almost time to defrost her after all!

 

 

Thanks for linking and sharing Mike  

 

 

[+Karl G]

It's really quite remarkable how much it gets right, even if there were three different pronunciations for "Maria". 🙂 

[RevEng]

Lol. Yeah, the Maria pronunciation really gets on my nerves, mainly because the content is pretty good otherwise.

 

I tried creating another document that contained the proper pronunciation of "Maria", and the notebook interface correctly identified the doc as containing pronunciation information for "maria", but it didn't help. I think the script generation AI is a bit uncoupled from the voice generation AI.

 

According to this youtube interview, they're looking at adding stuff to guide the podcast content. Hopefully they add in something to fix the pronunciation too.