Live data from Hacker News

Google Illuminate: Books and papers turned into audio

illuminate.google.com

1–10 of 251 posts

Re: Google Illuminate: Books and papers turned into audio

#2
Very clever use case. I'm presuming the set up here is as follows:

- LLM-driven back and forth with the paper as context

- Text-to-speech

Pricing for high quality text to speech with Google's studio voices run at USD 160.00/1M count. And given the average 10 minute recording at the average 130 WPM is 1,300 words and at 5 characters per word is 6500, we can estimate an audio cost of $1. LLM cost is probably about the same given the research paper processing and conversation.

So only costs about $2-3 per 10 minute recording. Wild.

Re: Google Illuminate: Books and papers turned into audio

#4

Great idea. I wonder how long until we'd see a lot of "autogenerated" podcasts with syndicated advertising inside spamming the podcast space. Like with robovoiced videos on YT reading some scraped content.

Amazon has a project for this already, apparently they are using voice actors to train it.

Re: Google Illuminate: Books and papers turned into audio

#6
post #2

Very clever use case. I'm presuming the set up here is as follows: - LLM-driven back and forth with the paper as context - Text-to-speech Pricing for high quality text to speech with Google's studio voices run at USD 160.00/1M count. And given the average 10 minute recording at the average 130 WPM is 1,300 words and at 5 characters per word is 6500, we can estimate an audio cost of $1. LLM cost is probably about the…

Retail pricing != Google's actual cost.

Re: Google Illuminate: Books and papers turned into audio

#8

Great idea. I wonder how long until we'd see a lot of "autogenerated" podcasts with syndicated advertising inside spamming the podcast space. Like with robovoiced videos on YT reading some scraped content.

Would you listen to an auto-generated podcast? Seems like removing the humans from the equation kind of defeats the purpose.

Re: Google Illuminate: Books and papers turned into audio

#10

Is that audio all generated? All the pauses, breaths, speed ups and everything?

From the "Help" modal:

"Illuminate is an experimental technology that uses AI to adapt content to your learning preferences. Illuminate generates audio with two AI-generated voices in conversation, discussing the key points of select papers. Illuminate is currently optimized for published computer science academic papers.

As an experimental product, the generated audio with two AI-generated voices in conversation may not always perfectly capture the nuances of the original research papers. Please be aware that there may be occasional errors or inconsistencies and that we are continually iterating to improve the user experience."

Post reply on HN