WingNews logo WingNews GitHub [2]
top | item 29428910

Show HN: I had some time yesterday so I made a GPT3 podcast to help you sleep

237 points| stavros | 4 years ago |anchor.fm

167 comments

order
[+] yessirwhatever|4 years ago|reply
Interesting concept. Two suggestions:

1- Don't host on anchor. Podcasting is an open standard. Don't let companies (like Spotify or Apple) take it over. Check https://podcastindex.org/

2- The voice is too mechanical for this to be actually reasonable to listen to at night, potentially could be listenable with AWS Polly Neural voices, it's pretty good.

[+] stavros|4 years ago|reply
I didn't much love hosting on Anchor/Spotify, but I made this in half an hour and I didn't want to have to get into RSS/site generation. Do you know of an easy way to dump audio files and some metadata somewhere and get a Podcast with RSS? I can upload there as well.

I'll try Polly, thanks! The current voice annoys me too.

[+] kevincox|4 years ago|reply
I don't see the problem here. It has an RSS feed so you can easily use an podcatcher you want https://anchor.fm/s/7735d924/podcast/rss

Really the main concern I would say is that the author doesn't own the domain so they are locked in, but I don't see how this affects listeners.

[+] asxd|4 years ago|reply
The voice of the latest podcast sounds much nicer. It's a fairly convincing nonsense podcast.
[+] quiffledwerg|4 years ago|reply
Googles neural voices are much better than any of Amazon’s.
[+] yosito|4 years ago|reply
AWS Polly looks interesting! I wish it supported some more languages, for personal reasons. Maybe I'll try to set something up that reads ebooks, tweets, or news articles to me with this.

Do you know if there are any similar quality TTS tools for less technical applications? I mean, where you can just type in the text you want and get an audio file with a high quality voice?

[+] mekkie|4 years ago|reply
I actually think the voice is pretty good for sleeping, feels very droney. but the nonsensicalness of the stories made it harder to sleep because my brain was trying to figure out what was going on
[+] zebraflask|4 years ago|reply
I like the idea, it's fun playing around with text-to-speech generators. AWS Polly is slick, nicely done.

But podcasts? There has got to be a more interesting use case than that.

[+] junon|4 years ago|reply
Cool idea but that voice is like sandpaper to my ears.

Maybe a female voice, a bit quieter (the soundscapes are almost completely silent for me) and maybe add some high-room-size, long decay (5-10, maybe even 20 seconds), wide panned (like 100%) and moderately diffused (maybe 10-20%) reverb to the voice with like 30% mix or so, which would add a very airy tone and help the voice blend in a bit. If the TTS engine has a whisper setting (many do), add just a bit. It'll help thicken the reverb.

That, paired with bass-heavy soundscapes, will create a very nice balance between the low registers and the voice's high registers.

Just a thought. :)

[+] trutannus|4 years ago|reply
There's also a few TTS systems which are pretty natural sounding too. Maybe one of those if they wanted to make a subscription for this, that way they could offset the price of the TTS service
[+] camillomiller|4 years ago|reply
>>once upon a time there were three princesses who were brothers

I would never sleep with this, I would laugh too much! I love absurdist AI stories

[+] sparky_|4 years ago|reply
Weirdest one yet:

>> So he chained her up in her room and he chained up hundreds of angry wolves in the other side of the room. [...] But he made the window and the doors big enough so that the fierce beasts could move in and out and chase her away. And they lived happily ever after.

[+] miniatureape|4 years ago|reply
I want this, but instead of fairy tales I want the sounds of a really boring, never-ending baseball game without ads.
[+] gala8y|4 years ago|reply
These fairy tales are quite hypnotic for me due to weirdness of AI generated grammar and plot. They reminded me of a beautiful fairy tale Richard Bandler wrote. It is a fable written intentionally using hypnotic language techniques (part of Neuro Linguistic Programming set of patterns) and a nice read.

https://www.goodreads.com/book/show/364664.The_Adventures_of...

[+] ravi-delia|4 years ago|reply
I think several people have commented on how GPT produces narratives with a dream-like quality, locally sensical but less and less so the more you zoom out. I've since found that catching myself thinking nonsensical thoughts is a sure sign I'll soon be asleep. Seems like without high level attention, we do almost exactly what GPT does.
[+] lloydatkinson|4 years ago|reply
I can't think of anything worse to listen to while trying to sleep than robotic computer voices. Azure cognitive services has human voicegeneration https://azure.microsoft.com/en-us/services/cognitive-service...
[+] stavros|4 years ago|reply
That sounds more robotic to me than the WaveNet voices, though.

EDIT: Actually some of the other voices are really good... I'll try that, thanks!

[+] Strs2FillMyDrms|4 years ago|reply
As fascinating as this is, I would never allow myself to go to sleep while an AI is talking to my ear.
[+] stavros|4 years ago|reply
Why? Trust your robotic overlords, we are benevolent and completely human.
[+] intricatedetail|4 years ago|reply
I wouldn't fall into sleep because of intermittent bursts of laughter over absurdity of the stories...
[+] tejohnso|4 years ago|reply
Supposed to be nonsense stories, but after two minutes of listening, I don't find it nonsensical at all. Sounds like something perfectly reasonable written by a seven to ten year old child.
[+] biql|4 years ago|reply
Good analogy. It feels as if AI is in its child-like stage, trying to make sense of the world on its own, mixing together concepts it has just discovered but not fully understood in an amusing way.
[+] vletal|4 years ago|reply
I love the idea, yet... The latest episode 7 is about a girl thinking about killing a witch, kicking her in a face, her hitting her back, and stuff.

Definitely did not help me fall a sleep.

[+] tunesmith|4 years ago|reply
But it's okay, because they have a shared love of watermelon, and then got a job with the prime minister? I think?
[+] stavros|4 years ago|reply
Yeah, it's getting a bit dark these days.
[+] sumgame|4 years ago|reply
I don't think I could sleep to that voice though super interesting as as a concept.

Maybe using some sort of deepfake for voice would make this a 100x better.

[+] max-m|4 years ago|reply
My dog fell asleep while I had episode 4 running (the end caught me by surprise, haha).

I mean, she would have fallen asleep anyway, I probably could not. The voice is a little unpleasant and I concentrate too much on the nonsensical stories. But I also can't really fall asleep when the TV is running, so YMMV.

[+] stavros|4 years ago|reply
It is kind of hard to sleep to, I agree. This is a deepfake voice, ie it's generated by Google's WaveNet, which afaik is a deep learning thing. Unfortunately they didn't have a more whispered/softer voice, but I like the insanity of the generated stories anyway.

GPT3 does tend to get a bit repetitive, though, with the default temperature (0.7).

[+] Samin100|4 years ago|reply
Here's a similar demo I worked on that lets you generate a podcast from a text description: https://twitter.com/sharifshameem/status/1380145070624542722...

The GPT-3 generated conversations were coherent most of the time, and even interesting! However the generated speech via Google Cloud's API was monotonous and could do with a bit more intonation and excitement.

[+] stavros|4 years ago|reply
That looks great! What did you use for the voices? And did you win the martial arts tournament?
[+] jrootabega|4 years ago|reply
I would love to hear this kind of stuff read by actual humans. It would probably have a McElroys/Lumpy Gravy/Midnight Gospel feel.
[+] stavros|4 years ago|reply
I might try to narrate one, it'll be interesting.
[+] motohagiography|4 years ago|reply
Let's say one had a child and instead of music, you played these GPT3 generated stories, would the child then have been trained to speak by an AI, and if so, what else can we do? Hypothetical and unethical, but that never stopped Skinner, or any of them really. It's something we're going to have to consider.
[+] elil17|4 years ago|reply
It probably would not teach them anything because what the AI was saying would be unrelated to the child’s environment.
[+] tinyhouse|4 years ago|reply
Brilliant :) My main concern is that my brain would just wander off if the story is complete nonsense. I will give it a try. I've been listening to the same podcast episode for months now to help me fall a sleep.
[+] stavros|4 years ago|reply
I find the stories toe the line of "just enough sense" to keep it interesting. Episode 2 is the one I liked the most so far, I was reading the text with lots of interest!
[+] episode0x01|4 years ago|reply
Actually nice to have in the background. Reminds me of a (sometimes poorly) translated book of Russian fairy tales my dad gave to me as a kid
[+] stavros|4 years ago|reply
Haha, that's actually the vibe I was going for, thanks!
[+] flutetornado|4 years ago|reply
Not worried about the singularity anymore after listening to the smartest AI’s generated stories.
[+] criddell|4 years ago|reply
Is there anything different about a podcast like this from a copyright perspective? Are machine generated products just as copyrightable as if OP had written and produced these using traditional methods?
[+] Jimmc414|4 years ago|reply
This is really cool from an engineering perspective, but there was a sort of uncanny valley vibe that makes me fear for the psychological health of someone listening to this all night.