11–20 of 35 posts
Also as a turing test you should make one and never reveal it's entirely automated until it develops a big following. Due to the speed of automation you could mass produce podcasts of different types until one sticks, then the ones gaining more traction put 10x more resources into, etc.
Very good idea and execution. I think you could do a lot more interesting stuff than making it about horoscopes. Also as a turing test you should make one and never reveal it's entirely automated until it develops a big following. Due to the speed of automation you could mass produce podcasts of different types until one sticks, then the ones gaining more traction put 10x more resources into, etc.
I think when the little glitches are ironed out of 'real' TTS - we'll be awash with generated content.
What vocal synthesis program did you use? Sounds 100% real at parts.
Would be great to do it with an off-the-shelf TTS engine but I don't think there quite there yet. I know my recording skills and microphone technique is rubbish - but if I knew what I was doing on that front - I think you'd be really hard pushed to tell it was stitched together phrases.
So how die you do it?
Very good idea and execution. I think you could do a lot more interesting stuff than making it about horoscopes. Also as a turing test you should make one and never reveal it's entirely automated until it develops a big following. Due to the speed of automation you could mass produce podcasts of different types until one sticks, then the ones gaining more traction put 10x more resources into, etc.
I like your thinking :) I thought horoscopes (Because they are kind of repetitive) was a good first fit - because the scripts could be generated from stock fragments 'A chance encounter' etc... I think when the little glitches are ironed out of 'real' TTS - we'll be awash with generated content.
There really is no stopping this train. In 2030 90% of internet content adopting the guise of being from the "real world" will be entirely generated by machine learning models. 90% of conversations you have with strangers online will likewise be with bots catered to influence you in subtle ways to maximize the return on revenue of your attention.
So how die you do it?
[the podcast] = [intro] [main body] [outro]
[main body] = [main prediction] [lucky colours] [alibi] etc
// these rules finally break down to text, eg
[main prediction start] = "A bite from a wild animal" or "A chance encounter"§
So the script has lots of combinations and is semi random - but it should always make sense.
Earlier quoted context omitted.
I like your thinking :) I thought horoscopes (Because they are kind of repetitive) was a good first fit - because the scripts could be generated from stock fragments 'A chance encounter' etc... I think when the little glitches are ironed out of 'real' TTS - we'll be awash with generated content.
I can imagine. Imagine a podcast generation system. You'd simply have to describe the personalities of the host(s), the topic, the general vibe of the theme music, length, hardcode any sponsors, and a GPT-4 powered MLops service could produce something liked by a list of demographics 8 times out of 10 in 5 minutes. There really is no stopping this train. In 2030 90% of internet content adopting the guise of being fro…
The fight is real.
I can’t say I understand the point of this, so my only feedback is that the date in the episode from Saturday 21st of May is announced as “Thursday 21st of April”.
As to the point, its programming practice, perhaps a stepping stone to more elaborate content-generation systems, and jolly good fun too.