using podcastfy (python lib) I just created a workflow where I can turn any url, pdf or youtube video into a custom ai-generated podcast. it even generates an rss feed so I can listen on my phone via fountain when I'm out and about.
I just pointed it at my relatively empty website to see what would happen:
https://cdn.jb55.com/s/bbbd6633c2fafa9c.mp3
this is hilarious.
Isnāt that what Googleās Notebook LLM does?
yeah but I wanted something more programmatic, that could update an rss feed, etc. there doesn't seem to be an api for notebooklm
Eleven labs does exactly this - just put a link to any article or body of text - pick a voice to narrate it (out of hundreds and any language) and save it to your phone or computer or whatever to listen - Iāve been listening to all the long form articles I want to read at the gym !
this is a bit different, it will reformat the content into a podcast (two people talking back and forth and going over the content). its not just direct text to speech. its nice for technical papers that are hard to get through.
Oh got it - like notebook LM :)
The audio ai is really a game changer - love the idea of curating a heap of content (which gives you much more quality control) & creating your own custom conversation on a topic !
I even generate nice titles and descriptions by feeding the transcript into a local llama model 
This is awesome, so far I was manually using Notebook LM, but this sounds almost as good and is ultimately more versatile. Very nice!
Impressive, I wrote a lib to do something similar but I didnāt know how to make it in two different voices
Not sure what podcastfy does, line by line I guess? I noticed i hit the api rate limit on openai tts-hd, not sure why though since i seem like im still under RPM limitā¦
Looking into kokoro now but im not sure if that supports different voices
I gave it a go and its indeed good.
The reason I wrote the code for that is I wanted to convert NIPs readme into some easy to listen / short podcast series that new coming devs could listen on their way back from the office and get a general idea on which nips to use for what purpose.
mine: https://hook.cafe/files/mylib.mp3
podcastify: https://hook.cafe/files/podcastfy.mp3
obviously they win with their voice switch, but I already uploaded mine to apple during the weekend just for a test and I didn't know that python lib existed! Anyways, maybe this will help someone one day:
https://podcasts.apple.com/us/podcast/walk-through-the-nips-of-nostr/id1799447906
Would you be willing to share your workflow? This sounds great.
Itās just podcastfy + some code that modifies an rss feed. I wrote most of it with https://cursor.com and claude 3.7
nostr:npub1m2mvvpjugwdehtaskrcl7ksvdqnnhnjur9v6g9v266nss504q7mqvlr8p9 has a similar tool
loaditfor.me
nostr:npub1wf4pufsucer5va8g9p0rj5dnhvfeh6d8w0g6eayaep5dhps6rsgs43dgh9
Pretty cool
š
Couldnāt get past the pronunciation of āclightningā š
This is awesome
Amazing
