Could this be extended to include podcast ad-skipping? Being able to define A-B points and adding that to a blocklist would be amazing. I have several podcasts I've essentially stopped listening to because they're so consumed by ads.
We thought about that and actually decided against a dedicated feature doing exactly this. The reason being that we do not want to hurt podcaster's ability to monetize their content.
That being said, with the automatically generated chapters in our app, you do already get a good sense of where the ads are.
I personally am hoping that some of the podcasting 2.0 features will make it easy for listeners to tip podcasters directly. Once we have that, we could implement an ad-skipping feature which is then only activated for listeners who have tipped the podcast creator.
I had not heard about that, but I'm glad for it. I listen to a lot of podcasts, and I try to throw money at them, in a somewhat haphazard way. I'd do it a lot more consistently if I could just push a button in the app.
Being able to skip the ads would be a nice bonus, though I'll admit that I use the existing features to skip ad breaks extensively. (I still end up hearing enough that I'm familiar with the products, and even try to patronize them. In fact, I need some new socks...)
Haha, I know what you mean. I think almost everyone skips the ads to a certain extent. But you still end up hearing about them at some point. Some of my favorite podcasts are Lex Fridman, Tim Ferris and Andrew Huberman. So there is no way around hearing some "Athletic Greens" ads. And after a while, I actually bought some :D
Great to hear your feedback regarding tipping. Maybe we should prioritize this feature.
I think my favorite feature is its good toolkit for speeding things up. I listen to most podcasts at about 1.4x, and there's a button for removing silences. I have no idea how they do it, but it doesn't sound unnatural. It just peps up the pace and makes people sound more lively. I've used other apps and their speedup algorithms aren't as good.
All told with its various speedup features, I download about 30 hours of podcasts a week, but I probably spend half of that actually listening. (At least some of that is ditching episodes I find dull, but not many.)
Other than that I really am just used to my "workflow". New stuff gets downloaded and added to a queue. I imagine most podcast apps have something like that, but this one has a nice feature set for managing it all.
There are already tools for that. Still, might I suggest just skipping manually yourself or paying for ad free access? Creators need to be reimbursed for their efforts, otherwise we'll only be left with those rich enough to do it free or increasingly subtle 'native' ads.
(Full disclosure, I work for a service that helps monitize ad free feeds. Opinions are my own, don't reflect my employer, and obviously I'm biased.)
I completely get that. See my comment above why we decided against having a dedicated feature for this. I'm hoping that tipping (or similar forms) will get more popular in the future and be supported by more podcast creators in their RSS feed.
Wow! I'm working on something exactly like this as a personal project!
I have a few questions about how you're doing time segmentation.
Are you using a purely text based approach? as in your pipeline looks like
STT -> some BERT based model for segmentation/summary?
or are you using a text + audio model to get extra signal?
Have you found any cool tricks (pre-processing/heuristics) that really improved your approach?
How are you dealing with ad placement insertion that can have different times for different users? For example user A might have a 30 second ad inserted and user B might have two ads inserted for a total of 60 seconds. That would shift all your times at a user specific level. Or are you serving the podcasts from your own server?
My project goal is slightly different than yours in that my goal is almost entirely automatically skipping ads until I am able to just pay a subscription fee to the podcasters to support their content.
Awesome app! Super exciting to see folks working on this
Cool! That's great. I think there's so much still to do in the space of AI for spoken audio. Be it podcasts, audio books, video calls or similar. So definitely keep at it.
I hope you understand that I can't reveal all of our tricks. But what I can say is that it definitely helped us to think about what we as humans use as input for our processing in these situations. So it's not just text. The audio has value as well. To see this you can do a small experiment by just looking at the transcript manually and then trying to find optimal segmentation points. It's difficult.
Dynamic ad insertion is also still a challenge for us. We'd like to develop a technical solution for it but haven't found the time to tackle it yet.
Cool! Nice to hear that you're already using it :)
I'll add your vote to the apple watch app request. We do have it on the longer term roadmap. But given that we are still early, we are trying to focus our energy as much as possible on the mobile experience to make sure we get that part right before we branch out. After that, we'd like to build a car, smart watch and web-app version (not necessarily in that order).
Can explain how it works from a user perspective? The website is slim on details. It just has one sentence explaining what it does. I don’t want to install it to find out.
EDIT: I guess the Apple App Store description has the info I wanted
Yes, we definitely need to add more info on the homepage. The best way to get an overview of how it works & feels like as a user is this youtube video here, which we created for our PH launch today: https://www.youtube.com/watch?v=jzPekGpC4uw
Let me know if you have any specific questions. Happy to answer :)
Looks great! I’ll probably use it just for the chapters alone. Huberman lab only has “clickable” YouTube but I find I end up getting distracted while I’m on there. This is way better.
Unrelated: I noticed you’re not using the App Store banner on your landing page. Why is that? Difficulty tracking conversions?
Yes, there was! And there are even some similarities.
My understanding is that they focused on collecting valuable pages from the web. In comparison, we are focused on collecting valuable moments from podcasts :)
Any plans to go beyond podcasts? I'd like to import any EPUB, PDF or TXT document, have it read to me by text-to-speech, and then have all the features you currently have for podcasts (i.e. reading along on the screen, one-tap highlights, etc.).
Given how early we still are we first want to focus on podcasts and make sure we nail the functionality & experience. In the future, we then want to enable users to also upload their own audio content (e.g. an audio book) and benefit from all of the same features.
For now, we haven't really thought about enabling text mediums and going the other way around (text to speech instead of speech to text). You could however check out the Matter app. Not sure whether you can upload your own pdfs, but you can do text-to-speech for blog posts, including highlighting. They also have a Readwise integration like us.
Gotcha. No, if you have plans to focus on audio, then, by all means, don't let yourself get sidetracked. For text content, I already am using Voice Dream Reader, which, in my mind, is the best there is. Being able to study both text and audio content in the same app and with the same workflow for highlights would just be the icing on the cake.
And I really like your one-tap highlight functionality (or triple clicking the headphone buttons). Very useful when driving or when the phone is tucked away and you're listening via headphones.
Thx! With the highlighting, one of our main goals is to make it as easy as possible. At least for me personally, if it's not easy to do, I won't do it. Mainly because I am often on the go when listening to podcasts.
And thx to AI, this is now much more possible.
Exactly. For me, if it’s not easy to record a highlight, I will stop reading in that situation for fear of missing something important that I’d want to get back to later. Hence one tap highlighting lets me “read” where I normally couldn’t.
neat! I'm going to try it. I wonder if I can import my subscriptions from Castro? And, I wonder if there is anything similar to the queue feature to always have a custom-curated list of fresh episodes to listen to.
My only feedback before downloading... the video demo[1] (ironically for a podcast app>) has an unpleasant voiceover, the woman needs a drink of water! Content-wise it's great but I was distracted by the almost ASMR-like experience of feeling like she was very close to my ear, and I didn't like it.
Haha, note-taken. This was our first public video and we just recorded it ourselves. Lot of potential for improvement :D
Regarding your questions: Yes, you can import your subscriptions from Castro via OPML. We have a How-To in the app for how to do this specifically for Castro.
The queue & inbox system is still missing, but very high on our roadmap. We're actually working on the queue right now. With the inbox, our plan is to go in a similar direction as Castro has done it.
Let me know if you have any more thoughts on the queue/inbox system.
This looks really cool! Can't wait to try it when I'm listening to podcasts on my walk; are you using a paid API for the transcript or are you using an open source solution yourselves?
We don't have a clear date yet when we will tackle it, but it will definitely come. And the more users request it, the sooner it will come. So I'll add your vot to this request ;)
Are your private feeds all podcasts or also some other content?
Just like all other podcast apps, we are relying on the RSS feed system and are not streaming any audio from our own servers. The podcasts are streamed directly from the podcast hosters via the URLs provided by podcasters in their RSS feeds.
