shadesofmike

The app works by blocking ads that the community finds objectionable. We have found that a lot of users are frustrated by longer and longer ads, repetitive ads, and ads inappropriate for their interests. In particular, a lot of our users are not based in America, so an ad for buying US postage stamps isn't that relevant.

We allow users to subscribe to up to 6 podcasts without paying the subscription fee. I think this is a pretty good deal. Unfortunately, unlike a desktop ad blocker - we need a lot of human involvement to block the ads.

Hi everyone, I got sick of hearing the same ads over and over again in podcasts, so I made this ad blocker for podcasts.

How it detects ads?

The app detect ads by either a user identifying an ad (by clicking the Podblocker button) or by a large minority of users skipping forward at the same point in a podcast. Once an ad is identified, we have a team that locates the exact starting and ending position of the ad.

Why not use ML to identify ads?

We would love to, but we can't work out how to make it economically feasible. A bag-of-words model we think would work reasonably well to detect an ad. However, at this stage, the cost of speech to text recognition is around $0.02 a minute, so if you are identifying ads in 10,000 podcasts that release once a week with an average duration of 45 minutes you are looking at spending around $468,000 a year just to get speech to text recognition.

If anyone has any other ideas on how to tackle this we are all ears.

It's super sad. It was so great when it was hosted by them. I am bit worried about what is going to happen to the documentation.

I am currently using SashiDo which I quite like. Excellent support. Before that, I tried NodeChef, but I have found Sashido a little more intuitive. Your millage may vary.