Generated Transcripts in Pocket Casts
With version 7.85, we’ve introduced Generated Transcripts, a powerful new feature that makes engaging with your favorite podcasts easier than ever. Available on both Android and iOS for our Plus and Patron members, this feature allows you to follow along with podcast conversations.
Podcasts are full of incredible insights, but sometimes you want to revisit a key moment without scrubbing through the entire episode. With Generated Transcripts, you can now read along, search for specific phrases, and quickly find key discussions—even if a show doesn’t have their own transcripts.
As with Apple’s offering, this happens on the server, so it doesn’t work with your own uploads. In fact, it’s only available for a subset of popular podcasts.
Despite Marco Arment being a longtime friend, I switched from using his Overcast as my preferred podcast player to using the stock Apple Podcasts app on my iPhone and iMac. I did so largely because of the immense accessibility transcripts provide me; Apple announced support for transcripts a little over a year ago, which is when I made the decision to change over.
It looks like there were some APIs announced at WWDC that will make it possible for future versions of Overcast and other apps to generate transcripts on-device.
I was watching the new speech transcription APIs video and looking at the example code. It doesn’t feel like an Apple API. They’ve always been very straightforward simple easy to use APIs for powerful features.
Now with all the Swift async sequences and the new 4 part API they have you have to setup and create helper objects you just need to “know” that’s how you create it 5 steps earlier than you’d think you need it.
The APIs are going the same way.
Notes does not perform identically across platforms, with the Mac version producing notably better results than the iPhone version. If you care about transcription accuracy, let a Notes recording on the iPhone sync to an Apple silicon Mac and transcribe it there.
[…]
Audio Hijack and MacWhisper support about 100 languages because they use Whisper. Notes, on the other hand, is currently limited to English.
[…]
Audio Hijack is more accurate than Notes, and transcription comes on top of numerous other audio recording capabilities. However, it doesn’t provide line breaks, and if accuracy is important to you, MacWhisper is a better choice.
Previously:
Update (2025-06-17): John Voorhees:
What stood out above all else was Yap’s speed. By harnessing SpeechAnalyzer and SpeechTranscriber on-device, the command line tool tore through the 7GB video file a full 55% faster than MacWhisper’s Large V3 Turbo model, with no noticeable difference in transcription quality.
2 Comments RSS · Twitter · Mastodon
I tried Pocket Casts recently, and it was shit. Why would I want to play the previous episode after the currently playing?
Will Pocket Cast display the transcripts in the same tiny font size like the rest of the interface with no way to change it?
This app unusable if you don't have perfect vision and the Github issues regarding dynamic text are ignored since 2023.