Marco Arment:

Unforgetful isn’t a new productivity system to learn.

[…]

This is designed for a small number of short-term tasks. What do you need to do today, tomorrow, this week, or this month?

[…]

If you want tagging, folders, archives, or other ways to organize or file away tasks, this isn’t the app you’re looking for.

Unforgetful is for people who know that if they file away a task, it never gets done.

I’m an OmniFocus person. I love tagging, folders, and archives; I never want to see a notification for a to-do item. I prefer pull to push. So this is absolutely not the right tool for me. But I like the fresh thinking behind this app and how the various design choices interact to make it an opinionated tool for the right type of person.

Marco Arment:

Calendar alarms changed my life. Events without alarms don’t happen.

[…]

Most of my Reminders interaction has always been via Siri and notifications. And that fits me very well, with three major exceptions:

1. If I say “Remind me to buy milk,” but I forget to specify a time (or Siri misses it), Reminders will never notify me, and I’ll never check the app, so it’ll be lost.
2. If I inadvertently dismiss a Reminders notification without snoozing it, Reminders will never notify me about it again, so it’ll be lost.
3. When I do snooze a Reminders notification, which I do a lot, the snooze options suck.

He has good solutions to these and other problems. I’m tempted to try out Unforgetful just for the purported quick capture of dictated reminders, however there’s no watch app.

Listen to Accidental Tech Podcast to hear about unfortunate limitations of EventKit. Reminders itself is interesting to me in that the (private) data model is now so rich, but I’m put off by the UI, the lack of export, and the limited support for driving it from the keyboard.

Previously:

• TabControl Scam and the App Review Queue
• OmniFocus 4.8.10
• Dictating Literal Reminders to My Apple Watch
• CKSyncEngine
• Bulk Setting “Catch Up Automatically” in OmniFocus
• Overcast’s New Foundation
• Adventures in Siri Failures: Reminders Edition

Apple has finally completed its silicon transition: macOS 27 drops all Intel-based Macs, and iPadOS 27 and watchOS 27 each leave five models by the wayside, whereas the iPhone compatibility list remains unchanged.

Om Malik (2023):

One of the key advantages of MacWhisper, as it utilizes the Whisper technology, is its superior accuracy in transcriptions compared to other services I have used. I was an early adopter of Rev.com and eventually switched to Otter.ai, for which I paid approximately $100/year. However, I have since canceled my subscription.

[…]

After comparing the audio transcripts from MacWhisper and Otter, I found that while Otter’s formatting is superior, there is hardly any difference in the transcriptions. I started with the free model, which was sufficient for my needs, and eventually upgraded to the large models. Nowadays, I primarily use MacWhisper to transcribe my voice memos, which I then import into Lex.Page.

Bon Adamson:

Whisper, which is made by OpenAI, has the distinct advantage of allowing you to transcribe audio in almost any language you may ever need to. For the time being, Otter can only transcribe English. The benefits of better accuracy and accurate punctuation that the service already holds over Siri hold up across other languages as well. If you’re looking to transcribe non-English audio accurately, Whisper is definitely the best option available on Mac.

Dan Moren:

By taking advantage of OpenAI’s Whisper framework, Audio Hijack can now take any audio it’s recording and generate a text transcript. While this process was possible before—see Jason’s lengthy post about his workflow—it required a lot of fiddling and several different tools to accomplish; it’s certainly a lot easier to simply drop Audio Hijack’s block into your existing session. If you record multiple sources, it can even appropriately label each one—though if you record multiple people via one input, say the other end of a Zoom call, it can’t distinguish between the various participants.

Inscribe (2026, Hacker News):

Apple’s new SpeechAnalyzer is the most accurate on-device speech engine we tested. It beat every Whisper model we ship, including Whisper Small, on both the clean and the noisy half of LibriSpeech, while running roughly three times faster than Small. And the API it replaces, SFSpeechRecognizer, came last on clean speech: behind even Whisper Tiny, a 40MB model.

[…]

The new API cuts word error rate by 3.5 to 4x on the same audio: from 9.02% to 2.12% on clean speech, and from 16.25% to 4.56% on noisy speech. There is no accuracy trade-off to weigh; the new API wins everywhere we measured, and it produces punctuated, cased text where the legacy engine’s output is rougher.

[…]

All five engines ran comfortably faster than real time: between roughly 12x and 40x on the M2 Pro, meaning an hour of audio transcribes in about 1.5 to 5 minutes on-device. SpeechAnalyzer was about 3x faster than Whisper Small per second of audio while beating it on accuracy.

Yuki:

SpeechAnalyzer’s ReportingOption.fastResults reads like a knob you’d reach for when you want to trade power for latency. That framing is what cost me the afternoon.

[…]

If a recording matters — and in a notes app, a lost meeting is the worst thing that can happen to a user — then the container you write while recording has to be PCM in CAF. Not m4a, and not AAC-in-CAF either.

[…]

AVAudioEngine’s inputNode silently ignores your device selection

[…]

I wanted summarization to run on-device. Everything else in Nib’s transcription path does, the audio never leaves the machine, and it would have been a much cleaner story to tell.

But 4,096 tokens for the Foundation Models isn’t enough.

Previously:

• Apple Foundation Models in appleOS 27
• WhisperPad Rejected From the Mac App Store
• Overcast Transcripts
• Generated Transcripts in Pocket Casts
• Apple Podcasts Transcripts
• Dictation and Predictive Text in macOS Sonoma and iOS 17
• macOS vs. Dragon Dictation