This Week's Sponsor:

Washing Machine X9

Spring Clean Your Mac Effortlessly

Posts tagged with "automation"

Using Simon Willison’s LLM CLI to Process YouTube Transcripts in Shortcuts with Claude and Gemini

Video Processor.

Video Processor.

I’ve been experimenting with different automations and command line utilities to handle audio and video transcripts lately. In particular, I’ve been working with Simon Willison’s LLM command line utility as a way to interact with cloud-based large language models (primarily Claude and Gemini) directly from the macOS terminal.

For those unfamiliar, Willison’s LLM CLI tool is a command line utility that lets you communicate with services like ChatGPT, Gemini, and Claude using shell commands and dedicated plugins. The llm command is extremely flexible when it comes to input and output; it supports multiple modalities like audio and video attachments for certain models, and it offers custom schemas to return structured output from an API. Even for someone like me – not exactly a Terminal power user – the different llm commands and options are easy to understand and tweak.

Today, I want to share a shortcut I created on my Mac that takes long transcripts of YouTube videos and:

  1. reformats them for clarity with proper paragraphs and punctuation, without altering the original text,
  2. extracts key points and highlights from the transcript, and
  3. organizes highlights by theme or idea.

I created this shortcut because I wanted a better system for linking to YouTube videos, along with interesting passages from them, on MacStories. Initially, I thought I could use an app I recently mentioned on AppStories and Connected to handle this sort of task: AI Actions by Sindre Sorhus. However, when I started experimenting with long transcripts (such as this one with 8,000 words from Theo about Electron), I immediately ran into limitations with native Shortcuts actions. Those actions were running out of memory and randomly stopping the shortcut.

I figured that invoking a shell script using macOS’ built-in ‘Run Shell Script’ action would be more reliable. Typically, Apple’s built-in system actions (especially on macOS) aren’t bound to the same memory constraints as third-party ones. My early tests indicated that I was right, which is why I decided to build the shortcut around Willison’s llm tool.

Read more

Recording Video and Gaming: A Setup Update→

It’s been a couple of months since I updated my desk setup. In that time, I’ve concentrated on two areas: video recording and handheld gaming.

I wasn’t happy with the Elgato Facecam Pro 4K camera, so I switched to the iPhone 16e. The Facecam Pro is a great webcam, but the footage it shot for our podcasts was mediocre. In the few weeks that I’ve moved to the 16e, I’ve been very happy with it. My office is well lit, and the video I’ve shot with the 16e is clear, detailed, and vibrant.

The iPhone 16e sits behind an Elgato Prompter, a desktop teleprompter that can act as a second Mac display. That display can be used to read scripts, which I haven’t done much of yet, or for apps. I typically put my Zoom window on the Prompter’s display, so when I look at my co-hosts on Zoom, I am also looking into the camera.

The final piece of my video setup that I added since the beginning of the year is the Tourbox Elite Plus. It’s a funny looking contraption with lots of buttons and dials that fits comfortably in your hand. It’s a lot like a Stream Deck or Logitech MX Creative Console, but the many shapes and sizes of its buttons, dials, and knobs set it apart and make it easier to associate each with a certain action. Like similar devices, everything can be tied to keyboard shortcuts, macros, and automations, making it an excellent companion for audio and video editing.

On the gaming side of things, my biggest investment has been in a TP-Link Wi-Fi 7 Mesh System. Living in a three-story condo makes setting up good Wi-Fi coverage hard. With my previous system I decided to skip putting a router on the third floor, which was fine unless I wanted to play games in bed in the evening. With a new three-router system that supports Wi-Fi 7 I have better coverage and speed, which has already made game streaming noticeably better.

Ayn Odin 2 Portal Pro. Source: Ayn.

Ayn Odin 2 Portal Pro. Source: Ayn.

The other changes are the addition of the Ayn Odin 2 Portal Pro, which we’ve covered on NPC: Next Portable Console. I love its OLED screen and the fact that it runs Android, which makes streaming games and setting up emulators a breeze. It supports Wi-Fi 7, too, so it pairs nicely with my new Wi-Fi setup.

A few weeks ago, I realized that I often sit on my couch with a pillow in my lap to prop up my laptop or iPad Pro. That convinced me to add Mechanism’s Gaming Pillow to my setup, which I use in the evening from my couch or later in bed. Mechanism makes a bunch of brackets and other accessories to connect various devices to the pillow’s arm, which I plan to explore more in the coming weeks.

The 8BitDo Ultimate 2 Controller. Source: 8BitDo.

The 8BitDo Ultimate 2 Controller. Source: 8BitDo.

There are a handful of other changes that I’ve made to my setup that you can find along with everything else I’m currently using on our Setups page, but there are two other items I wanted to shout out here. The first is the JSAUX 16” FlipGo Pro Dual Monitor, which I recently reviewed. It’s two 16” stacked matte screens joined by a hinge. It’s a wonderfully weird and incredibly useful way to get a lot of screen real estate in a relatively small package. The second item is 8BitDo’s new Ultimate 2 Wireless Controller that works with Windows and Android. I was a fan of the original version of this controller, but this update preserves the original’s build quality and adds new features like L4 and R4 buttons, TMR joysticks that use less energy than Hall Effect joysticks, and 2.4G via a USB-C dongle and Bluetooth connection options.

That’s it for now. In the coming months, I hope to redo parts of my smart home setup, so stay tuned for another update later this summer or in the fall.

Permalink

Federico’s Latest Automation Academy Lesson: Working with Web APIs in Shortcuts→

Federico's Todoist shortcuts.

Federico’s Todoist shortcuts.

Earlier today, Federico released a collection of four advanced Todoist shortcuts as part of his Automation Academy column, an exclusive perk of Club MacStories+ and Club Premier.

Federico started using Todoist again a few months ago specifically because it has a robust web API:

There were several reasons behind my decision to return to Todoist, but the most important one was its web API. I’m convinced that our modern AI era is marking a resurgence of web services, and I wanted to find something that could theoretically support some kind of connection to an AI assistant (such as ChatGPT or Gemini) down the road. At the same time, I also wanted something that could be easily _and_consistently automated. With more responsibilities coming into my life, it’s essential for me to automate all the boring parts of my job that can happen without my manual, time-consuming input. With the combination of a REST API and native Shortcuts actions, Todoist simply felt like the perfect candidate.

Federico is absolutely right. As I recently wrote for Club members, web apps have been on the rise for a long time, and the trend is only accelerating with the ascension of AI tools. As a result, knowing how to use web APIs with Shortcuts is only going to become more important over time. Sure, you can often manage to scrape information from a website directly, but you’re much better off with a thoughtfully designed REST API that can fetch data for you in a structured way.

Today’s Automation Academy installment is the perfect place to get started. Todoist’s API is rich and thorough, and Federico takes readers through each of his four shortcuts in a methodical but conversational way that concludes with key takeaways readers can use in other contexts.

I struggled with implementing web APIs in Shortcuts for a long time. Web APIs aren’t easy. But today’s Academy lesson is the perfect introduction that starts with the basics and builds up to more advanced techniques, helping readers do more with Todoist and apply their new skills to other web APIs they encounter.

Discounts are just one of the many Club MacStories perks.

Discounts are just one of the many Club MacStories perks.

Automation Academy is just one of many perks that Club MacStories Plus and Club Premier members enjoy including:

  • Weekly and monthly newsletters 
  • A sophisticated web app with search and filtering tools to navigate eight years of content
  • Customizable RSS feeds
  • Bonus columns
  • An early and ad-free version of our Internet culture and media podcast, MacStories Unwind
  • A vibrant Discord community of smart app and automation fans who trade a wealth of tips and discoveries every day
  • Live Discord audio events after Apple events and at other times of the year

On top of that, Club Premier members get AppStories+, an extended, ad-free version of our flagship podcast that we deliver early every week in high-bitrate audio.

Use the buttons below to learn more and sign up for Club MacStories+ or Club Premier.

Join Club MacStories+:

Join Club Premier:

Permalink

BANG!CASE: Push-Button iPhone Automation

I’ve been intrigued by the BANG!CASE ever since it was introduced by Bitmo Lab as a Kickstarter campaign about a year ago. The case includes a programmable button that can be used to automate actions using your iPhone’s accessibility features. However, because I don’t normally use a case with my iPhone, I never followed through on buying the BANG!CASE.

Fast forward to early January at CES when I visited the booth for JSAUX, an affiliate of Bitmo Lab. In addition to JSAUX’s portable displays and gaming accessories, the company was showing off the BANG!CASE and GAMEBABY. (More on that on NPC soon.)

It just so happens that since the holidays, I’ve continued my quest to refine how I collect and process information throughout my day. That’s led me to test a dozen or so apps, build new shortcuts, and explore other new setups. As a result, I was primed to give the BANG!CASE a try when Bitmo offered me a review unit at their booth, and I’ve been using it for a couple of weeks.

The case has a couple of minor drawbacks that I’ll get to, but by and large, it’s the most unique and useful case I’ve ever put on an iPhone. After enjoying my iPhone without a case for nearly two years, I’ve found that the utility of the BANG!CASE is significant enough that I’ve decided to keep using it, which I didn’t expect. So today, I thought I’d lay out why I like the BANG!CASE so much and how I’m using it.

Read more

Apple Frames 3.3 Adds Support for iPhone 16 and 16 Pro, M4 iPad Pro, and Apple Watch Series 10 (feat. An Unexpected Technical Detour)

Apple Frames 3.3 supports all the new devices released by Apple in 2024.

Apple Frames 3.3 supports all the new devices released by Apple in 2024.

Well, this certainly took longer than expected.

Today, I’m happy to finally release version 3.3 of Apple Frames, my shortcut to put screenshots inside physical frames of Apple devices. In this new version, which is a free update for everyone, you’ll find support for all the new devices Apple released in 2024:

  • 11” and 13” M4 iPad Pro
  • iPhone 16 and iPhone 16 Pro lineup
  • 42mm and 46mm Apple Watch Series 10

To get started with Apple Frames, simply head to the end of this post (or search for Apple Frames in the MacStories Shortcuts Archive), download the updated shortcut, and replace any older version you may have installed with it. The first time you run the shortcut, you’ll be asked to redownload the file assets necessary for Apple Frames, which is a one-time operation. Once that’s done, you can resume framing your screenshots like you’ve always done, either using the native Apple Frames menu or the advanced API that I introduced last year.

So what took this update so long? Well, if you want to know the backstory, keep on reading.

Read more

A Feature from 10 Years Ago Is Back – with a Twist – in My Favorite RSS Client

Unread's new custom shortcuts.

Unread’s new custom shortcuts.

When it comes to productivity apps, especially those that have to work within the constraints of iOS and iPadOS, it’s rare these days to stumble upon a new idea that has never been tried before. With the exception of objectively new technologies such as LLMs, or unless there’s a new framework that Apple is opening up to developers, it can often feel like most ideas have been attempted before and we’re simply retreading old ground.

Let me be clear: I don’t think there’s anything inherently wrong with that. I’ve been writing about iPhone and iPad apps for over a decade now, and I believe there are dozens of design patterns and features that have undeservedly fallen out of fashion. But such is life.

Today marks the return of a very MacStories-y feature in one of my longtime favorite apps, which – thanks to this new functionality – is gaining a permanent spot on my Home Screen. Namely, the RSS client Unread now lets you create custom article actions powered by the Shortcuts app.

Read more

POP Icon Keys: Logitech Brings Automation to a Budget-Friendly Keyboard

A couple of weeks ago, I wrote about and showed off Logitech’s MX Creative Console, a two-piece device made up of a keypad and dialpad, that takes the Elgato Stream Deck head-on. Well, today, Logitech is back with a slightly different approach in the form of its POP Icon Keys keyboard, which borrows some tricks from the Creative Console.

The $49.99 keyboard, shipping later this month, is solidly built and low-profile. It weighs 530g and has four big rubber pads on the bottom corners, giving it a sturdy, stable feel on my desk. The keys use scissor switches and feature aggressively rounded corners, and they’re quiet and have more throw and resistance than an Apple Magic Keyboard, but are easy to adapt to if you’re used to Apple’s keyboards. I particularly like the texture of the keys – which could be partially due to the fact that I’ve been using a worn-down Magic Keyboard – but the keys have a nice feel and don’t show fingerprints.

The POP Icon Keys comes in four color options.

The POP Icon Keys comes in four color options.

The body of the keyboard is made of a similar plastic, and the keys are surrounded by a strip of glossy, transparent plastic that adds a little flair to the entire package. The color options available for the POP Icon Keys are fun, too. I’ve been testing a black keyboard with neon yellow accents for about a week, and I like it a lot, but there are other color combinations available, including pink, orange and white, and a purpleish-blue color scheme. Also, the POP Icon Keys runs on two AAA batteries, which Logitech says can provide 36 months of operation thanks to the keyboard’s onboard power management.

If that’s where the story ended for the POP Icon Keys, I’d recommend it because it’s a very good keyboard for the price. What sets the POP Icon Keys apart, though, is that it goes a step further, adding automation features similar to those found on the more expensive MX Creative Console.

Logitech has designated the Home, End, Page Up, Page Down, F4-F12, and brightness keys as programmable via its Logi Options+ app. Among other things, you can use these keys to control system settings, execute keyboard shortcuts, and run multiple actions combined into macros. The keys’ original functionality remains available, too, if you hold down the function button. The POP Icon Keys also shares the MX Creative Console’s ability to set up app-specific profiles, meaning you can program keys to perform different tasks depending on which app is active.

For example, you could use the Home, End, Page Up, and Page Down buttons to open different sets of apps for work, a special project, or relaxing with a game. Or you could use the function keys to trigger keyboard shortcuts in your favorite apps or Shortcuts automations.

There are a couple of things I love about this functionality. First, the flexibility is fantastic, especially since you can access the programmable keys without taking your hands off the keyboard, which is an advantage over the MX Creative Console. Second, for just $50, the POP Icon Keys is a great entry point into the world of push-button automation. If it turns out that keyboard-driven automation isn’t your thing, you still have an excellent keyboard, but if it is, you can go a long way with the POP Icon Keys’ options before you graduate to the MX Creative Console or another similar device.

All in all, I like the POP Icon Keys a lot. It’s nicely built and a great way to get started with keyboard automation or supplement other automation workflows you already use. The device is available directly from Logitech and Amazon.

First Look: Logitech’s MX Creative Console Is Poised to Compete with Elgato’s Stream Deck Lineup

Source: Logitech.

Source: Logitech.

Today, Logitech revealed the MX Creative Console, the company’s first product that takes advantage technology from Loupedeck, a company it acquired in July 2023.

I’ve been a user of Loupedeck products since 2019. When I heard about the acquisition last summer, I was intrigued. Loupedeck positioned itself as a premium accessory for creatives. The company’s early products were dedicated keyboard-like accessories for apps like Adobe Lightroom Classic. With the Loupedeck Live and later, the Live S, Loupedeck’s focus expanded to encompass the needs of streamers and automation more generally.

Suddenly, Loupedeck was competing head-to-head with Elgato and its line of Stream Deck peripherals. I’ve always preferred Loupedeck’s more premium hardware to the Stream Deck, but that came at a higher cost, which I expect made it hard to compete.

The Logitech MX Creative Console slots nicely into my existing setup.

The Logitech MX Creative Console slots nicely into my existing setup.

Fast forward to today, and the first Logitech product featuring Loupedeck’s know-how has been announced: the MX Creative Console. It’s a new direction for the hardware, coupled with familiar software. I’ve had Logitech’s new device for a couple of weeks, and I like it a lot.

The MX Creative Console is first and foremost built for Adobe users. That’s clear from the three-month free trial to Creative Cloud that comes with the $199.99 device. Logitech has not only partnered with Adobe for the free trial, but it has worked with Adobe to create a series of plugins specifically for Adobe’s most popular apps, although plugins for other apps are available, too.

Read more

Apple Marks Global Accessibility Awareness Day with a Preview of OS Features Coming Later This Year

Source: Apple.

Source: Apple.

Thursday is Global Accessibility Awareness Day, and to mark the occasion, Apple has previewed several new accessibility features coming to its OSes later this year. Although this accessibility preview has become an annual affair, this year’s preview is more packed than most years, with a wide variety of features for navigating UIs, automating tasks, interacting with Siri and CarPlay, enabling live captions in visionOS, and more. Apple hasn’t announced when these features will debut, but if past years are any indication, most should be released in the fall as part of the annual OS release cycle.

Eye Tracking

Often, Apple’s work in one area lends itself to new accessibility features in another. With Eye Tracking in iOS and iPadOS, the connection to the company’s work on visionOS is clear. The feature will allow users to look at UI elements on the iPhone and iPad, and the front-facing camera – combined with a machine learning model – will follow their gaze, moving the selection as what they look at changes. No additional hardware is necessary.

Eye Tracking also works with Dwell, meaning that when a user pauses their gaze on an interface element, it will be clicked. The feature, which requires a one-time calibration setup process, will work with Apple’s apps, as well as third-party apps, on iPhones and iPads with an A12 Bionic chip or newer.

Vocal Shortcuts

Source: Apple.

Source: Apple.

Vocal Shortcuts provide a way to define custom utterances that launch shortcuts and other tasks. The phrases are defined on-device for maximum privacy using a process similar to Personal Voice. The feature is like triggering shortcuts with Siri, but it doesn’t require an assistant trigger word or phrase.

Read more