This Free Mac App Combines Several AI-Powered Transcription Tools
If you’ve ever wanted your Mac’s text-to-speech feature to work better, Spokenly might be the solution for you. It’s a free Mac app that lets you use state-of-the-art AI transcription right on your Mac for free — just launch the app with a keyboard shortcut, say what you want to type, and watch it appear on the screen.
Whatever you think of modern AI, it’s hard to deny that it’s good at turning spoken word into text. Whether it’s transcribing in real time or creating a transcript for a video or audio file, Whisper’s open-source engine is accurate and fast. Spokenly is a free app that brings this technology to your Mac.
Install the app, which is currently free in the Mac App Store , and it will launch in the menu bar. Transcription is easy: just press and hold the right Command button, and you’ll see a pop-up window like the one above. Say what you want to type, and let go when you’re done — the text will appear in the currently active text field.
Honestly, you could just install the app, use it that way, and never think about the settings — it mostly just works. However, if you want to dig deeper, open the settings by clicking the menu bar icon and clicking General settings . You can decide whether the app appears in the menu bar, the dock, or both. You can decide which microphone the app uses first if you use more than one. And you can decide whether to copy transcribed text to the clipboard by default.
If you like experimenting with AI, you should check out the Voice Models tab. Here, you can choose which AI model you want to use. By default, the app uses the online version of “Whisper Large v3,” which is the only model that supports displaying your transcription in a pop-up window during a conversation. However, there are other models you can use, including GTP-4o via Spokenly.
If you don’t want to use the online service, there is support for downloading and running various Whisper models locally. You’ll have to find a balance between hard drive space, performance, and accuracy—I recommend trying a few models until you find one that works for you. There’s also support for using Deepgram, Fireworks, and OpenAI API keys if you’re already paying for one of those services.
If you don’t know what all this means, don’t worry: the default model works very well. And there’s a lot more to explore with this app. The Transcribe File tab of the settings window lets you add any video or audio file and get a transcript with or without timestamps. There’s even support for creating subtitle files for your videos.
And there are a few power-user tools you can customize. The Shortcuts tab lets you choose a few word combinations that trigger an action instead of transcribing. Just pick a trigger phrase and what you want that phrase to do — open a URL, launch an app, or run one of your Apple Shortcuts. For example, you could set “Open Lifehacker” as a trigger phrase and our home page as a URL. Do that, and the Lifehacker website will open every time you say the words “Open Lifehacker,” improving your life (supposedly).
Another feature, AI Prompts , lets you set a prompt that will change your text after you dictate it. Simply select a specific key combination and type a prompt for the text. For example, you could write a prompt that says “translate this text into Spanish” — now you can use a custom key combination to transcribe something before using AI to translate it. Any prompt you can come up with will do.
All of these features reward skill, and this is the kind of app I like. And the app is completely free at the time of writing, offering features that allow you to use it privately. Give it a try if you want to get more out of your transcription software.