Whisper dictation on a Mac, typing into any app

By · Published · Updated

Whisper dictation on a Mac, with no Terminal, is what YapToText does: a free Mac app that runs Whisper Large v3 Turbo (Q5) on your Mac through whisper.cpp and types what you say into any app. The model ships inside the App Store download, there is no Python and no account, and your voice never leaves your Mac.

Download YapToText on the Mac App StoreThis app is completely free. You don't have to make an account. There are no subscriptions, no difficult downloads, and nothing is locked. Made for Apple silicon Macs. Source on GitHub.

This guide in other languages: العربية, Čeština, Dansk, Deutsch, Ελληνικά, Español, Suomi, Français, עברית, हिन्दी, Magyar, Bahasa Indonesia, Italiano, 日本語, 한국어, Norsk, Nederlands, Polski, Português, Română, Русский, Slovenčina, Svenska, ไทย, Türkçe, Українська, Tiếng Việt, 简体中文, 繁體中文

App Store poster headed Nothing leaves your Mac, over YapToText's AI Models page with both models marked Included.
Figure 1. Whisper Large v3 Turbo (Q5) is the dictation model under Your defaults, marked Included, because it ships inside the App Store download.
On this page: 12 sections
  1. Steps
  2. What Whisper is
  3. The Whisper model inside YapToText
  4. Whisper dictation apps for Mac, compared
  5. Run Whisper yourself, or use an app
  6. Pick another Whisper model
  7. Start dictating with Whisper
  8. The open-source repository
  9. If Whisper mishears you
  10. What it cannot do
  11. The short version
  12. Questions

Steps

  1. Install YapToText from the Mac App Store. Whisper Large v3 Turbo is inside.
  2. Allow the microphone, then turn on Accessibility for YapToText in System Settings.
  3. Click where you want the words in any app.
  4. Tap Right Command, talk, and tap it again.

What Whisper is

I built it because my hands make typing difficult and I needed dictation that works in every app. Below I cover what Whisper is, the model file, the other apps, and the code.

Whisper is OpenAI's speech recognition model, released with its code and weights under the MIT License, which is why a free app can ship it. Whisper Large v3 Turbo is the model YapToText runs. OpenAI describes turbo as an optimized version of large-v3 that offers faster transcription with a minimal degradation in accuracy, and its model card on Hugging Face says the decoding layers were cut from 32 to 4.

whisper.cpp is what makes it practical on a Mac: an MIT-licensed C and C++ implementation whose README calls Apple silicon a first-class citizen. Whisper is the model, whisper.cpp is the engine, and YapToText is the app that types the result where your cursor is.

The Whisper model inside YapToText

  • The file. ggml-large-v3-turbo-q5_0.bin, 574 MB, from the ggerganov/whisper.cpp repository on Hugging Face. Its SHA-256 matches the published file, so it is the standard 5-bit build, which I have not fine-tuned, retrained or modified.
  • Why the 5-bit build. I picked it for the memory it saves: it runs in about a third of the memory of the full model. It has been the default since 1.3.1. The page on Whisper Large v3 Turbo has more on the model itself.
  • The engine. A copy of whisper.cpp built into the app with Metal and Accelerate, with llama.cpp beside it for the cleanup model.
  • The licenses. The model is MIT, and the app is GPL-3.0.

What I did tune is everything around the model. Background noise is reduced and quiet speech is lifted before Whisper hears it, the half second before you press the key is kept so first words are not clipped, noisy audio gets deeper decoding, and hallucinated speaker labels and stage directions are removed from what comes back. Your dictionaries also prime Whisper with your own words. The model is stock. The pipeline around it is where the work went.

App Store poster headed It hears you through anything, listing the audio steps above the expanded recording panel.
Figure 2. The steps around the stock model, from background noise removal to pace correction. This pipeline is where the tuning went, not the model file.

Whisper dictation apps for Mac, compared

Several Mac apps run Whisper for live dictation. What separates them is the price, whether the code is public, and whether they also take a file.

Checked October 3 to 5, 2026, on each app's own pages. The open source roundup has more on the three whose code is public.

AppPriceOpen sourceSpeech modelsTypes into any appTranscribes files
YapToTextFree, no paid tierYes, GPL-3.0Whisper Large v3 Turbo (Q5) inside; ten more Whisper models, or your own fileYesYes, as plain text
superwhisperFree plan; Pro $8.49 a month, $84.99 a year, or $249.99 onceNot statedWhisper on the free plan; Parakeet, Cohere Transcribe and cloud models on ProYesOn Pro
MacWhisperFree version; Pro €64 onceNot statedWhisperIn the macwhisper.com version onlyYes, free, with subtitle export
VoiceInk7-day trial, then from $25 onceYes, GPL v3Parakeet, Whisper, Apple Speech and others; Parakeet V3 is the defaultYes, at the cursorYes
HandyFree; donations welcomeYes, MITParakeet V3, and Whisper Small, Medium, Turbo and LargeYes, pasted at the cursorNot stated
SpokenlyFree with local models; Pro $9.99 a monthNo; its site says its code is proprietaryWhisper and Parakeet free; cloud models through Pro or your own keysYes, in the build from its websiteYes, with subtitle export
HarkerFree for local transcription; Premium from $5.75 a monthNot statedEvery Whisper model tier, per its siteYes, auto-pasteNot stated

The superwhisper alternative page and the MacWhisper alternative page go through the two best-known ones, and Apple Dictation vs Whisper sets the model against what macOS already has.

Run Whisper yourself, or use an app

You can run Whisper on a Mac without any app, and it is a good way to learn how it works. Here is what each route asks of you.

Checked October 3, 2026, on each project's own README.

OpenAI's whisperwhisper.cppYapToText
Installpip install -U openai-whisper, with Python 3.8 to 3.11 and ffmpegClone the repository, download a model with its script, build with CMakeThe Mac App Store, with the model inside
How you use itA Terminal command or Python, on audio fileswhisper-cli on 16-bit WAV files; whisper-stream for a live microphone, with SDL2A key in any app, and audio files on the Utility page
Modelstiny to large, plus turboWhisper models in ggml format, including quantized onesLarge v3 Turbo (Q5) inside, ten more in the library, or your own ggml file
MacsNot statedIntel and ArmApple silicon, macOS 14 or later
Price and licenseFree, MITFree, MITFree, GPL-3.0

Running it yourself wins on control: any model, any flag, and Intel Macs too, since whisper.cpp lists Intel and Arm Macs as supported. YapToText wins on everything after the transcript: it types into the app you are in, cleans up with a local model if you want, keeps a History, and needs no setup. The only command to remember is Right Command. Run Whisper yourself to learn and tinker. Use an app when you just want the words.

To run it yourself, the local Whisper guide has the whisper.cpp commands and what each model costs in disk space and memory.

For recordings rather than live dictation, the audio file transcription page covers the Utility page, and the MacWhisper alternative page compares YapToText with MacWhisper. The comparison page sets superwhisper, Wispr Flow, MacWhisper and VoiceInk side by side.

Pick another Whisper model

The AI Models page has a Dictation Model Library with ten more Whisper models, each downloaded once from Hugging Face and run on your Mac. The app's own rule of thumb: bigger models hear better, and smaller ones are lighter on battery and memory. Under Your own models you can add any whisper.cpp GGML .bin file. The app recognizes it from the file itself and rejects anything else.

The local Whisper guide has the table of models with what each costs in disk space and memory, and the AI models guide and the energy guide cover choosing one and switching on battery.

The AI Models page in YapToText: Whisper Large v3 Turbo (Q5) and Phi-3.5 Mini Instruct marked Included, model library below.
Figure 3. The Dictation Model Library: every Whisper model shows its stars for accuracy and speed, its languages, its size and a download button.

Start dictating with Whisper

There is nothing to set up beyond two permissions. Install it, allow Microphone and Accessibility, click where the words go, and tap Right Command.

The App Store download is about 2.9 GB, because both models are inside, so it dictates with Wi-Fi off from the first launch. The Homebrew build has no models inside, so download a speech model before your first dictation. The install page has both routes, and the first dictation guide walks through each step with what you should see.

The open-source repository

The code is on GitHub at github.com/ryleighnewman/YapToText, under GPL-3.0. You can read exactly how audio reaches Whisper and what happens to the text afterward, open an issue, or build it yourself with Xcode 26 or later. Every line is public, so you never have to take my word for where your voice goes.

Terminal: Get the source and open it in Xcode.

git clone https://github.com/ryleighnewman/YapToText.git
open YapToText/YapToText.xcodeproj

What happens: Xcode opens the project. Choose the YapToText scheme and press Command R. The app builds sandboxed, the way it ships, but without the models, so download a speech model on the AI Models page before your first dictation.

One honest gap: the source on GitHub and the Homebrew build can trail the App Store build by a release. What's new lists each.

If Whisper mishears you

  1. Teach it your words. Add names and terms on the Dictionaries page. They prime Whisper, not just fix its output. The dictionaries guide shows how.
  2. Set your language. The Language picker on the AI Models page starts on your Mac's system language. The languages page lists all 29.
  3. Fix the microphone. Bluetooth microphones are phone quality, so pick the Mac's own microphone in the menu bar panel's Input picker. The app also warns when the room or the fans are too loud for it to hear you.
  4. Try a bigger model. Whisper Large v3, or the Q8 build of Turbo, means a bigger download and slower runs, and the star ratings on the AI Models page show the trade.
YapToText's Dictionaries page: suggested fixes such as thursday to Thursday, and the General dictionary with iPhone and Wi-Fi.
Figure 4. The Dictionaries page. Entries such as iPhone and Wi-Fi fix how words are written, and they also prime Whisper to listen for them.

What it cannot do

  • Intel Macs. YapToText needs Apple silicon and macOS 14 or later, and nothing is claimed for Intel Macs.
  • Subtitles and speakers. File transcription gives plain text: no timestamps, no subtitles and no speaker labels.
  • Translation. It types what you said in the language you said it, and OpenAI notes the turbo model is not trained for translation tasks.
  • Every language equally. OpenAI says Whisper's performance varies widely depending on the language.

The offline dictation page covers what works with Wi-Fi off.

The short version

  • Whisper. It is OpenAI's MIT-licensed speech model. YapToText runs Large v3 Turbo (Q5), the stock 574 MB whisper.cpp file.
  • Local. It runs on your Mac through whisper.cpp with Metal, with no Terminal and no account.
  • Everywhere. The words land at your cursor in any app, for free.

It is Whisper, on your Mac, typing wherever you are. If Whisper mishears something it should not, open an issue on GitHub. Every one gets read.

Download YapToText on the Mac App StoreThis app is completely free. You don't have to make an account. There are no subscriptions, no difficult downloads, and nothing is locked. Made for Apple silicon Macs. Source on GitHub.

About the author. Ryleigh Newman is a developer whose hands make typing difficult and who dictates every day with YapToText, the app this site describes. Facts about other apps come from their own sites, with the date they were read. More about the project.

Sources

Questions

Is there a Whisper app for Mac?

Yes. YapToText is a free Mac app that runs Whisper Large v3 Turbo on your Mac and types into any app. Others exist too, and the comparison page on this site sets several side by side.

Can you run Whisper locally on a Mac?

Yes. whisper.cpp runs Whisper on a Mac and is optimized for Apple silicon, and OpenAI's own package runs from Python. YapToText packages whisper.cpp and the model into an App Store app, so it runs locally with no setup.

Is Whisper free?

Yes. OpenAI released Whisper's code and model weights under the MIT License. YapToText, which runs it, is free too, with no paid tier.

Does Whisper work offline on a Mac?

Yes, when it runs locally. YapToText's App Store build ships the model, so it transcribes with no internet connection. The only network use is a model download you start yourself.

Which Whisper model is best for a Mac?

Large v3 Turbo (Q5) is the one YapToText ships, at 574 MB, because it runs in about a third of the memory of the full model. Bigger models hear better and smaller ones are lighter, so the library lets you choose.

Does Whisper work on Intel Macs?

Yes, if you run whisper.cpp yourself: its README lists Intel and Arm Macs as supported. YapToText needs Apple silicon and macOS 14 or later, and nothing is claimed for Intel Macs.

Does Whisper run on an M4 Mac?

Yes. YapToText runs Whisper on any Apple silicon Mac with macOS 14 or later, and Apple silicon covers the M-series chips, M4 included. It needs no Python and no Terminal.

How do I install Whisper on a Mac?

The simplest way is an app that ships it. YapToText from the Mac App Store includes Whisper Large v3 Turbo (Q5), so there is no Python, Terminal or separate model download. The Homebrew build installs the app in one command, and you download the model from its AI Models page.