Where your voice goes when you dictate with DeepType

A dictation app hears everything you say to it. Before you give it your voice, you should know where the audio and the text end up. This post follows one dictation from the shortcut to the text landing in another app, and names every point where something can leave your Mac.

The default stays on your Mac

A fresh install uses local speech recognition. You pick a model in Models: Apple on device recognition through a macOS language pack, NVIDIA Parakeet, or Whisper. Parakeet and Whisper run on your Mac once you install them.

DeepType has no account and no cloud transcription fallback. If a local model is missing or fails, the app says so. It does not quietly send the recording somewhere else for an answer.

Downloads happen only when you ask

Parakeet and Whisper download when you press install in Models. Loading a model you already installed never reaches the network, and starting a dictation never downloads anything. If a model is missing, DeepType asks you to install it first.

Apple on device recognition is managed by macOS. It needs a supported language and the matching system assets, and it never falls back to Apple's server recognition.

Cleanup you control

After recognition, Auto cleanup can tidy the text. You choose the level:

• None keeps every word you said.
• Light, the default, removes English filler words, repeats and false starts with rules that run on your Mac.
• Medium also edits English for clarity with the notes model you chose in Models.

Medium is where your notes model matters. Apple Intelligence and Ollama run on your Mac; DeepType talks to Ollama at 127.0.0.1, the local address of your own machine. Claude Code, Codex and API connections send the dictation to that provider, and only if you pick one. History keeps the raw transcript next to the cleaned one, so Use Original can always bring back what you actually said.

API connections are opt in

You can add a speech API connection for Sarvam AI, Smallest AI or any OpenAI compatible endpoint. When you select one, your recordings go to that service. DeepType never uses a connection as a fallback for a local model, so audio leaves your Mac only after you choose that connection.

API keys live in your login Keychain, not in the app's settings file. Each key is tied to the exact endpoint it was saved for, so editing a connection's URL cannot forward an old key to a new server. Endpoints must use HTTPS. Plain HTTP is allowed only for addresses on your own Mac, such as localhost.

What stays on disk

Settings, vocabulary and dictation history live in your Mac's Application Support folder. History is on by default and stores both the raw and the corrected text. You can turn it off for future dictations. The app does not encrypt this local data, so treat it like any other document on your Mac.

Temporary recordings are deleted when a dictation finishes or is cancelled. A force quit or a crash can interrupt that cleanup. Meeting recordings are a separate feature and keep their own files.

Typing into other apps

DeepType needs Accessibility access to type into the app you were using. Automatic insertion can use the clipboard. Once the text lands, the destination app handles it under its own privacy practices.

Updates

DeepType checks for updates through its release feed. That check uses the network. Your recordings and transcripts are never part of it.

Check it yourself

Every claim in this post is covered in short form on the privacy page.