superwhisper context awareness: what it captures, when, and why it sometimes captures nothing
By Ryleigh Newman · Published
Context awareness lets a superwhisper mode hand its AI model more than your words: the text you had selected, text from the window you are in, and what is on your clipboard. It makes replies and edits fit what you are looking at. Each of the three is captured at a different moment, and most problems come from that timing, so this page goes through it.
I built YapToText, a different dictation app for the Mac, so read what I say about superwhisper with that in mind. Every fact about superwhisper here comes from its own docs, read on October 10, 2026.
This 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
The three kinds of context
From superwhisper's docs, Context awareness, read October 10, 2026.
| Context | What it is | When it is captured |
|---|---|---|
| Selected text | Text highlighted in your active window | The moment you start recording |
| Application | Text from active input fields, names and the title of the active window | After transcription, before the AI step |
| Clipboard | What you copied | Within three seconds before recording starts, or during dictation. The last copy wins |
Which modes use it
- Super Mode. The only built-in mode with all three on by default.
- Other built-in modes. Most have context off.
- Custom modes. Any combination, with three checkboxes in the Context row of the editor. The docs say those checkboxes need a Pro license.
superwhisper's own advice is to turn on only what a mode needs, because extra context sends more information to the AI and can make the result worse. The Prompt field in History shows exactly what context was sent.
When it does not work
From superwhisper's docs, Context awareness, read October 10, 2026.
| Problem | What to check |
|---|---|
| Selected text is ignored | Keep focus on the app with the selection when you start recording, and use a mode with selected text on |
| Application context is wrong or empty | Do not switch windows before processing ends, and check Accessibility in System Settings, Privacy and Security |
| Clipboard is ignored | Copy within three seconds before you start, or while dictating |
| Started by a deep link from a shell | Open the link in the background, with the -g flag, so focus stays on your app |
Where the context goes
Context goes to the language model of the mode, together with your transcript. superwhisper lets each mode use a local language model or a cloud one, so whether that text leaves your Mac depends on the model the mode uses. The superwhisper privacy page covers that choice, and the modes page covers Super Mode and custom modes.
Context in YapToText
superwhisper from its docs, read October 10, 2026. YapToText from its own settings.
| superwhisper | YapToText | |
|---|---|---|
| Selected text | Yes | Yes |
| Clipboard | Yes, copied within 3 seconds before or during | Yes |
| The app or window | Text and title from the active window | The app you are dictating into |
| Price | Pro license for custom modes | Free |
| Where the AI runs | The mode's model, local or cloud | On the Mac |
Each YapToText mode has its own switches for context from the app, your selection and your clipboard, and its cleanup model runs on your Mac. VoiceInk's version of the same feature reads screen text too, if you want to compare all three.
This 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.
The short version
- Selected text. Captured when you start, so keep focus on that app.
- Application. Captured after transcription, so do not switch windows.
- Clipboard. Copy within three seconds before, or during.
- Modes. On in Super Mode. Custom modes need Pro for it.
- Check it. History's Prompt field shows what was sent.
If superwhisper changes how context works, open an issue on GitHub and I will update this page. Every one gets read.
This 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.
Related
Sources
- https://superwhisper.com/docs/common-issues/context (checked 2026-10-10)
- https://superwhisper.com/docs/modes/custom (checked 2026-10-10)
- https://github.com/ryleighnewman/YapToText (checked 2026-10-10)
- https://apps.apple.com/us/app/yaptotext/id6786382289 (checked 2026-10-10)
Questions
What is context awareness in superwhisper?
A mode can give its AI the text you had selected, text from the active window, and your clipboard, so the output fits what you are working on.
Why is superwhisper ignoring my selected text?
It is captured the moment you start recording, so the app with the selection must have focus then, and the mode must have selected text context on.
Which superwhisper mode uses context?
Super Mode has all three kinds on by default. Custom modes can use any of them, which the docs say needs a Pro license.
How do I see what context superwhisper sent?
Open the dictation in History. The Prompt field shows what was sent to the AI.
Does superwhisper send my screen to the cloud?
Context goes to the mode's language model. With a local model it stays on your Mac, with a cloud model it is sent to that provider.