Dictation
Dictate anywhere on your system with a global hotkey, have the finished text inserted where you were typing, and configure every part of it
Dictation turns speech into finished text in whatever application you happen to be in. You press the hotkey, speak, and the text lands in the field you were typing in: an email, a ticket, a chat message. The DeutschlandGPT window never has to come to the foreground.
Dictation exists only in the desktop app, because it needs native microphone capture and a system-wide hotkey. It also has to be enabled for your account. If you do not see a Dictation entry in the settings rail, ask your administrator.
Where to find it
| What | Where |
|---|---|
| The hotkey and how it fires | Settings, Shortcuts, group "System-wide" |
| Everything else | Settings, Dictation |
| Your past dictations | Settings, Dictation, at the bottom under "History" |
Open settings with Cmd/Ctrl+,. The hotkey deliberately lives with all the other shortcuts rather than in the dictation panel, because it describes a key press and not what happens to the text.
On Windows and macOS the dictation hotkey can also be made of modifier keys alone, for example Ctrl+Win or Ctrl+Cmd. It needs the Windows or Command key plus at least one more modifier. On macOS such a hotkey only works once DeutschlandGPT has the Accessibility permission, and the shortcut settings offer a button to grant it.
Dictating
Put the cursor where the text should go, then press the dictation hotkey. The default is
Cmd+Shift+L on macOS and Ctrl+Shift+L on Windows. A small overlay appears on the screen your
mouse pointer is on and shows that it is listening.
Speak. How you stop depends on the trigger setting: press the hotkey again in toggle mode,
or release the keys in push to talk mode. Esc cancels.
The recording is transcribed, refined according to the selected mode, and inserted at the cursor.
If the text cannot be inserted automatically, most often because the Accessibility permission is missing on macOS, it is placed on the clipboard instead and the overlay says so. Dictation never ends with no text at all.
Permissions
The two rows at the top of the dictation settings are not preferences, they are preconditions. Both are granted in your system settings, and the panel links straight to the right pane.
| Permission | Needed for |
|---|---|
| Microphone | Recording at all. Without it the app records silence |
| Accessibility (macOS) | Inserting the text automatically. Without it the dictation stays on the clipboard |
Each row shows its state: granted, not granted, or not requested yet. Allow access fires the one system prompt while the DeutschlandGPT window is in front, which is much better than having it appear mid-dictation over the app you were dictating into.
macOS often only picks up a newly granted permission after the app restarts. The panel offers Restart now for exactly that. If dictation still does not work after granting, restart before looking for anything else.
Two platform notes. On Windows there is no state to read: the system asks on your first dictation, and a blocked microphone surfaces as a real recording error rather than as a status. So Windows gets the settings shortcut and the explanation, never a claim about a state the app cannot verify. If the microphone is blocked by device management, the row says so and points you at your IT team, because no click in the app can lift that.
Trigger: push to talk or toggle
In Settings, Shortcuts, right under the system-wide hotkeys.
| Mode | Behaviour |
|---|---|
| Push to talk | Records only while you hold the keys, and stops the moment you let go |
| Toggle | One press starts, the next press stops |
Toggle is the default. Push to talk suits short dictations and never leaves a recording running by accident. Toggle suits long ones, where holding a chord for two minutes is uncomfortable.
Insert automatically
On, the result goes straight into the app you were last using. Off, it only goes to the clipboard and you paste it yourself.
Turn it off if you dictate into applications that react badly to simulated keystrokes, or if you would rather look at the text before it lands in a customer-facing email.
Keep in clipboard
Only appears while Insert automatically is on, because without automatic insertion the clipboard is the delivery channel and the text always stays there.
On, the dictation stays in the clipboard after being inserted, so you can paste it again. Off, your previous clipboard contents are restored, which matters if you were in the middle of copying something else.
How long the result stays visible
The transcribed text stays in the dictation overlay for the chosen duration and then disappears on its own: 3, 5, 10 or 20 seconds, or stay open. With don't show the overlay closes as soon as the text is inserted. Error messages stay up regardless, so you can read them.
Fixed steps rather than a free field, because a free millisecond value invites values that are either unreadably short or leave the overlay parked on top of another app. Pick stay open if you want to read and copy the text yourself every time.
Close right after pasting
Only shown while Insert automatically is on. When it is on, the overlay closes about one and a half seconds after the text was pasted, whatever duration you picked above. If the text could only be copied, or something went wrong, the overlay stays up for the chosen duration so you can still read the message.
Sounds
Off by default. When on, a short, quiet rising tone plays as soon as the microphone is actually recording, and a falling tone when the recording ends. Wait for the first tone before you speak, then nothing at the start gets lost.
Microphone
Which microphone dictation records from. System default follows whatever is set as the default input device in your operating system. Pick a specific microphone if the default is often the wrong one, for example a laptop microphone while a headset is connected.
If the chosen microphone is not connected when you start dictating, the app records from the system default instead, and the picker marks the device as not connected. The list only shows microphones the system currently reports, so reopen the settings after plugging a new one in.
Dictation language
Tells the transcription which language to expect. App language, the default, uses the language of the interface. Detect automatically lets the transcription guess, and below those two you can pick a fixed language.
A fixed language matters most on short recordings, where automatic detection is at its least reliable. Choose Detect automatically if you dictate in several languages.
Mode
A mode decides what happens to the raw transcript before it is inserted.
| Mode | Result |
|---|---|
| Raw text | The transcript verbatim, no model call. The fastest path |
| Light cleanup | Only punctuation, capitalisation and misheard proper nouns are fixed. Nothing is reworded or reordered, and filler words stay. The default |
| Cleaned up | Filler words, repetitions, self-corrections and stutters removed, punctuation and capitalisation fixed. Wording, tone and content untouched |
| Message | A short, casual chat message. No salutation, no sign-off, no bullet lists unless you dictated one |
| A polite, clearly structured email in short paragraphs. No salutation or sign-off is invented if you did not dictate one, and no content is added | |
| Note | Condensed into short bullet points, keeping every fact, name, number and date |
| AI prompt | A precise, complete instruction to an AI model. The intent stays exactly as dictated, no new requirements, and the instruction is not answered |
| Custom mode | Your own instruction |
Every mode keeps the language you spoke, so dictating in English gives English back.
Raw text is also the fallback: if refinement fails for any reason, you get the plain transcript rather than nothing.
Custom instruction
Only appears while Custom mode is selected. Whatever you write here is the instruction passed to the model, for example "rewrite as a factual email in English, without greeting or sign-off".
Left empty, the custom mode behaves exactly like Raw text instead of sending an empty instruction to the model.
Vocabulary
Proper nouns and product names are what speech recognition reliably gets wrong. Enter them here, one term per line, and obviously mis-transcribed variants of those words are corrected in the finished transcript without the rest of the text being touched.
If a word keeps coming back as something entirely different, write a rule on its own line: wrong => right, for example Deutschland Jipiti => DeutschlandGPT.
One per line rather than comma-separated, because that is the only format that survives terms containing commas or spaces.
The vocabulary applies in every mode, Raw text included. Where the speech provider supports it, it is also passed to the recognition as a hint. A short built-in list (DeutschlandGPT, ChatGPT, OpenAI, Anthropic, Claude, Titanom) always applies, and your own entry wins if it covers the same word.
History
Your recent dictations, newest first, with their recordings. Per entry you can:
- Copy the text to the clipboard again.
- Reprocess it with the currently selected mode, which replaces the listed entry. This needs the raw transcript, so an entry without one reports that instead of silently doing nothing.
- Play or download the recording.
- Delete it, on the server and locally.
The history exists for one specific failure: the paste can land in the wrong window, and by the time you notice, the clipboard already holds the next dictation.
Entries are stored on the server, so they survive a reinstall and are visible on your other machines, and they are governed by the retention periods under Data storage. Recent local entries are merged in on top, which covers being offline and the seconds between a dictation finishing and its upload landing.
Clear history deletes every listed dictation and its recording permanently, including on your other devices.
An interrupted dictation, where the app crashed or was quit mid-recording, is recovered and processed at the next start and marked as recovered in the list.