Mac · 2.2.3 (80) · 2026-10-05
Reduced ancillary network requests in the Mac edition from the website and replaced the computer name with a neutral device label in license requests. Clarified on-device Apple translation and privacy information.
Privacy
Diktator processes speech recognition locally on supported devices. Translation with Diktator's own speech model also stays on the device.
Diktator does not send your dictated audio, transcripts, documents, or personal writing to a cloud transcription service.
Reduced ancillary network requests in the Mac edition from the website and replaced the computer name with a neutral device label in license requests. Clarified on-device Apple translation and privacy information.
Audio and recognized text stay on your device unless you choose to send the result through another app or service.
Email is used only to restore a previous purchase with a one-time code.
Recording starts when you tap the button on Apple Watch. The recording is transferred to the paired iPhone and processed locally.
Diktator's own model and the Apple Translation API used by this app both translate on your device. Apple uses separately downloaded language models. Apple may collect API usage and performance data, including Diktator's app identifier and the language pair, without the original or translated text.
Microphone access is used only while you start and control recording. The recording capsule makes active capture visible.
Speech models and keyboard packs download when you request or approve them. Mac website releases before 2.2.3 (80) can also automatically download small Chinese and Japanese diagnostic packs. File requests expose your IP address and the requested file, not your dictation.
Online services handle purchases, licensing, updates, recovery and security records. Website license activation and refresh send the license key, a random installation identifier and a device label. Mac website releases before 2.2.3 (80) use the computer name, which can contain your name. Apple handles App Store purchases and entitlement checks under its policies. These records do not include dictation content.
When the Android app opens, it checks a small public version file on diktator.app. The request includes no installation identifier, audio or dictated text. If an update is available, the app offers a link to the APK; Android asks you to confirm installation. The site may see the usual network address and browser or app request metadata.
Existing iPhone and iPad releases may query Apple's App Store lookup when an app's return link is unknown. This sends that app's identifier and your device region to Apple, without dictated audio or text. This behavior depends on the installed version.
An iPhone or iPad diagnostic report may include device and system details, technical events, and names or identifiers of apps used for dictation. Review the report before sending it. It leaves the device only when you send it through your mail app. Reports from existing versions may also contain short excerpts of dictated text.
Temporary audio and diagnostic files are cleaned locally. Downloaded model files remain on your device until you remove them or use the available uninstall tools.
If you send dictated text through Mail, Messages, WhatsApp, a browser, or another app, that sending is controlled by that app or service, not by Diktator.
Edit results and choose corrections. Set separate modes for dictation and proofreading. Restore an existing website purchase by email and optionally sync your dictionary with private iCloud.
Edit your dictation before inserting or copying it. Compare the original and proofread text, with red deletions and green additions, and accept or reject each change separately. Direct can insert the edited draft when its original destination is available. In the Mac App Store edition, copy the edited draft and paste it into your app; ordinary dictation continues to use macOS Services.
Choose Faster, Balanced or Thorough independently for dictation and proofreading. Save names, preferred spellings and replacements in your personal dictionary; add entries from the editor’s context menu. Use an editable filler-word list with optional removal, off by default. Preferred spellings can provide optional recognition hints. They do not train Whisper or guarantee a spelling.
On-device storage is the default; private iCloud sync is optional. Save to merge your dictionary, filler words and their options with your private iCloud. Audio and transcripts stay on this device. Turning sync off keeps both copies. Dictionary sync requires Pro or an active trial. Sync works between Diktator versions that support this iCloud dictionary format.
Use the email associated with your Diktator purchase. Choose “Existing website purchase”, then “Send verification code”. Enter the emailed 8-digit code and choose “Verify purchase”. Email restoration is optional. License-key activation and existing Direct licenses remain available. For an App Store purchase, choose “Restore with Apple Account”. Email restoration is an optional way to verify an existing website purchase; it does not replace Apple purchase restoration. Direct and App Store installations each use one device slot. Your email is sent to Diktator to verify this purchase. Recordings and dictated text are not sent.
Updated onboarding, model descriptions and Help explain these features in all 13 interface languages.
Editing, individual corrections, separate recognition modes, the personal dictionary, filler removal and iCloud sync require Pro or an active trial. Free includes Small-model dictation and Copy with no expiry. Start the 21-day trial only when you choose.
These notes cover Direct Mac 2.3.1 and the prepared Mac App Store adaptation. Sync works only between Diktator versions supporting the same iCloud dictionary format. Whisper model files and the recognition engine are unchanged.