Diktator 2.3.1 · Build 88

Diktator 2.3.1 · Build 88

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 a result

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.

Recognition mode · Personal dictionary

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.

Dictionary storage

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.

Restore access

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.

Help

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.

Fewer background requests

• Removed automatic downloads of Chinese and Japanese diagnostic packs.

A neutral device label

• License requests use a neutral device label instead of the computer name.

Clearer translation privacy

• Clarified privacy information for on-device Apple translation, separate language downloads and possible Apple API usage metrics without translation text.

macOS

• macOS 26 / macOS 27 · Apple silicon

Recognition and punctuation

• Removed the general English hint about keyboard names that was sent with every dictation. Recognition no longer receives that unrelated English context.
• Diktator no longer replaces spoken punctuation names with symbols in its own text processing. The speech model continues to add punctuation naturally.

Transcript window and recording controls · Pro

• When enabled, the transcript window now shows recording and processing status, then the final text, even without segmentation. It does not add another recognition pass.
• When enabled, the noise threshold and stop-on-silence work with or without segmentation. You can choose how to record without losing these controls.

Proofreading

• Optional final proofreading applies to segmented recordings.
• Without segmentation, the recording is recognized once after Stop, without a redundant proofreading pass.

Interface

• Settings panels keep their width and alignment when options change or the window is resized. The dictation instructions in Settings and first-run setup are more compact.
• The model files, translation options, and licensing are unchanged. Apple silicon Macs running macOS 26 or later remain supported, including macOS 27. The transcript window, advanced audio tuning, and final proofreading remain Pro features.

macOS 27 compatibility

• Built with the macOS 27 SDK. Requirements are unchanged: an Apple silicon Mac running macOS 26 or later.

Text insertion and cursor checks

• Accessibility delivery now checks inserted text and cursor position more carefully.
• When the outcome is uncertain, the app does not blindly try another automatic insertion path, helping avoid duplicate text or replacement of an unrelated passage.
• In Codex, an available keyboard helper is tried before Accessibility delivery.

Retained results

• If safe insertion or replacement cannot be confirmed, the complete result stays in its window with Copy All available.
• Speech models, recognition and translation processing, Free and Pro tiers, and licensing are unchanged in this build.

Known issue

• Command-V may not paste a license key in the activation dialog. Right-click the field and choose Paste from the context menu.

Shared processing foundation

• The website edition now uses the shared Diktator processing foundation while preserving Direct licensing, configurable shortcuts, Accessibility delivery, and Input Method support.

Recognition and translation

• Short recordings are evaluated from saved audio instead of relying only on a momentary live level.
• Translation requests are isolated so a late result cannot replace newer output.
• Retained source text can still be sent to Apple Translation after a proofreading failure.

Delivery and models

• Text delivery and final clipboard behavior follow the selected automatic copy and replacement settings more consistently.
• Model fallback no longer overwrites the saved larger-model choice.

Known issue

• Command-V may not paste a license key in the activation dialog. Right-click the field and choose Paste from the context menu.

Version number aligned at 2.2

• Version 2.2 (75) retains the features of stable website Build 70. The version number now matches the Mac App Store edition.

Dictation and translation

• Choose the output language separately from the source dictation language. Select your preferred supported target from the translation catalog.
• The dictation catalog includes 100 languages and is not limited to the 13 interface languages.
• Diktator’s local model and Apple Translation have different capabilities. A language appearing in the catalog does not guarantee support or equal quality for every language pair.

Insertion and setup

• Improved input-source preparation for ordinary dictation, restoration of the previous input source and delayed focus handback.
• Switching the input source off no longer removes its installed component. An already configured and approved component is reused without reinstallation.
• Successful direct insertion preserves the clipboard. When insertion is unavailable, you can copy or drag the result.
• Updated onboarding, the grouping of language and translation settings, and processing color cues. Removed the legacy macOS Service from the direct-download edition.

Free and advanced versions

• The free version uses Small and displays the model actually in use. If Small is missing, the app offers to download it.
• Your advanced-version model choice is saved and restored after activation. Unavailable advanced settings remain visible but disabled.

Licensing

• The Mac limit comes from server-reported metadata. An unknown limit is no longer assumed to be three.
• Inactive or invalid key errors are distinguished from network and service problems, with explanations in all 13 interface languages.

Known limitation

• Command-V still does not paste a key into the activation dialog. Right-click the field and choose Paste from the context menu. A fix is deferred to the next version.

Dictation and translation

• Choose the output language separately from the source dictation language. Select your preferred supported target from the translation catalog.
• The dictation catalog includes 100 languages and is not limited to the 13 interface languages.
• Diktator’s local model and Apple Translation have different capabilities. A language appearing in the catalog does not guarantee support or equal quality for every language pair.

Insertion and setup

• Improved input-source preparation for ordinary dictation, restoration of the previous input source and delayed focus handback.
• Switching the input source off no longer removes its installed component. An already configured and approved component is reused without reinstallation.
• Successful direct insertion preserves the clipboard. When insertion is unavailable, you can copy or drag the result.
• Updated onboarding, the grouping of language and translation settings, and processing color cues. Removed the legacy macOS Service from the direct-download edition.

Free and advanced versions

• The free version uses Small and displays the model actually in use. If Small is missing, the app offers to download it.
• Your advanced-version model choice is saved and restored after activation. Unavailable advanced settings remain visible but disabled.

Licensing

• The Mac limit comes from server-reported metadata. An unknown limit is no longer assumed to be three.
• Inactive or invalid key errors are distinguished from network and service problems, with explanations in all 13 interface languages.

Known limitation

• Command-V still does not paste a key into the activation dialog. Right-click the field and choose Paste from the context menu. A fix is deferred to the next version.

Translation

• Added target-language selection from the full catalog.
• Added translation with Diktator’s local model; results depend on the model and language pair.
• Added a second method: Apple Translation. Apple Translation in Diktator translates on the device with separately downloaded Apple language models.
• Regular dictation and translation have separate shortcuts and states.

Languages and text

• The full 100-language catalog is available for dictation and translation targets.
• Added Arabic and Turkish interface translations and dedicated post-processing profiles.
• Improved Chinese and Japanese text cleanup and plausibility checks.
• Short mixed-language segments are recognized independently.
• Mixed-script protection preserves valid passages in different languages.
• Improved final proofreading and paragraph preservation.

Setup and text insertion

• Initial setup walks through languages, models, microphone access, text-insertion methods and shortcuts.
• Accessibility access remains optional for direct insertion.
• The Diktator input source provides another automatic insertion method; copying and dragging remain safe manual options.