From private local dictation to multilingual translation.
The public Direct Mac line began in August 2026. Every release below is preserved in chronological order; the newest signed build remains the recommended download.
Detailed build notes are currently available in English.
Current release
Diktator 2.2.3 · Build 80
The model files, translation options, and licensing are unchanged. Apple silicon Macs running macOS 26 or later remain supported, including macOS 27.
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.
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.
Diktator 2.2.2 simplifies recognition prompts and punctuation handling, makes recording controls independent of segmentation, and keeps the transcript window useful in one-shot mode.
Updated for macOS 27, with more reliable text insertion and a recovery window that keeps your result available.
Diktator checks the inserted text and cursor before replacing text. If delivery cannot be confirmed, it avoids a blind retry and keeps the full result available to copy. Speech models, translation options, and existing licenses are unchanged.
Build 76 moves the Direct edition onto the shared Diktator processing foundation while preserving its website licensing and delivery features.
Translate speech from the broad supported source-language catalog into a selected target language. Availability and quality depend on the language pair, model, and translation method. Improved text insertion and helper setup, clearer license status and errors, and automatic model selection when switching between the free and advanced versions.
Translate speech from the broad supported source-language catalog into a selected target language. Availability and quality depend on the language pair, model, and translation method. Improved text insertion and helper setup, clearer license status and errors, and automatic model selection when switching between the free and advanced versions.
Selectable local translation, Arabic and Turkish support, improved Chinese and Japanese processing, the complete dictation-language catalog, and a more polished Direct Mac experience.
Introduced independent language detection and language-specific processing for short segments, improving mixed-language dictation without changing the single-language workflow.
Added Arabic and Turkish interface localization, portable language post-processing, improved Chinese and Japanese plausibility checks, more model mirrors, and a nonblocking About window.
Launched local short and segmented dictation, downloadable speech models, live transcripts, final proofreading, customizable shortcuts, 11 prepared languages, Free and Trial modes, Pro licensing, and signed updates.