Originally published at: MacWhisper 15.2 - TidBITS
Jordi Bruin recently released version 15 of his AI-powered transcription app, MacWhisper, with several new features. You can now organize transcriptions into folders and subfolders; transcribe meetings as they happen with speaker identification (beta); send audio directly to MacWhisper from other apps using the macOS share menu; transcribe audio or video through Shortcuts in macOS 27 Golden Gate using your choice of model, language, and speaker identification; and find transcriptions by their content and open, retrieve, or share them through Siri and Shortcuts in Golden Gate. The update also refined the transcript editor layout, improved VoiceOver support and translations throughout the app, and raised the minimum system requirements to macOS 15 Sequoia.
Several maintenance updates followed, with a variety of improvements and bug fixes. The most recent release (version 15.2/15.2.1) adds new features for Pro license users, including support for Claude Opus 5.5, Gemini 3.7 Flash, and Gemini 3.8 Flash in AI services, recognition of up to 8 speakers per recording thanks to speaker detection powered by the Nvidia Nemotron Diarization model, and turning on live meeting transcription by default. Pro users also get more reliable Dictation AI prompts using Apple’s on-device model, staying in the language you dictated rather than switching to English. (Free or €64 for Pro license, free update, 139 MB, macOS 15+)