Software for transcribing discussions, video calls and interviews has progressed significantly in recent years. An innovation is that this is also possible locally on the computer – thanks to Openai thanks to the source -open models. The most popular software on the Mac is called MacWhisper And comes from the Dutch developer Jordi Bruin. He has now fulfilled a long-awaited feature request to its users: it is finally possible to automatically distinguish between speakers. The feature has been available since version 12.0.1 that has been published this month.
Who is talking right now?
“If you now transcribe an interview, a meeting or a conversation, MacWhisper automatically recognizes different speakers, groups their statements and labels them – their transcripts become clearer and are easier to navigate,” writes Bruin in the package insert. The function had been one of the most popular features within the user. Nothing changes in the fact that transcribing continues to run on your own Mac, i.e. not (for example for training).
“The entire processing happens privately on your Mac, nothing is sent to a server and it also works offline.” This was implemented in cooperation with Argmax and its models whisperkit pro and speaker kit. Accordingly, you have to select them. It is also possible to select a language in advance or to be recognized automatically. In practice, this works particularly well if the conversation only uses one language. If there are several, sometimes word salad comes out.
Server models also available
The speaker recognition is part of MacWhisper Pro, so it cannot be used free of charge – not cheap 59 euros are due for the activation. There is also a text and grammatical correction via server models, batch transcribution and support for distilled models. The Pro version can also transcribe YouTube videos and supports various other cloud models from Openai, Anthropic, X.AI and Via Ollama. A feature overview can be found here. Bruin gives students, non-profits and journalists 30 percent discount if they contact him by email. Finally, support for Elevenlabs Skribe and Deepgram Nova was also added.
MacWhisper masters over 100 languages. The app can also directly capture audio from various Mac apps, so that you don't have to save anything cumbersome. Hardware requirement is a Mac with M-chip, i.e. Apple Silicon. Updates are integrated in the price, there is no subscription.
Discover more from Apple News
Subscribe to get the latest posts sent to your email.