You Can Use AI to Transcribe Any Audio on Mac for Free
Getting accurate speech-to-text conversion has always been a headache. Ten years ago it would have cost you $199 to purchase the app and the result would still require a lot of editing to make it accurate. But this is where we start to see the tangible benefits of the AI revolution, where learning models can do things incredibly fast and without using a ton of resources. While OpenAI Whisper technology is amazingly good at speech-to-text, you need to be a developer or techie to get the most out of it. But now the developer has done the hard work of turning this technology into a delightful little Mac app: MacWhisper .
You can use MacWhisper to directly record audio to be transcribed into text (with timestamps). However, things get a lot more interesting when you import an audio file or video file – the app can quickly create an accurate transcription with a timestamp down to the millisecond.
After the text is generated, you can view and edit it. The Reader feature can show you all the text together in a document preview; then you can copy the transcript. Click the Share button and you can download the entire transcript as an SRT file (that’s where those timestamps really come in handy).
You can download the MacWhisper app for free through Gumroad – put a “0” (zero, not an “o”) in the payment box to get it for free. The app currently requires macOS Monterey or Ventura and Apple Silicon Mac is recommended for fast results. The free version will be enough for most people, but if you plan to use this in a professional setting, we suggest you upgrade to the Pro version for €9. This gives you access to a 3 GB big data model, which improves accuracy.