Rogue Amoeba announced the new feature, which they currently label as beta, on their blog post:
Transcribe can convert speech from an astonishing 57 languages into text, providing you with a written transcript of any spoken audio. It’s powered by OpenAI’s automatic speech recognition system Whisper, and features two powerful models for fast and accurate transcriptions.
As you would expect from Rogue Amoeba, transcription is processed entirely on your Mac so it’s privacy-friendly. You can transcribe audio from a mic input, VoIP apps like Zoom, or files through media playback apps.
In their blog post, they explain how this makes it possible to easily create timestamped transcriptions of podcasts. For best results, of course, Apple silicon is recommended but not required.
Check out Audio Hijack here.
