Audio Hijack 4.3 adds speech-to-text transcription powered by OpenAI's Whisper

Audio Hijack, the professional-grade recording software for macOS, has launched its version 4.3, introducing a new feature called Transcribe. This new block has the capability to convert spoken audio into written text transcripts. It can process speech from 57 different languages, making it a versatile tool for users operating in multiple linguistic environments.

Transcribe is powered by OpenAI’s automatic speech recognition system, Whisper. It utilizes two robust models to ensure speedy and accurate transcription of spoken content.

A significant advantage of Transcribe is its cost-effectiveness. It operates within Audio Hijack without any additional charges, allowing users to generate unlimited transcriptions without incurring ongoing costs.

Notably, Transcribe prioritizes user privacy. All transcription processes take place directly on the user's Mac, ensuring that data is not transmitted to the cloud or shared with third parties. This feature ensures that users can transcribe their audio content without compromising on privacy and data security.