By Dan Moren
November 2, 2023 10:57 AM PT
Audio Hijack adds automatic transcription
Rogue Amoeba’s Audio Hijack has long been an indispensable tool for Mac podcasters1: this Swiss Army knife of audio utilities lets you not just grab audio from your Mac’s mics, but also from any app running on the system. You can then apply effects, record in a variety of formats, and even broadcast audio live. Now, with the newly released version 4.3, Audio Hijack has added a new tool to its arsenal: audio transcription.
By taking advantage of OpenAI’s Whisper framework, Audio Hijack can now take any audio it’s recording and generate a text transcript. While this process was possible before—see Jason’s lengthy post about his workflow—it required a lot of fiddling and several different tools to accomplish; it’s certainly a lot easier to simply drop Audio Hijack’s block into your existing session. If you record multiple sources, it can even appropriately label each one—though if you record multiple people via one input, say the other end of a Zoom call, it can’t distinguish between the various participants.
If each person had Audio Hijack running on their own machine and transcribing, you could potentially assemble a transcript, though at present Audio Hijack only lets you tag transcript lines with Source and Timestamp, the latter of which is based on the amount of time elapsed in the session, which would make that process a little tricky. Hopefully, a future version will allow you to use the system clock as well.
AI-based transcription has been growing by leaps and bounds in the past couple years, and it’s been a particular boon to podcasters, who often want to create accessible and searchable archives of their show, without spending the lengthy amount of time to generate it by hand (or use a post-processing tool that requires tweaking and editing).
I ran the Transcribe block through a very quick test using just my MacBook Air’s built-in microphone. The results were, if not 100 percent accurate, extremely good, and I’m quite excited to try this out for several of my podcasts in the future.
Audio Hijack 4.3 is a free update for all owners of Audio Hijack 4; for new customers, it costs $64 or $29 if you’re updating from Audio Hijack 3. While the transcription feature will work on Intel-based Macs, Rogue Amoeba recommends Apple silicon Macs for the best experience.
- Full disclosure: Rogue Amoeba has sponsored Six Colors in the past, and CEO Paul Kafasis is a personal friend. ↩
[Dan Moren is the East Coast Bureau Chief of Six Colors. You can find him on Mastodon at @firstname.lastname@example.org or reach him by email at email@example.com. His latest novel, the supernatural detective story All Souls Lost, is out now.]
If you appreciate articles like this one, support us by becoming a Six Colors subscriber. Subscribers get access to an exclusive podcast, members-only stories, and a special community.