Turn Speech Into Text With Audio Hijack 4.3’s New Transcribe Block

Our flagship recording tool Audio Hijack can now act as your own personal stenographer! We’ve just released version 4.3, with a brand-new Transcribe block to turn spoken audio into a written text transcript. Read on for more details, or grab this free update immediately by selecting Check for Updates in the Audio Hijack menu or downloading right here.

The Brand-New Transcribe Block

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.1
Best of all, unlike traditional transcription services, Transcribe works for free inside of Audio Hijack. There’s absolutely no ongoing cost, so you can generate unlimited transcriptions and never again pay a per-minute charge. It’s pretty incredible.
It’s also completely private. When you use Transcribe, everything happens right on your Mac. That means your data is never sent to the cloud, nor shared with anyone else.
Transcribe Audio From a Microphone
To get started, use Audio Hijack’s Template Chooser to create a new Transcribe session, which you can see running below:

This straightforward configuration takes audio from a microphone and runs it through the Transcribe block, while also saving a recording for reference. Just speak into a microphone connected to your Mac and you’ll get a transcript file.
Transcribe Calls or Any Audio From an Application
Thanks to Audio Hijack’s ability to capture audio from any app running on your Mac, you can now transcribe anything you can hear. This is particularly useful for voice and video calls over Zoom, Skype, and other VoIP services.

Skip the note-taking! With text transcripts, your meetings on Zoom and calls on FaceTime can now be referenced and searched. And of course, this isn’t limited to just VoIP apps. Use Transcribe with any application on your Mac, for endless speech to text possibilities.
Transcribe From a File

Your audio doesn’t even need to be live. If you already have a recorded audio file, it can serve as a source for transcription. Play the audio file in any app (such as our audio editor Fission), then capture the audio with Audio Hijack and route it through the Transcribe block to get your transcript.
Great for Podcasters
With Audio Hijack and the new Transcribe block, it’s easy for podcasters to provide audiences with a text transcript of every show. Make it part of your podcasting setup, and your transcript will be ready for you moments after you finish recording.
When recording from multiple inputs, Transcribe can even handle multiple hosts, with the transcript accurately labeling each speaker:

Your resulting transcript will be easy to read:

You may wish to clean up transcripts for accuracy before posting, but even a rough, unedited transcript can be very helpful for listeners.
Beta; More to Come

When using the Transcribe block, you may notice it has a “beta” label. It’s not yet as polished as we plan for it to be and you should be cautious when using it in production systems. Still, we’ve tested it thoroughly, and it’s incredibly useful even as a beta.
Try it out, then let us know what you think. We already have plans for more transcription integration in future Audio Hijack updates, and user feedback will definitely be a helpful guide.
Get Audio Hijack 4.3 Right Now

The new Transcribe block will be a boon to all manner of users, from podcasters to lawyers to doctors and more. The ability to quickly convert spoken audio into a text file opens up countless new workflows, and we’re excited to see how you use it!
Get the brand-new Transcribe block right in Audio Hijack 4.3, which is a free update for all existing users of version 4. Just select Check for Updates from the Audio Hijack menu to download it today.
If you’re new to Audio Hijack, visit the app’s product page to learn more about the Mac’s very best audio recording tool, then download the free trial to test it out. You’re going to be delighted.

Footnotes:

For the best experience, Apple Silicon-based Macs are strongly recommended. Due to the processing requirements of the machine learning models, Intel Macs can be very slow to transcribe. Transcribe will run on any Mac that supports Audio Hijack 4.3, but Apple Silicon Macs are best. ↩︎