Tapping Into Google’s Speech Recognition

Remember when you were in a lecture and the professor told you that they will hand the transcript after class so you can pay better attention? Technology today can help us make all lectures like that one!

Besides lecture transcripts, video (or audio) recordings can be very important in social sciences. The problem with such data is the need to transcribe them in order to summarize or count word occurrences or even evaluate if a response was right or wrong, say in a Stroop task.

In this article I will present a simple way to automatically transcribe audio or video recordings using Google’s speech recognition and save transcripts directly as Google documents. The main idea was from this video I have found when looking for a solution. However, I wasn’t satisfied completely, so I took it a step further.


We’ll start by making sure the video or audio file is on phone. On iOS (or iPadOS) this can be done easily by downloading the file directly or copying it to iCloud drive from a mac or PC.

Then, we connect your iPhone to your mac using a lightning cable to use it as an audio input device. Now, look for the Audio MIDI Setup app in your applications (usually found in the Utilities folder), open it and click “Enable” on the phone device in the left panel. Now you can select your phone as an input device in sound preferences (found in System Preferences). The benefit of doing this is that it isolates the sound from your phone and will not pick up any sounds from the surroundings.

The technical stuff is over!

an image showing the steps for using an iOS device as an audio source in macOS
Steps to use an iOS device as audio source on macOS

All is needed now is to go to Google Docs, sign in and create a new document. We will be using the “Voice Typing”* feature found under “Tools” in the menu bar. Choose the language from the drop-down menu and click the microphone icon, which will activate speech recognition for that document.

an image showing the steps for using voice typing in google docs
Steps to use Voice Typing in Google Docs

Finally, start the video or audio file on your phone and see the magic happening!

an animated gif to demonstrate voice typing in action

Applications for this method can be very useful in the academic field, for example, to transcribe lecture recordings or interviews. Other applications can be to prepare a transcript for videos in order to prepare them for translation, which is the main reason I got into this in the first place.

If you don’t have and iOS or a Mac and want to take advantage of this functionality, you’re still in luck; You can use a traditional 3.5 mm audio cable to connect your phone’s headphone jack to your computer’s line-in jack. The rest is history.

I hope you find this tutorial useful. If you have questions or would like to use this method but need some help, feel free to drop me a line through this form or on social media links below.

* Voice Typing only works on Google Chrome browser. For more information check out this page.