If you are in an important video conference session and you are getting a transcript, to know you won’t remember, having a transcription of that session can be very helpful. Video and audio recordings are all well and good, but if you’re looking for a specific piece of data within an hour of conversation, searching for a text version of your meeting can be a lot easier.
There are a number of third-party apps that provide AI transcription for recorded audio, such as Rev and Otter.ai. They also offer extra features like listening to the audio at the same time and tracking where it needs fixing, or integrating it directly with other apps like Zoom. But these are paid subscription services. If free is what you’re looking for, there are a few workarounds that can help, although they have certain limitations.
Google Docs voice typing
Even long-time Google Docs users may not be aware of the voice typing tool that converts speech to text. This can be very handy if you have trouble typing or find speaking faster or easier than typing. It can also be used as a transcription tool for any video or audio recording you may have. You can even run it during a live video conference to write the speech as it is.
To use voice typing as a transcription tool:
- Open a new Google Doc
- Choose Tools > Voice typing
- If the language you are using is not displayed, click the link above the microphone icon and select your language
- Click the microphone icon when you’re ready to start recording. It will turn bright red and start transcription. Note: be careful to click on the microphone icon after that you start the sound you want to copy. Why? I will explain.
Once you start the transcription feature, you cannot leave the Google Docs page, otherwise the feature will turn off automatically. For example, if you’re transcribing a Zoom meeting and take a moment to click your email, from that point on you’ll lose everything until you go back to your document and click the microphone again.
Additionally, the resulting transcription – no, it’s less than perfect. If people are speaking intelligibly, the Google Docs transcription feature will do a decent job, but murmurs, slurs, or unclear speech can disappear altogether. In addition, forget about commas, periods and other subtleties – you will have to fill them in later if you want a completely grammatically correct document.
But there is an alternative.
Google Live Translate Text
Google’s Live Caption is an Android app that streams audio to your phone’s screen as soon as it “hears” it live. The app is incredibly simple: you install it, install it, and it starts transcribing right away. Originally developed as an accessibility tool for the deaf or hard of hearing, Live Transcribe will store a transcript for three days. If you want to keep the text longer than that, simply copy and paste it into a document.
To test these transcription apps, I ran them while playing a YouTube video of each. BoundaryDieter Bohn Offers to buy Pixel 4A. As you can see from the screenshots below, Live Transcribe handled the audio stream reasonably better than the Docs, although neither would receive any awards for accuracy. (I have to admit, I found the repeated mention of “pixel for a” in both apps quite funny.)
(By the way, I tried using Gmail’s voice-to-text mode on my mobile to get a transcription, but the app kept choking me for about 20 seconds.)
Decision? If you only need the occasional transcript of a meeting and don’t mind a few mistakes and only a few dots, commas and the like, then both might work for you, although I’d rather head over to Live Caption. Otherwise, check out third-party transcription services. They may not be free, but they are more accurate, which may be worth it.
