If you are in an important video conference session and you get an info dump that you can't remember, doing a transcription of that session can be very useful. Video and audio recordings are all well and good, but a text version of your meeting can be a lot easier to find if you're looking for a specific bit of data within an hour of conversation.
There are a number of third party apps that provide AI transcriptions for recorded audio, such as: B. Rev and Otter.ai. They also offer additional functions such as: For example, the ability to simultaneously listen to audio and search for places that need correction, or integrate directly into other apps such as Zoom. However, these are paid subscription services. If you are looking for free, there are a few workarounds that you might find helpful – though they have certain limitations.
Google Docs voice typing
Even long-time users of Google Docs may not be familiar with the voice input tool that converts speech to text. This can be very handy if you are having trouble typing or just 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 do it during a live video conference to transcribe the conversation.
To use voice input as a transcription tool:
- Open a new Google Doc
- Choose Tools> Voice Input
- If you don't see the language you are using, click the link above the microphone icon and select your language
- When you're ready to start recording, click the microphone icon. It turns bright red and starts transcribing. Note: After starting the audio to be transcribed, carefully click the microphone icon. Why? I will explain.
Once you have started the transcription function, you cannot exit the Google Docs page. Otherwise the function is automatically deactivated. For example, if you transcribe a Zoom meeting and take a moment to click into your email, after that point you will lose everything until you return to your document and click the microphone again.
Additionally, the resulting transcription – well, being a nonprofit – isn't perfect. When people speak clearly, the Google Docs transcription feature does a reasonable job, but murmurs, aside comments, or unclear language can be completely lost. Also, forget about commas, periods and other special features. If you want a completely grammatically correct document, you will have to fill it in later.
However, there is an alternative.
Google Live Transcribe
Google Live Transcribe is an Android app that broadcasts audio live to your phone's screen as it "hears" it. The app is extremely simple: you install it, download it and it starts transcribing straight away. Live Transcribe was originally developed as an accessibility tool for the deaf or hard of hearing and stores a transcription for three days. If you want to keep the text longer, just copy and paste it into a document.
To test these transcription apps, I played a YouTube video by Dieter Bohn from The Verge in which he presented his attitude towards the Pixel 4A. As you can see in the screenshots below, Live Transcribe handled the audio feed somewhat better than Docs. (Though I have to admit, I found the repeated mentions of the "Pixel for a" from both apps quite funny.)
You can transcribe audio using Google Docs. It's free, but not that accurate.
Live Transcribe on Android is a little more accurate, but only slightly.
(By the way, I also tried using Gmail's voice-to-text mode on my phone to get a transcription, but the app choked me in about 20 seconds.)
The judgment? If you only need an occasional transcription of a meeting and don't care about a bunch of mistakes and few periods, commas, and the like, both of these may work for you, although I lean toward Live Transcribe. Otherwise, check third-party transcription services. They may not be free, but they are more specific, which is well worth it.