If we are regulars at video conferences and virtual meetings, we may be interested in transcribing video calls into text , either to read what is said on the screen using subtitles, or to save the entire conversation in a file.
Some video calling apps add automatic subtitles from the audio, analyzing it using artificial intelligence, and even translate it if it is in another language.
Now, if we want to transcribe what has been said in the conversation and save it as text , be it in Word or another format, our objective is complicated. It will almost always depend on external add-ons to the main apps (Skype, Microsoft Teams, Google Meet, Zoom, Jitsi Meet …), and it is not always easy.
How to transcribe an audio to text
So first we are going to explain step by step a method that works in any video call and has no cost , and then learn more specific options.
Google transcription: simple, free and universal
Since not all apps allow us to transcribe conversations, a solution is to use an app on the mobile , which records the audio of the video call and converts it to text. Logically, it is best to do it from a different device.
For this we can use Google Instant Transcription , an Android app that supports 70 languages, allows you to instantly switch between two of them and save the text for later use.
- Download Google Instant Transcript for Android
- As soon as you install and open the app, you have to click on “Allow” to record the sound from the microphone:
- The app will start to transcribe automatically, but we need to enter the settings, by clicking on the symbol of a cogwheel in the lower left corner:
- We must activate the option “Save this transcript” so that the text is preserved, with the limit of 3 days that the app indicates:
- If we go to “More settings” we can change the language (for example, if we make video calls in English) and choose a secondary language to change quickly:
- Any sound the microphone picks up will be transcribed, so it’s best to move it closer to the source of the video call. The system works best if people speak slowly and without background noise :
- Although when transcribing the app it does not put commas and makes mistakes with proper names , it has other strong aspects, such as that it identifies common sounds:
- Once the conversation is finished, it only remains to select the fragment to be transcribed , and press the “Copy” button to paste it into a Word document, email or another text editor:
This Google tool is not perfect, but it works well, it is free and simple. It is similar to Google Translate, which also supports text transcriptions , but between different languages.
We are going to see other more specific alternatives, which have different advantages and disadvantages, but which are worth knowing if they adapt to our needs.
Third party transcription services
On the other hand, some services allow you to transform video call conversations to text , in certain cases at a fairly high cost. For companies and professionals they may make sense, but not so much for private users.
Happy Scribe is an example, a software that covers more than 100 languages, puts commas, periods and questions, and even allows us to add frequently used words to the dictionary. We just have to download the recording of the video calls and upload them to their website.
The price starts at $ 12 per hour of transcription, with discounts if we buy packs of hours, so it is not cheap at all.
Another such service is Otter.ai , which offers a free plan with limitations, although the limit of 10 free hours per month is quite generous. Premium plans start at $ 8 per month, and allow you to integrate Otter.ai directly into Zoom , although the service can be used with any platform
A third alternative is Tactiq Pins , aimed at transcribing Google Meet video calls . It works like a Chrome browser extension, has a fairly complete free version and works in a premium version that for $ 5 a month will give us more possibilities.
Microsoft Teams: native transcription with limitations
Finally, in Microsoft Teams the transcription of recordings is a feature included by default, but not everyone will be able to use. If the recordings are uploaded to the Microsoft Stream cloud, it will allow us to access the subtitles section and download them as a text file.
Of course, in most cases the end user has little control. The free version of Teams does not allow transcription, only those of business or education , which usually hire large organizations.
Your organization administrator must have enabled the recording of video calls using group policy, but you can also use commands to disable transcripts expressly, globally or for individual users.
In conclusion, there are quite a few options to transcribe video calls to text , although not a universal and 100% reliable solution. We must test the existing alternatives and choose the one that best suits the app we use and our specific needs.
