Connect with us
high angle photo of robot

Goldstuck on Gadgets

My robot assistant

Few of us have the patience to transcribe long interviews or speeches. But the robot assistant can do it for you, at no cost, writes ARTHUR GOLDSTUCK

What is it?

Allow me to introduce you to a miracle app: one of the few apps that I can truly say has changed my life.

It’s called, and it is primarily a transcription app, allowing any voice recording to be made through it, and to produce an immediate text transcription. The recording is uploaded to the cloud, and it uses artificial intelligence to compare words and accents against a vast database. If the sound quality is good, the transcription typically comes out about 98% accurate, but you can read along as you follow the played-back recording, and correct as you go. The transcript can then be exported as a text file.

Here’s the real beauty of it: if you record an interview through the Otter app on your phone, it transcribes as you go along. You can even watch the words appear to see which it is getting wrong. On completion, it uploads the transcription and runs it through the same AI software in the cloud, in order to sharpen the accuracy of what it transcribes. It then lets you know when it’s ready via notification or email. 

You can then activate an edit mode, which allows you to correct the transcription as you listen to the audio. This means that, for example, a half-hour interview can be corrected in half an hour, compared to around 3 to 6 hours of manually transcribing a recorded interview. It at least tripled my productivity.

In a Pro version, the user can upload a pre-recorded interview, and it takes less than half an hour to transcribe it in the cloud.

Not only has it saved me many hours of transcription, but also ensured I capture everything that is said, and never get the quotes wrong. Best of all, during a face-to-face interview, I now focus entirely on the subject, and on the conversation – which is what it becomes – rather than have a laptop between us and having to catch up constantly in my typing. 

It is, without a shadow of a hype, one of my top apps of the past three year.

It is free to use, for the first 600 minutes every month. The free version does not allow uploading pre-recorded files, though.

While it can be used in conferences and the like of court proceedings, the accuracy rate drops substantially. It also drops with strong accents, including a range of typical South African accents. However, it does allow the creation of a custom vocabulary.

Bottom line is the quality of the audio, the clarity of the speakers, and how close the speakers are to the microphone. It 

What does it cost?

It is free for up to 600 minutes a month, while the power user who needs up to 6000 minutes a month pays $8.33 a month for the Pro version, with a 36% deduction if paid annually. The pro version includes Otter Assistant, which automatically joins Zoom, Google Meet, or Microsoft Teams links from one’s calendar, and records and transcribes the meeting. It can shares live transcripts with all meeting participants, allowing everyone to add highlights and comments collaboratively.

Why should you care?

Most of us, from time to time, need to make notes from a meeting, lecture, or event, and most of the time we only get a snapshot of what was said. Thanks to the tools available on any smartphone, and when all parties to the conversation content, we tend to record proceedings and transcribe the recording later. The problem is that transcription can take four to eight times longer than the recording itself, leading to procrastination or even abandonment of the recording. With, transcription is instantaneous. It is a massive productivity boost.

What are the biggest negatives

  • Free alternatives for dictation are built into Microsoft Word, Google Docs Voice Typing and Apple Dictation. However, they use only voice recognition, and not AI, and their accuracy levels are well below that of Otter.
  • It does not record phone interviews within the app, but one can use a voice recorder on one handset to record a conversation on speakerphone on the other.

What are the biggest positives?

  • It doesn’t need training
  • It transcribes as it goes along.
  • It stores all one’s recordings and transcriptions on the website, and requires no software on the computer.
  • Works equally well on an app on a smartphone.

* Goldstuck is founder of World Wide Worx and editor-in-chief of Follow him on Twitter on @art2gee.

Subscribe to our free newsletter
To Top