Apps like Siri and Google Assistant have required leaps in voice-recognition software to become user-friendly, and it seems like all that investment into R&D might yield a few other impressive apps in the near future, too.
One of those impressive apps is the Otter transcription app, which sounds like it might just be a standard voice recognition app, but it actually promises more functionality when you take a closer look.
It’s a relatively simple concept in practice, but impressive in execution. Simply start the app up and whatever conversation is going on and in listening proximity of the microphone, it’ll turn into text. This means a lot of time and effort saved for people that conduct interviews, students that want to record lectures, or anyone that needs to take notes in meetings. One of the biggest potential benefits is that it can even distinguish between different speakers, so taking minutes at an important conference or meeting should become a lot easier with an app like Otter.
It’s currently freely available, and a paid version is expected to release in the second half of 2018 – and the reception so far is positive, although there are clearly some improvements to be made. The app doesn’t seem completely accurate in noisy environments, or if there are too many speakers, but that’s to be expected. Like all new apps or hardware, it takes companies a while to iron out the issues, but after a while it should work perfectly.