Instant Transcription Tools

You may find yourself in need of an instant transcription tool for a whole host of reasons. Maybe you’d like to dictate your novel. Perhaps you need a transcription of your latest speech. Or maybe someone with whom you’re working speaks another language or is hard of hearing.

Whatever the reason, you have several free choices that will get you started. This week, I tried out three different voice-to-text tools to find their strengths and weaknesses: Google’s Voice Typing feature in Google Docs, Microsoft Translator and the Ava app. Watch this 2.5-minute video first, then we’ll discuss.


It’s kinda trippy to watch, right? As I talk, all three tools are transcribing in real time. It took me a while to go back to analyze which tools were best for which purpose. Here are my findings…

Best for Hearing Impaired: Ava

I guess there’s no surprise that the best tool for communicating with hearing-impaired people is the one made for that purpose. Ava was created to help hearing impaired people communicate with others. Their first releases specialized in helping with conversations with groups. Each person chatting around a table would download the Ava app and log in, Then the hearing-impaired person could see the transcriptions of each person on his screen. The app has gotten better over time, and I plan to use it in sessions like this:

The audience members won’t have to have the app. They can just go to a link and follow along in any browser.

Best for Transcription: Ava

Ava also wins for the tool that creates the best written transcription. As you saw from the video, Google Docs just records everything you say. You’d have to either speak the punctuation or go back and add it. Ava did a great job of finding the ends of my sentences and adding punctuation (but in this process, I learned that I pause a lot, which causes the tools to think I’m ending a sentence.)

Here is how the tools handled the transcripts. As you can see, Ava’s is going to be the easiest to cut and paste. Microsoft Translator adds time codes and the language. And Google Docs is just one big pile of words.

I also appreciated the fact that Ava would go back and correct phrases after it comprehended the bigger picture of the conversation. Microsoft and Google just kind of carried on.

None of them got everything 100% right, but that doesn’t surprise me.

Best for Larger Groups: Microsoft Translator

Although Ava was definitely my favorite for accuracy, for a casual user, you’re going to hit the 5-hour free limit pretty quickly. Microsoft Translator is 100% free, and you can create a link that people can visit to see the transcriptions. What’s more, Microsoft’s true purpose is that it will let you speak using one language, and people watching can have it translated into their native languages on the fly. So even though the accuracy was not as good and the written transcript wasn’t incredibly helpful for later use, Microsoft Translator will probably help you more with your larger audiences.

And if you have PowerPoint for Windows (won’t work on my Mac), check this out. Ummm… Awesome!

 

Best for Sitting at Home Talking to Yourself: Google Docs Voice Typing

Eh. Overall I have mixed feelings about Google Doc’s Voice Type feature. If you’re willing to punctuate your speech by saying “comma” and “period” aloud, this tool can be quite helpful. But I find that if I’m truly flowing in a dictation, adding the stops and the punctuation stifles my creativity. But it is free, so there’s that.

One last thing about Google Docs Voice Typing. Some people are using it to capture a transcript of recordings, and I found it works better if you play the recordings on a different device then push the Voice Typing button in Google Docs. If you play the recording on the same device, it doesn’t work well at all.

Product Hunt's Best Tech Tools
Win an Echo Dot!