38

So i'm looking into building a speech to text app for fun. I did some research and found an inbuilt Speech to Text API using RecognizerIntent that is free, but also found that google is now offerieng a cloud speech API that the charge for.

My question is, what is the difference between them, and If i use the inbuilt RecognizerIntent, is it free?

Markus Kauppinen
  • 2,756
  • 4
  • 16
  • 28
AndroidDev21921
  • 645
  • 1
  • 7
  • 19
  • Like you noted, one is inbuilt, and the other is a cloud API. –  Nov 30 '16 at 23:32
  • Yup - i'm assuming the cloud one is more robust and has more features? Otherwise, why would one use one and not the other? – AndroidDev21921 Dec 01 '16 at 14:53
  • 1
    With a cloud API, you can use it from any device that can make http requests (laptop, iOS, server). There might also be usage restrictions like speed limits or # of requests per day. With something built-in, you need to use those libraries specifically (Android), and there are usually no restrictions (unless the lib just wraps the cloud API). But this is just general API vs. Library stuff. –  Dec 01 '16 at 16:55
  • Makes sense, thanks! I just didn't want to build something without realizing there might be future limiting and not building that into my app logic. Thanks again! – AndroidDev21921 Dec 01 '16 at 17:25
  • 1
    I would also like to know whether the two rely on the same technology or models, seeing as they are both by Google. And do they perform similarly. – ishido Jan 31 '17 at 11:26

1 Answers1

53

For the Google Cloud Speech API, refer to the following link:

https://cloud.google.com/speech/. Here are the highlights:

  1. It supports 80 different languages.
  2. It can recognize audio uploaded in the request.
  3. It returns text results in real-time.
  4. It is accurate in noisy environments.
  5. It works with apps across any device and platform.
  6. It is not free. Refer to the following link for pricing:

https://cloud.google.com/speech/pricing

For the Android Speech-to-Text API (Recognizer Intent), refer to the following link:

http://www.androidhive.info/2014/07/android-speech-to-text-tutorial/. Here are the highlights:

  1. Need to pass local language to convert speech to text.
  2. Not all devices support offline speech input.
  3. You cannot pass an audio file to be recognized.
  4. The intent returns an array of strings which match to out input. We can consider first one as the most accurate.
  5. It only works with Android phones.
  6. It is free.
Daniel
  • 2,339
  • 9
  • 21
  • 28
Patrick R
  • 5,704
  • 1
  • 18
  • 25