Speech to Text API or SDK for Mobile (Cross-Platform)
What are the best currently supported speech or text API or SDK for mobile (multiple platforms: Android, iOS, etc)
There are a few posts particular to the iPhone, but I am looking for a solution that would work ideally cross-platform.
N.B. It seems that all solutions ultimately post to a REST-ful API on a remote server, as opposed to doing speech processing locally. (Is this true?)
Answer
I can think of a few that are cross platform for Android and iOS. However, they are commercial services and at at some level of service you must pay for them. For Android, Google provides free speech recognition. So, you might want to consider using Google's free recognition for Android.
You can look at:
- The Nuance SDK - http://dragonmobile.nuancemobiledeveloper.com/public/index.php?task=home
- iSpeech.org - https://www.ispeech.org/developers
- AT&T Watson - http://developer.att.com/developer/apiDetailPage.jsp?passedItemId=10700023
- Mozilla - https://wiki.mozilla.org/HTML5_Speech_API
If you want to try client side recognition on the mobile device. See:
- PocketSphinx - http://cmusphinx.sourceforge.net/
- OpenEars - http://www.politepix.com/openears/#
For some more background Text-to-speech (voice generation) and speech-to-text (voice recognition) APIs? may be helpful.