Speech recognition and text to speech have already been used in so many popular apps on the iPhone and iPad — dialing apps, dictation apps, translation apps. There are some commercial libraries available, but all of them seem to have a significant up front or usage costs.
The open source PocketSphinx library from Carnegie Mellon University has been used in several apps. The only instructions I could find on how to implement the library on the iPhone the instructions were very cryptic, and I just didn’t have the inclination to figure everything out.
Fortunately an open source library just for iOS devices known as OpenEars has become available, and it looks good. Featuring high performance and low cpu usage, multiple voices, Objective-C methods for easy interaction, Java speech grammar format support, and more.
The libary along with detailed instructions on how to get started and use OpenEars within your apps can be found on the Politepix website at:
Welcome To OpenEars!
It will be interesting to see how the speech recognition compares to the big name commercial apps in the app store, and those apps that require connection to a server for speech recognition. There are a few steps to the install process, and I’m off to try it out.
Submit A Resource
Have you created a useful tutorial, library or tool for iOS development that you would like to get in front of our 300,000+ monthly page views from iOS developers?
You can submit the url here.
The resources we feel will appeal to our readers the most will be posted on the front page.