New iPhone OS to have voice recognition?
The rumor mill has been put into high gear this morning by a discovery of some code in the latest iPhone OS 3.0 beta release indicating that voice recognition may be a part of the new operating system.
Even though the newest beta developer code for for Apple’s iPhone 3.0 operating system has been out for about a week, people are still finding new things in it. There appears to be hooks in the new API for both voice recognition and voice synthesis, in the form of an OS component named Jabbler, already in the new operating system, according to a PC World story.
This new OS component will apparently be used to build an enhanced Springboard application, which is the software in the iPhone which controls the home screen and launches applications. This part of the OS will also be the basis of the new Spotlight search feature. It is possible that we have already seen part of the new Apple voice functionality built into the latest iPod shuffle, which is able to read items like playlists, song selections, and other text items in a synthesized voice.
Apparently this rumor started this morning when sources close to the iPhone OS 3.0 project told ars technica about the existence of the voice recognition part of the package. It seems surprising that it had not been noticed before, since the current beta developers code has been out for a week and has been pretty thoroughly investigated. Apple has not confirmed this rumor.
Give that some part of this technology has already been released in the iPod product line, and because there is a tendency for Apple to use new features across product lines, there is some chance that this rumor is true. It does seem as if any announcement of the feature has been left a little late, since the new OS and the new iPhones are due out in early July. There does not seem to have been much developer notice, which would lead one to believe that not many apps could take advantage of the new feature by the scheduled release data.
Still, think about what developers could do with such software. Just as one example, think of Wikipedia software that you could invoke by saying its name, then have it search for a spoken search term, and finally have it read the Wikipedia article, all without taking the phone from your ear. That, no matter how you slice it, is good stuff.
Related Posts:
