I doubt they will be bought by Google, Apple is probably already writing cheques. Apple has been getting the pants beat off them by Google in mobile translation for awhile now. If there is a patent behind this then Apple will grab this for their stable just to keep it off the Android platform. It would be a huge 'one-up' for them. (which makes me sad as I strongly prefer Android devices) In time you'll see it licensed to other platforms as a new cash cow.
This should also be viewed as a prime example that it is not always better to push complex processing into the cloud. This would not be possible trying to push to a server somewhere real-time.
I don’t think the translation is the amazing part – as one of the creators said here, at the moment it mostly does word-for-word translation. Google’s statistical machine translation is mightily impressive technology, I’m not sure whether you could even theoretically put it on a phone at the moment.
You would ideally want the OCR and text replacement together with Google’s translation algorithms, which, besides requiring a network connection at the moment, would also introduce way too much lag that would kill the experience.
(Word-for-word translation is a perfect compromise in the meantime.)
Requiring a network connection would also make it useless while travelling abroad, which would probably make up about 90% of the times when you'd actually need this app. Not using a network connection is vital for this app to be of any real use.
Here's an interesting thought. This app is so good it could influence Apple hardware.
While I agree this is a killer app for the iOS platform, it doesn't yet have the polish that Jobs would demand for a live demo. A good deal of that is the hardware contraints of the system.
I think if you had invented a dedicated device that did nothing but this app it would sell like hotcakes, and we've heard in this forum that people are considering buying iPod touches just to give them out this app to family.
Thus if you wanted to move the needle from 'wow' to 'insanely great' it would take hardware level engineering to optimize the device, which I don't think it outside the realm of possibility.
Remember it was killer apps like quake, unreal, and crisis that moved the graphics card industry for years. This app has the potential for even broader appeal, and its successors will require even more horsepower.
This should also be viewed as a prime example that it is not always better to push complex processing into the cloud. This would not be possible trying to push to a server somewhere real-time.
Kudos to this team.