AT&T opens up its Watson speech engine via SDK for iOS and Android

Realizing Apple and Google are moving swiftly to mainstream speech recognition on mobile devices, U.S. carrier AT&T today announced that it is opening up its own Watson speech engine to iOS and Android platforms via a software development kit (SDK), now available on the AT&T Developer website.

Much like Apple’s Siri or Google Voice Actions in Android (and Google Now), Watson takes input, analyzes it, performs one or more services and returns a result. Input can be audio files, speech, gestures, face recognition and text. Here’s a video of Watson in action…

An AT&T Labs Research project, Watson can transcribe spoken words into text on the fly. iOS and Android developers can now tap the official Watson SDK to quickly add advanced voice recognition feature to their apps.


Watson can learn different accents, speech patterns and dialects over time, as well as distinguish between speaker and platform variations and background environments.

According to AT&T:

Watson can not only convert from speech to text but can combine speech with other modalities, such as a touch-screen tap (“show me the closest Starbucks, here”) or other gesture, and send the information to a device.

Watson also converts from speech to speech to do translations, even involving multiple languages: speech input in one language can be converted to text in real time, followed by a text translation (with little delay), followed by the spoken translated sentence at sentence end.

And here’s the free AT&T Translator app which relies on the Watson API.


Some of the more notable features it supports: Web Search Speech to Text, Business Search Speech to Text, Voicemail to Text, SMS Speech to Text, Question and Answer Transcription, TV Speech to Text, Generic Speech to Text.

It’s no Siri, but surely Watson impresses with a comprehensive list of advanced features some of them quite unique.

Currently, iOS developers cannot tap Siri because Apple has yet to open up its technology via APIs, something that has been rumored to arrive with iOS 6 though it seems Apple pushed back those plans.