This SDK provides an interface to the DOCOMO Speech Recognition API, enabling speech recognition to be added to Android applications. This particular Android SDK contains technologies powered by NTT IT language processing, and provides support up to Android version 4.2. The SDK offers a recording time of 15 seconds. The API accepts spoken voice within an audio file, and transcribes the language detected into words.
iSpeech, a leading provider of speech technology solutions and mobile applications, has just announced the launch of the iSpeech Publishing Platform which makes it possible to convert text from books, websites, mobile applications and other text-based content into human quality audio. iSpeech also provides a suite of Text to Speech APIs and SDKs for developers to use in web and mobile applications.
The Rekognition API differentiates its feature set by processing images to recognize more than just the location of faces. Rekognition's technology will analyze a given photo and present a list of scenes, each with a probability rating. Faces are not simply identified, but are also classified for age and emotion.