Main output of TalkToTalk is Speech. In this app, Speech is generated using Images and Text using various mechanisms, and sometimes store them. Following are the main Feature Activities in this app.
• Text to Speech - This mechanism is the ordinary text to speech generation. When user types something, that can be outputted as speech using this method.
• Camera Talk - Camera Talk is the facility of identifying text from camera and read them in real time. In here text is identified from the camera of the mobile device, and when you hit the speak button, those recognized text can be automatically read.
• Image Talk - Image Talk is similar to Camera Talk, but there is a little difference. In here, the user need to take a photo or import a photo from the gallery, and then the text will be generated from that still image. (Not a real-time text identifying mechanism)
• My Grid - The user can store images which he/she requires in his/her day to day life, with a word phrase in My Grid. When he/she clicks on a particular image, the phrase will be read automatically.