Flag this photo
Though firmware for the iPhone 3GS -- which introduced iOS Voice Control -- included a private voice synthesis framework called VoiceServices, Apple didn't release a version of iOS that made extensive use of voice synthesis until the unveiling of iOS 5 and iPhone 4S. Examples of speech synthesis for iOS include Apple's Siri, a virtual assistant app, and a handful of independently developed tools offering speech recognition and synthesis capabilities.Related Searches: SiriSiri, a feature integrated with the built-in apps in iOS 5, is a serious overhaul of the more limited Voice Control feature found in some pre-fifth generation iPhones. Siri uses speech synthesis in combination with speech recognition. Users can ask Siri to create lists or items in the Reminds app; play specific genres, artists or songs on the iPod; search through or compose emails, and text messages; check the weather by location and by date; or look for directions to a specific location using the Maps app. Siri responds to all queries with a multimedia message displayed in text and spoken aloud using speech synthesis. The initial synthesized reply asks the user to verify that Siri has recognized the correct task to perform. Upon receiving the go-ahead from the user, Siri responds again and performs the task.
ESpeakESpeak is an open-source speech synthesizer created for Windows and Linux. It supports 43 languages. Though eSpeak has not been ported to iOS officially, Google has notably integrated aspects of it into their Google Voice and Google Translate apps for the iPhone and iPad. In Google Translate, for example, eSpeak powers the automated synthesis when users request playback of translations into certain languages.
OpenEarsOpenEars is an independently developed, open-source text-to-speech and speech-recognition library for the English language, first released in late 2011. Developers looking to integrate Siri-inspired features into their iOS apps before Apple offers open access to their speech synthesis API will need to download the open-source Pocketsphinx and Flite libraries in addition to OpenEars itself. As of the publication of this article, no OpenEars powered apps had reached the iOS App store.
Acapela TTSAcapela TTS is an independently developed, commercial text-to-speech engine for iOS. Unlike OpenEars, Acapela TTS does not support speech recognition. Acapela TTS includes speech synthesis tools for 25 languages in addition to English, versions are available for competing mobile operating systems including Android and Windows Mobile. Apps for iPhone and iPad that use the Acapela API include Assistive Chat, an augmentative communication device for people with disabilities, the iSpeak series of talking foreign-language dictionaries and the RSS Speaker series of screen-reader apps.
ReferencesArs Technica: IPhone VoiceServices: Looking Under the HoodWired Magazine: With Siri, the IPhone Finds Its VoiceApple: iPhone 4S: Ask Siri to Help You Get Things DoneSourceforge: ESpeak Text to SpeechiTunes: Google TranslatePC Magazine: Google Voice Returns to App StoreOpenEars: Getting Started With OpenEarsAcapela Group: Acapela TTS for iPhone and iPadAcapela TTS for iPhone and iPad: FAQAcapela for IPhone: GalleryPhoto Credit Jupiterimages/Creatas/Getty ImagesRead Next: Print this articleCommentsAnnaDec 01, 2011but what about the basic fundamental drawbacks of a "talk-centric" society and the affects on the aging baby boom generation. Not to mention the next generation. What will they be talking to ( or at).Follow eHowFollowView the Original article
0Awesome Comments!