Text-to-speech or Speech synthesis process is the production of artificial human voice. A system used for this purpose is called voice synthesizer, and can be implemented in software or hardware. A text-to-speech(TTS) converts normal language text into voice; other systems interpret symbolic linguistic representation (such as phonetic transcription) of voice.
Synthesized voice can be created by concatenating pieces of recorded speech, stored in a database. The systems differ in the size of the stored speech units; a system that stores phones or allophones, provide the largest output range, but may lack clarity. For specific uses, storage of words or entire phrases enables a high quality output. Alternatively, a synthesizer can incorporate a model of the vocal tract (the path traveled by voice) and other characteristics of the human voice to create as a voice output completely "synthetic".