AN ARTIFICIAL INTELLIGENCE APPARATUS FOR CONVERTING TEXT AND SPEECH IN CONSIDERATION OF STYLE AND METHOD FOR THE SAME

摘要

An embodiment of the present invention provides an artificial intelligence apparatus for interconversion of text and voice. The artificial intelligence apparatus comprises: a memory storing a plurality of text-to-speech (TTS) engines; and a processor obtaining image data including text, determining a voice style corresponding to the text, generating voice corresponding to the text using a TTS engine corresponding to the determined voice style among the TTS engines, and outputting the generated voice. The artificial intelligence apparatus may provide an interconversion service of text and voice.