Abstract: An AI-based system and method for generating animated videos from an audio segment is disclosed. The method includes receiving a first audio segment including a description of one or more characters and a scenery for the one or more characters, and a second audio segment including a character speech to be spoken by each of the one or more characters by using one or more expressions. The method includes generating a character image for each of the one or more characters, extracting one or more character sounds and one or more character phrases from the second audio segment, and obtaining one or more prestored video clips from an external database. Furthermore, the method includes generating one or more character video clips and a final character video, such that the final character video may be outputted on user interface screen of one or more electronic devices.