Method, apparatus, device, medium, and program product for generating media content

Abstract

A method, apparatus, device, medium and program product for generating media content are provided. The method proposed herein includes: presenting, at an input component, a first element and a second element, the input component being used to interact with an intelligent system, the first element indicating a first video, the second element indicating a first audio; receiving, by the input component, a first input, the first input including a description text; and presenting a second video, the second video including a picture content of the first video and a second audio, the second audio being derived based on the picture content and the description text, at least a portion of the second audio having a first audio attribute matching the first audio attribute of the first audio. In this way, the quality of the generated media content can be improved.

Images