Audio generation method, server and storage medium are provided. The method includes obtaining a comparison audio, and performing a theme extraction on the comparison audio to obtain a comparison note sequence, the comparison note sequence comprising comparison note positions, comparison note pitches, and a comparison note duration; obtaining an original audio matching with the comparison audio via audio retrieval, and obtaining an original note sequence corresponding to the original audio by performing a theme extraction on the original audio, the original note sequence comprising original note positions, original note pitches, and an original note duration; calculating theme distances between fragments of the comparison audio and fragments of the original audio according to the comparison note sequence and the original note sequence; and generating an audio by capturing a fragment that is of the original audio and that satisfies the smallest theme distance.