The present disclosure provides a subtitle generation method and apparatus, a device, and a storage medium, and the method includes: in response to a subtitle generation triggering operation directed against at least one audio track in a target audio-video file, performing speech recognition on audio data on each audio track respectively to obtain text fragments corresponding to each audio track; and generating subtitles of the target audio-video file based on the text fragments corresponding to each audio track. Compared with a method of performing overall speech recognition on audio data on all audio tracks, in the present disclosure, independent speech recognition is performed on the audio data on each audio track, and thus, the influences of the audio tracks on each other are avoided, so that more accurate speech recognition results can be obtained, thereby improving the accuracy of subtitles generated based on the speech recognition results.