musiccaps
2 rows where audioset_names contains "Theme music" and audioset_names contains "Whale vocalization"
This data as json, CSV (advanced)
ytid ▼ | url | caption | aspect_list | audioset_names | author_id | start_s | end_s | is_balanced_subset | is_audioset_eval | audioset_ids |
---|---|---|---|---|---|---|---|---|---|---|
fBEGBuO3RXg | This song is an orchestral piece. The tempo is slow with the vocalist singing in soprano,alto, mezzo, treble and bass harmony. The song is intense, grim, sinister, indicative of danger, eerie, enigmatic, out worldly and mesmerising. There are incoherent vocal riffs and sounds towards the end of this clip. | ["orchestral music", "choral harmony", "sinister", "incoherent vocal riffs", "mesmerising", "outworldly", "soprano", "celestial", "enigmatic", "perfect sync", "grim", "sinister", "mezzo", "alto", "mezzo", "tenor", "bass", "violins", "syncopated sounds", "dissonant sounds", "sinister", "eerie", "dangerous tense sounds", "electronic organ"] | ["Theme music", "Whale vocalization", "Music"] | 7 | 30 | 40 | 0 | 1 | ["/m/02cjck", "/m/032n05", "/m/04rlf"] | |
nxdHojfss_A | This is a cinematic classical music piece. There is a piano playing the chords while the strings are holding the melodic background. There is a mysterious ambient synth sound coming and going. A repetitive low-to-mid frequency percussive sound effect is being played to imply the sound of whales. The atmosphere of the piece is reminiscent of both underwater and outer space at the same time. That is why it could be used in science fiction movies and shows that have an aquatic or outer space setting. | ["classical", "instrumental", "piano", "strings", "ambient synth", "sound effects", "cinematic", "animal-like", "underwater", "outer space"] | ["Theme music", "Whale vocalization", "Music", "Ambient music"] | 9 | 30 | 40 | 0 | 1 | ["/m/02cjck", "/m/032n05", "/m/04rlf", "/m/0fd3y"] |
Advanced export
JSON shape: default, array, newline-delimited, object
CREATE TABLE [musiccaps] ( [ytid] TEXT PRIMARY KEY, [url] TEXT, [caption] TEXT, [aspect_list] TEXT, [audioset_names] TEXT, [author_id] TEXT, [start_s] TEXT, [end_s] TEXT, [is_balanced_subset] INTEGER, [is_audioset_eval] INTEGER, [audioset_ids] TEXT );