musiccaps
2 rows where aspect_list contains "bass guitar", aspect_list contains "male vocals" and is_balanced_subset = 1
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 |
---|---|---|---|---|---|---|---|---|---|---|
QSaX7QfeWog | This is the live performance of a country music piece. There is a female vocal and two male vocals taking turns and sometimes singing the words at the same time. The melody consists of an electric guitar, an acoustic guitar and a bass guitar while in the rhythmic background there is an acoustic sounding upbeat drum beat. The atmosphere is cozy. There is an easygoing aura to it. This piece could be used in the soundtrack of a movie or a TV show that takes place in rural USA. | ["country music", "female vocal", "male vocals", "electric guitar", "acoustic guitar", "acoustic sounding drums", "bass guitar", "simple tune", "easygoing", "cozy", "joyful", "upbeat", "live performance"] | ["Singing", "Country", "Music", "Mandolin", "Ska", "Song"] | 9 | 30 | 40 | 1 | 1 | ["/m/015lz1", "/m/01lyv", "/m/04rlf", "/m/04rzd", "/m/06rqw", "/m/074ft"] | |
mqyeBqaUeN8 | This is a Brazilian samba piece used as a jingle. The male vocals are singing in a shouting-like manner, repeating a slogan. There is a heavy use of syncopated latin percussion in the rhythmic background. The acoustic guitar and the bass guitar in the background support the melodic structure of the vocals. | ["samba", "male vocals", "jingle", "percussion", "acoustic guitar", "bass guitar", "brazilian", "energetic", "uplifting"] | ["Music", "Middle Eastern music", "Salsa music"] | 9 | 30 | 40 | 1 | 1 | ["/m/04rlf", "/m/06j64v", "/m/0ln16"] |
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 );