musiccaps
2 rows where audioset_names contains "Happy music" and audioset_names contains "Soul music"
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 |
---|---|---|---|---|---|---|---|---|---|---|
2kcSUBkFbaQ | The Low Quality Hip Hop song features a dry, flat male vocal rapping over punchy kick layered with shimmering open hats, punchy kick, simple hi hats, claps, syncopated snare hits, wide arpeggiated synth melody and stuttering synth chords. It sounds energetic and kind of unnatural, since the vocal is so detached from the instrumental due to the bad mixing of the song. | ["low quality", "dry flat male vocal", "punchy kick", "shimmering open hat", "simple hi hats", "soft crash cymbal", "stuttering synth chords", "wide arpeggiated synth melody", "clapping", "hip hop", "unnatural mix", "energetic"] | ["Funk", "Music", "Dance music", "Soul music", "Happy music"] | 4 | 30 | 40 | 0 | 1 | ["/m/02x8m", "/m/04rlf", "/m/0ggx5q", "/m/0gywn", "/t/dd00031"] | |
svNayU6q3Dg | This is a pop music piece. There is a female vocalist singing in a shout-like style. There is a flute and an electric guitar playing the melody with the bass guitar playing in the background. The rhythm is provided by a medium tempo acoustic drum beat. The tune is catchy. The piece is in the major key and there is an easygoing atmosphere to it. This piece could be used in the soundtrack of a sit-com during the credits section. | ["pop music", "female voice", "shouting-like singing", "flute", "electric guitar", "bass guitar", "acoustic drums", "easygoing", "catchy", "sentimental", "medium tempo"] | ["Music", "Soul music", "Happy music"] | 9 | 20 | 30 | 0 | 0 | ["/m/04rlf", "/m/0gywn", "/t/dd00031"] |
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 );