musiccaps
2 rows where aspect_list contains "piano" and aspect_list contains "synth pads"
This data as json, CSV (advanced)
aspect_list (array) 16 ✖
- piano · 2 ✖
- slow tempo 2
- synth pads · 2 ✖
- bass 1
- cinematic 1
- contemporary gospel song 1
- drones 1
- easy listening 1
- falsetto voice 1
- female voice 1
- horror 1
- percussion 1
- scary 1
- synth sounds 1
- voice whispering 1
- wind 1
ytid ▼ | url | caption | aspect_list | audioset_names | author_id | start_s | end_s | is_balanced_subset | is_audioset_eval | audioset_ids |
---|---|---|---|---|---|---|---|---|---|---|
YEwikeeqF38 | This audio contains a scary song that may belong in a horror movie. There is a tuned wind sound, synth pads and drones creating an uncomfortable atmosphere. On top of that a synth pluck sound is playing a dissonant melody and a piano is playing one single note in the mid range. | ["cinematic", "horror", "synth pads", "drones", "voice whispering", "piano", "wind", "scary", "slow tempo"] | ["Music", "Scary music", "Inside, small room"] | 6 | 330 | 340 | 0 | 0 | ["/m/04rlf", "/t/dd00037", "/t/dd00125"] | |
k4kbpRRRgcQ | This contemporary gospel song features a female voice. When the voice reaches a high pitch, she sings in falsetto. This is accompanied by percussion playing the floor tom and kick. The splash cymbal is played on the fourth count of the bars. A piano plays arpeggiated chords in the background. Synth pads play chords in the background filling the musicscape. This gospel song is emotional. This song can be played in a worship session in church. | ["contemporary gospel song", "female voice", "synth pads", "falsetto voice", "percussion", "piano", "bass", "synth sounds", "slow tempo", "easy listening"] | ["Christian music", "Music"] | 0 | 250 | 260 | 0 | 0 | ["/m/02mscn", "/m/04rlf"] |
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 );