musiccaps
2 rows where aspect_list contains "flat male vocal", aspect_list contains "groovy" and aspect_list contains "punchy 808 bass"
This data as json, CSV (advanced)
aspect_list (array) 16 ✖
- addictive 2
- flat male vocal · 2 ✖
- groovy · 2 ✖
- low quality 2
- punchy 808 bass · 2 ✖
- afrobeats 1
- bouncy 1
- claps 1
- energetic 1
- high pitched riser 1
- repetitive synth lead melody 1
- shimmering hi hats 1
- snare rolls 1
- strings melody 1
- trap 1
- wide harmonizing male vocals 1
ytid ▼ | url | caption | aspect_list | audioset_names | author_id | start_s | end_s | is_balanced_subset | is_audioset_eval | audioset_ids |
---|---|---|---|---|---|---|---|---|---|---|
4PGzlwvXMnE | The low quality recording features a trap song that consists of flat male vocals, alongside wide harmonizing male vocals, singing over punchy 808 bass and repetitive synth lead melody in the background. There is a high pitched riser at the end of the loop. It sounds groovy and addictive thanks to that cadence. | ["low quality", "trap", "wide harmonizing male vocals", "flat male vocal", "punchy 808 bass", "repetitive synth lead melody", "groovy", "addictive", "high pitched riser"] | ["Blues", "Music"] | 4 | 30 | 40 | 0 | 1 | ["/m/0155w", "/m/04rlf"] | |
uE3BHXXiCFs | The low quality recording features an afrobeats song that consists of a flat male vocal rapping over punchy 808 bass, strings melody, shimmering hi hats, claps and some snare rolls. It sounds addictive, bouncy and groovy thanks to that rhythm. | ["low quality", "afrobeats", "flat male vocal", "strings melody", "punchy 808 bass", "shimmering hi hats", "claps", "snare rolls", "addictive", "bouncy", "groovy", "energetic"] | ["Singing", "Reggae"] | 4 | 40 | 50 | 0 | 0 | ["/m/015lz1", "/m/06cqb"] |
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 );