musiccaps
2 rows where aspect_list contains "autotune" and aspect_list contains "punchy kick"
This data as json, CSV (advanced)
aspect_list (array) 19 ✖
- autotune · 2 ✖
- low quality 2
- punchy kick · 2 ✖
- afrobeats 1
- background processed male vocal 1
- echoing effect 1
- echoing male vocal 1
- energetic 1
- folk 1
- fruity male vocal 1
- groovy synth bass 1
- loud 1
- noisy 1
- punchy snare 1
- repetitive synth melody 1
- shimmering hi hats 1
- syncopated toms 1
- uptempo 1
- wide plucked strings melody 1
ytid ▼ | url | caption | aspect_list | audioset_names | author_id | start_s | end_s | is_balanced_subset | is_audioset_eval | audioset_ids |
---|---|---|---|---|---|---|---|---|---|---|
AzsBSUmhl1M | The low quality recording features a folk song that consists of an echoing male vocal singing over syncopated toms, punchy kick, shimmering hi hats and wide plucked strings melody. It is kind of noisy and the vocals are really loud, compared to other instruments. | ["low quality", "echoing male vocal", "autotune", "syncopated toms", "punchy kick", "wide plucked strings melody", "shimmering hi hats", "noisy", "folk", "loud"] | ["Traditional music", "Music"] | 4 | 30 | 40 | 1 | 1 | ["/m/02p0sh1", "/m/04rlf"] | |
XjUmXwVlDDo | The low quality recording features a fruity male vocal, alongside processed background male vocal, with autotune and echoing effect on, rapping over repetitive synth melody, groovy synth bass, punchy kick and punchy snare hits. The song is uptempo and it sounds energetic. | ["low quality", "afrobeats", "fruity male vocal", "repetitive synth melody", "groovy synth bass", "punchy kick", "punchy snare", "energetic", "uptempo", "background processed male vocal", "autotune", "echoing effect"] | ["Afrobeat", "Music of Africa", "Music", "Rhythm and blues"] | 4 | 30 | 40 | 1 | 1 | ["/m/0145m", "/m/0164x2", "/m/04rlf", "/m/06j6l"] |
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 );