musiccaps
2 rows where aspect_list contains "passionate male vocal" and aspect_list contains "snappy snare"
This data as json, CSV (advanced)
aspect_list (array) 20 ✖
- passionate male vocal · 2 ✖
- snappy snare · 2 ✖
- acoustic rhythm guitar 1
- energetic crash cymbal 1
- happy 1
- joyful 1
- low quality 1
- mellow bass 1
- mono 1
- noisy 1
- passionate 1
- piano chords 1
- playback 1
- pop 1
- romantic 1
- shimmering hi hats 1
- shimmering shakers 1
- soul/r&b 1
- synth pad 1
- wide acoustic rhythm guitar melody 1
ytid ▼ | url | caption | aspect_list | audioset_names | author_id | start_s | end_s | is_balanced_subset | is_audioset_eval | audioset_ids |
---|---|---|---|---|---|---|---|---|---|---|
5ZX9Ig7XXsw | The Soul/R&B song features a passionate male vocal singing over shimmering hi hats, energetic crash cymbals, wide acoustic rhythm guitar melody, shimmering shakers, snappy snare, piano chords and mellow bass. It sounds passionate and romantic - like something you would sing to your partner. | ["soul/r&b", "passionate male vocal", "shimmering hi hats", "energetic crash cymbal", "wide acoustic rhythm guitar melody", "shimmering shakers", "snappy snare", "piano chords", "mellow bass", "passionate", "romantic"] | ["Singing", "Music", "Musical instrument", "Soul music"] | 4 | 170 | 180 | 0 | 0 | ["/m/015lz1", "/m/04rlf", "/m/04szw", "/m/0gywn"] | |
Aro-HcWNsHI | The low quality recording features an acoustic rhythm guitar playing over a pop song played on playback in the background. It sounds joyful and happy, while the recording is in mono and noisy. | ["low quality", "playback", "pop", "passionate male vocal", "snappy snare", "synth pad", "acoustic rhythm guitar", "noisy", "mono", "joyful", "happy"] | ["Country", "Music", "Strum", "Bluegrass"] | 4 | 30 | 40 | 0 | 0 | ["/m/01lyv", "/m/04rlf", "/m/07s0s5r", "/m/0gg8l"] |
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 );