musiccaps
1 row where aspect_list contains "happy", aspect_list contains "piano chords progression" and aspect_list contains "wide reverberant brass section melody"
This data as json, CSV (advanced)
Suggested facets: audioset_ids (array)
ytid ▼ | url | caption | aspect_list | audioset_names | author_id | start_s | end_s | is_balanced_subset | is_audioset_eval | audioset_ids |
---|---|---|---|---|---|---|---|---|---|---|
VnJeG9RGUVM | The low quality recording features a big band song that consists of wide reverberant brass section melody, shimmering shakers and cymbals, bells melody, piano chord progression, smooth bass and soft kick hits. There are some tom rolls that represent a transition into the next section. It sounds happy and fun, but it also gives off euphoric and nostalgic vibes, as it sounds vintage. | ["low quality", "big band", "wide reverberant brass section melody", "shimmering cymbals", "shimmering shakers", "tinny percussive elements", "tom rolls", "bells melody", "piano chords progression", "smooth bass", "soft kick", "happy", "fun", "nostalgic", "euphoric", "vintage"] | ["Swing music", "Music"] | 4 | 30 | 40 | 1 | 1 | ["/m/015y_n", "/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 );