musiccaps
2 rows where aspect_list contains "punchy snare" and audioset_ids = "["/m/04rlf", "/m/06bxc"]"
This data as json, CSV (advanced)
ytid ▼ | url | caption | aspect_list | audioset_names | author_id | start_s | end_s | is_balanced_subset | is_audioset_eval | audioset_ids |
---|---|---|---|---|---|---|---|---|---|---|
BeFjxrUwAC4 | The low quality recording features a trap song that consists flat male vocal, alongside widely spread male ad libs, rapping over arpeggiated, echoing synth melody, sustained and distorted synth melody, boomy 808 bass, punchy snare, soft kick hits, bouncy hi hats and shimmering open hats. There is a short snare roll at the end of the first part of the loop. It sounds quiet, but still energetic and exciting. | ["low quality", "trap", "wide male ad libs", "arpeggiated echoing synth melody", "boomy 808 bass", "white noise down sweep", "flat male vocal", "punchy snare", "bouncy hi hats", "shimmering open hats", "soft kick hits", "quiet", "sustained distorted synth melody", "energetic", "exciting"] | ["Music", "Rapping"] | 4 | 30 | 40 | 0 | 1 | ["/m/04rlf", "/m/06bxc"] | |
RXGDlFry3Vo | The low quality recording features a hip hop track that consists of flat male vocal rapping over smooth bass, high pitched female vocal, mellow piano melody, shimmering tambourine layered with punchy snare, followed by soft kick and crash cymbal hits. It sounds groovy and emotional, even though the recording is muffled and kind of dull, due to the bad mixing. | ["hip hop", "low quality", "smooth bass", "high pitched female vocal", "mellow piano melody", "flat male vocal", "shimmering tambourine", "soft crash cymbal", "punchy snare", "soft kick hits", "groovy", "emotional", "muffled", "dull"] | ["Music", "Rapping"] | 4 | 30 | 40 | 0 | 1 | ["/m/04rlf", "/m/06bxc"] |
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 );