musiccaps
5 rows where aspect_list contains "emotional", aspect_list contains "energetic" and aspect_list contains "live performance"
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 |
---|---|---|---|---|---|---|---|---|---|---|
2I6pPRWKsCQ | The low quality recording features a live performance of a R&B song that consists of muffled male vocal singing over groovy bass guitar, mellow synth keys melody and energetic drums. There are some crowd noises in the background. The recording is noisy, as it was probably recorded with a phone, but it sounds energetic, passionate and emotional. | ["low quality", "noisy", "crowd noise", "live performance", "r&b", "energetic drums", "muffled male vocal", "groovy bass", "mellow synth keys melody", "energetic", "passionate", "emotional"] | ["Electric piano", "Keyboard (musical)", "Piano"] | 4 | 380 | 390 | 0 | 0 | ["/m/01s0ps", "/m/05148p4", "/m/05r5c"] | |
P3ZPbGjHFXE | The low quality recording features a live performance of a rock song that consists of passionate male vocal singing over electric guitar solo melody, energetic cymbals, muffled snare and kick hits and groovy bass guitar. There are also some crowd noises, singing along. It sounds energetic, emotional and addictive, thanks to that cadence. | ["low quality", "crowd noises", "noisy", "rock", "live performance", "electric guitar solo melody", "energetic cymbals", "muffled snare hits", "muffled kick hits", "passionate male vocal", "groovy bass guitar", "energetic", "emotional", "addictive"] | ["Singing", "Music", "Roll"] | 4 | 220 | 230 | 0 | 1 | ["/m/015lz1", "/m/04rlf", "/m/07s8j8t"] | |
XILyHZyyCik | The low quality recording features a live performance of a pop song that consists of flat male vocal talking, passionate female vocal, alongside harmonizing wide female vocals, singing over punchy kick and snare hits, shimmering hi hats and groovy bass. There are crowd singing and cheering sounds in the background. It sounds groovy, emotional, energetic and passionate. | ["pop", "low quality", "live performance", "flat male vocal", "passionate female vocal", "wide harmonizing vocals", "punchy kick", "punchy snare", "shimmering hi hats", "groovy bass", "crowd cheering", "crowd singing", "energetic", "groovy", "emotional", "passionate"] | ["Singing", "Music of Asia", "Music"] | 4 | 140 | 150 | 0 | 0 | ["/m/015lz1", "/m/028sqc", "/m/04rlf"] | |
jFek2xLbEww | A male singer raises this passionate melody. The song is medium tempo with an acoustic guitar accompaniment, groovy bass line and a subtle drumming rhythm. The song is passionate and relaxing. The song is played live and has poor audio quality. | ["male singer", "live performance", "groovy bass line", "medium tempo", "story telling", "ambient room nosiness", "people talking", "guitar accompaniment", "bass rhythm", "steady percussions", "folk music", "emotional", "energetic", "people talking", "poor audio quality", "folk music", "folk music", "guitarist"] | ["Singing", "Music", "Rattle (instrument)"] | 1 | 190 | 200 | 0 | 1 | ["/m/015lz1", "/m/04rlf", "/m/05r5wn"] | |
sTcaIARuemA | The low quality recording features a live performance of a song that is barely audible due to distorted sound, loud cheering crowd and female screams. There is definitely at least a boomy bass, punchy kick and snare hits and energetic cymbals, alongside some vocals singing over it. It sounds messy and muddy, but also emotional and energetic. | ["low quality", "crowd cheering", "female screams", "live performance", "punchy snare", "boomy bass", "energetic cymbals", "muddy", "messy", "loud", "distorted", "punchy kick", "vocals", "emotional", "energetic"] | ["Singing", "Music", "Yell"] | 4 | 150 | 160 | 1 | 1 | ["/m/015lz1", "/m/04rlf", "/m/07sr1lc"] |
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 );