musiccaps
5 rows where aspect_list contains "happy", aspect_list contains "punchy kick", aspect_list contains "punchy snare" and aspect_list contains "shimmering hi hats"
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 |
---|---|---|---|---|---|---|---|---|---|---|
JNwt0afB1fQ | The Rock song features a flat male vocal singing over arpeggiated electric guitar melody located in the right channel of the stereo image, groovy bass guitar, punchy kick and snare hits and shimmering hi hats. The stereo image is unbalanced because of the electric guitar, which makes it lean towards the right channel. It sounds energetic, groovy, happy and fun. | ["rock", "groovy bass guitar", "punchy snare", "flat male vocal", "shimmering hi hats", "punchy kick", "arpeggiated electric guitar melody", "energetic", "groovy", "unbalanced stereo", "happy", "fun"] | ["Funk", "Music", "Rock music", "Ska"] | 4 | 30 | 40 | 0 | 1 | ["/m/02x8m", "/m/04rlf", "/m/06by7", "/m/06rqw"] | |
Pd4WnsXwdqw | The Children song features a mellow kid vocal singing over groovy bass, punchy kick and snare hits, shimmering hi hats, shimmering bells melody, plucked strings melody and wide keys melody. It sounds happy, joyful and fun - like something kids would listen to. | ["children song", "mellow kid vocal", "groovy bass", "punchy snare", "punchy kick", "shimmering hi hats", "shimmering bells melody", "plucked strings melody", "wide keys melody", "happy", "fun", "joyful"] | ["Music for children"] | 4 | 70 | 80 | 0 | 0 | ["/m/05fw6t"] | |
ca-rGWC4xPc | The low quality recording features a pop song played on playback while a male vocalist is mumbling over it. The song consists of a groovy bass, shimmering hi hats, punchy kick and snare hits, mellow bell melody, and flat repetitive female vocals singing over it. The recording is noisy, which is very audible at the very end of the loop where there is a finger licking sound. It still sounds happy and fun. | ["low quality", "pop", "noisy", "male vocal mumbling", "groovy bass", "shimmering hi hats", "punchy kick", "punchy snare", "mellow bells melody", "happy", "fun", "finger licking sound", "flat repetitive female vocal"] | ["Guitar", "Music", "Ukulele", "Inside, small room"] | 4 | 30 | 40 | 0 | 1 | ["/m/0342h", "/m/04rlf", "/m/07xzm", "/t/dd00125"] | |
oh5XmtSAOuM | The low quality recording features a blues song that consists of throaty male vocals, alongside harmonizing male vocals, singing over electric guitar melody, brass melody, shimmering hi hats, punchy snare and kick hits and walking double bass. It is a bit noisy and it sounds funky, groovy, happy, fun and vintage - like something you would want to dance to. | ["low quality", "noisy", "brass melody", "electric guitar melody", "shimmering hi hats", "punchy snare", "punchy kick", "throaty male vocal", "walking double bass", "groovy", "funky", "harmonizing background male vocals", "blues", "vintage", "happy", "fun"] | ["Music", "Rattle"] | 4 | 30 | 40 | 1 | 1 | ["/m/04rlf", "/m/07qn4z3"] | |
zGBKakEGSyc | The low quality recording features a pop song that consists passionate female vocal, alongside wide harmonizing female vocals, singing over hypnotic synth lead melody, mellow piano chords, punchy snare, bouncy syncopated snare hits, punchy kick hits, groovy bass, staccato violin melody, wide toms roll and shimmering hi hats. It sounds happy, fun and uplifting - like something you would hear on a radio. | ["low quality", "passionate female vocal", "wide harmonizing female vocals", "pop", "hypnotic synth lead melody", "punchy snare", "bouncy snare", "punchy kick", "groovy bass", "mellow piano chords", "staccato violin melody", "shimmering hi hats", "wide toms roll", "happy", "fun", "uplifting"] | ["Music", "Harmonic"] | 4 | 30 | 40 | 1 | 1 | ["/m/04rlf", "/m/0b9m1"] |
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 );