musiccaps
14 rows where audioset_names contains "Vocal music" and author_id = 4
This data as json, CSV (advanced)
Suggested facets: start_s, audioset_ids, audioset_ids (array)
ytid ▼ | url | caption | aspect_list | audioset_names | author_id | start_s | end_s | is_balanced_subset | is_audioset_eval | audioset_ids |
---|---|---|---|---|---|---|---|---|---|---|
46WpyRUqwXU | The low quality recording features a pop song that contains a passionate female vocal, alongside wide harmonizing male vocals, singing over wide brass melody, electric guitar chords, straight piano melody, punchy snare and smooth bass guitar. It sounds groovy, addictive and passionate. | ["low quality", "pop", "wide harmonizing male vocals", "wide shimmering hi hats", "wide brass melody", "electric guitar chords", "straight piano melody", "reverberant passionate female vocal", "punchy snare", "smooth bass guitar", "groovy", "addictive", "passionate"] | ["Music", "Vocal music"] | 4 | 30 | 40 | 0 | 0 | ["/m/04rlf", "/m/0y4f8"] | |
9ziKfjHWqZ0 | The low quality recording features a gospel song that consists of harmonizing mixed choir singing. The recording is noisy, in mono and it sounds passionate, joyful, soulful and reverberant. | ["low quality", "gospel", "harmonizing mixed choir", "reverberant", "noisy", "mono", "joyful", "passionate", "soulful"] | ["Singing", "Gospel music", "Christian music", "Choir", "Vocal music", "A capella"] | 4 | 40 | 50 | 0 | 0 | ["/m/015lz1", "/m/016cjb", "/m/02mscn", "/m/0l14jd", "/m/0y4f8", "/m/0z9c"] | |
JOhK7oq9KtU | The low quality recording features a live performance of an indie song and it contains passionate female vocal singing over arpeggiated electric guitar melody and shimmering shakers. It is a bit noisy, there are some crowd noises and it sounds passionate, emotional and like an intro section of the song. | ["low quality", "crowd noises", "noisy", "indie", "live performance", "passionate female vocal", "shimmering shakers", "arpeggiated electric guitar melody", "emotional", "passionate", "intro"] | ["Music", "Vocal music", "Tender music"] | 4 | 30 | 40 | 0 | 1 | ["/m/04rlf", "/m/0y4f8", "/t/dd00034"] | |
OHZZuO2vY50 | The low quality recording features a shimmering cymbals in the left channel, alongside suspenseful didgeridoo melody, followed by tinny wooden percussion and violin melody in the right channel of the stereo image. The recording is noisy and due to the unconventional panning, the stereo image is unbalanced.Overall it sounds suspenseful and intense. | ["low quality", "noisy", "unbalanced stereo", "shimmering cymbals", "suspenseful didgeridoo", "tinny wooden percussions", "intense", "suspenseful", "tinny violin melody"] | ["Music", "Vocal music"] | 4 | 30 | 40 | 0 | 0 | ["/m/04rlf", "/m/0y4f8"] | |
QtjMlA_7dds | The low quality recording features a live performance of an indie song and it features a passionate male vocal singing over acoustic rhythm guitar and soft double bass, There are laughing and crowd chattering noises in the background. It sounds emotional and sad, even though the recording is a bit noisy. | ["low quality", "indie", "live performance", "noisy", "passionate male vocal", "acoustic rhythm guitar", "soft double bass", "crowd chattering", "laughing", "passionate", "emotional", "sad"] | ["Country", "Flamenco", "Music", "Bluegrass", "Vocal music"] | 4 | 30 | 40 | 0 | 1 | ["/m/01lyv", "/m/0326g", "/m/04rlf", "/m/0gg8l", "/m/0y4f8"] | |
Wp5AiCmbQjA | The low quality recording features an acapella cover of a R&B song that consists of flat female vocal singing over hand tapping sounds and snaps. The recording is mono and noisy, as it was probably recorded with a phone. | ["low quality", "mono", "noisy", "flat female vocal", "hand tapping sounds", "snaps", "r&b", "cover", "acapella"] | ["Finger snapping", "Vocal music"] | 4 | 70 | 80 | 0 | 0 | ["/m/025_jnm", "/m/0y4f8"] | |
X28GWrn9LlI | The low quality recording features a live performance that consists of a flat female vocal singing over electric rhythm guitar melody. It sounds passionate, reverberant and emotional. The recording is noisy and in mono, as it was probably recorded with a phone. | ["low quality", "live performance", "flat female vocal", "electric rhythm guitar melody", "passionate", "reverberant", "emotional", "noisy", "mono"] | ["Singing", "Music", "Vocal music"] | 4 | 110 | 120 | 0 | 0 | ["/m/015lz1", "/m/04rlf", "/m/0y4f8"] | |
XWhmLbnrtd0 | The low quality recording features a cover of a pop song and it consists of harmonizing male vocals and loud shoe tapping that serves as a rhythm. The recording is in mono and very noisy, as it was probably recorded with a phone. It sounds passionate and energetic - even without the instruments. | ["low quality", "loud shoe tapping", "harmonizing male vocals", "pop", "cover", "noisy", "mono", "passionate", "energetic"] | ["Singing", "Tap", "Choir", "Vocal music", "A capella"] | 4 | 160 | 170 | 0 | 0 | ["/m/015lz1", "/m/07qcpgn", "/m/0l14jd", "/m/0y4f8", "/m/0z9c"] | |
_78P-0zWJtg | The low quality recording features a live performance of fruity male vocal singing over funky piano melody and beat played on playback that consists of punchy snare and kick hits, shimmering hi hats and smooth bass. The crowd is also singing along, harmonizing with the lead vocal. It sounds emotional and groovy, even though the recording is noisy. | ["low quality", "folk", "fruity male vocal", "funky piano melody", "playback beat", "shimmering hi hats", "punchy snare", "punchy kick", "smooth bass", "noisy", "live performance", "harmonizing crowd vocals", "emotional", "groovy"] | ["Singing", "Gospel music", "Music", "Vocal music"] | 4 | 420 | 430 | 1 | 1 | ["/m/015lz1", "/m/016cjb", "/m/04rlf", "/m/0y4f8"] | |
gxzU5EqNL14 | The low quality recording features a live performance of a flamenco song sung by passionate male vocalists and followed by aggressive strumming of flamenco rhythm guitar. It is reverberant and noisy, as it was probably recorded with a phone, and it sounds passionate and emotional. | ["low quality", "flamenco", "flamenco rhythm guitar", "aggressive strumming", "passionate male vocal", "live performance", "reverberant", "noisy", "passionate", "emotional"] | ["Flamenco", "Music", "Vocal music"] | 4 | 30 | 40 | 1 | 1 | ["/m/0326g", "/m/04rlf", "/m/0y4f8"] | |
hM88FG1_D5Q | The low quality recording features harmonizing male vocals singing over a song played on playback, followed by a flat male vocal talking. At the end of the recording, there is a male laughter. It sounds fun and the recording is noisy. | ["low quality", "noisy", "harmonizing male vocals", "flat male vocal", "laughing", "playback", "fun"] | ["Music", "Speech", "Vocal music"] | 4 | 190 | 200 | 0 | 0 | ["/m/04rlf", "/m/09x0r", "/m/0y4f8"] | |
jcZQhxb5lyw | The low quality recording features a harmonizing female vocals singing. It sounds passionate, emotional and the recording is noisy and in mono. | ["low quality", "noisy", "mono", "harmonizing female vocals", "emotional", "passionate"] | ["Singing", "Vocal music", "A capella"] | 4 | 190 | 200 | 0 | 0 | ["/m/015lz1", "/m/0y4f8", "/m/0z9c"] | |
maeSHVZX8xc | The low quality recording features a gospel song that contains a harmonizing mixed vocals singing. The recording is a bit noisy and it sounds emotional and passionate. | ["low quality", "noisy", "gospel", "harmonizing mixed vocals", "emotional", "passionate"] | ["Singing", "Humming", "Music", "Choir", "Vocal music", "A capella"] | 4 | 60 | 70 | 0 | 0 | ["/m/015lz1", "/m/02fxyj", "/m/04rlf", "/m/0l14jd", "/m/0y4f8", "/m/0z9c"] | |
nJaezskegdc | The low quality recording features passionate female harmonizing vocals, alongside wide staccato female vocals melodies singing over some claps. It sounds passionate and joyful. | ["low quality", "passionate female harmonizing vocals", "wide staccato female vocal melody", "clapping", "passionate", "joyful"] | ["Singing", "Music", "Vocal music", "A capella"] | 4 | 20 | 30 | 0 | 0 | ["/m/015lz1", "/m/04rlf", "/m/0y4f8", "/m/0z9c"] |
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 );