musiccaps
5 rows where aspect_list contains "acoustic piano" and aspect_list contains "male voice singing"
This data as json, CSV (advanced)
aspect_list (array) 30 ✖
- acoustic piano · 5 ✖
- male voice singing · 5 ✖
- uptempo 3
- acoustic guitar 2
- e-bass 2
- pop 2
- background noises 1
- backing vocals 1
- backing voices 1
- bongos 1
- cajon 1
- cowbell 1
- digital strings 1
- e-guitar 1
- electric piano 1
- flute 1
- funk/r&b/jazz 1
- high register 1
- horn 1
- keyboard 1
- maracas 1
- medium tempo 1
- medium to uptempo 1
- mid range 1
- mid-range voice 1
- r&b/soul 1
- salsa 1
- sensitive 1
- sensual 1
- tambourine 1
ytid ▼ | url | caption | aspect_list | audioset_names | author_id | start_s | end_s | is_balanced_subset | is_audioset_eval | audioset_ids |
---|---|---|---|---|---|---|---|---|---|---|
31DNFoW3NAw | A keyboard is playing chords with a string sound along with something that sounds like a cembalo or another keyboard playing chords and a melody in the mid to higher register. A male voice is singing in an upper key sounding soulful and sensitive. This song may be playing for a sensual music video. | ["r&b/soul", "acoustic piano", "digital strings", "keyboard", "e-bass", "male voice singing", "high register", "sensual", "medium tempo"] | ["Blues", "Music", "Independent music", "Tender music"] | 6 | 30 | 40 | 0 | 0 | ["/m/0155w", "/m/04rlf", "/m/05rwpb", "/t/dd00034"] | |
8oUI02eK3SM | This song contains a male voice singing in the midrange while backing voices are supported with vocals in the higher register. Someone is playing a complex jazzlike groove on the drums. An e-guitar is playing a loud arpeggio melody panned to the right side of the speakers along with an e-bass. This song may be playing live at a jazz festival. | ["funk/r&b/jazz", "acoustic piano", "e-bass", "e-guitar", "male voice singing", "backing voices", "uptempo"] | ["Blues", "Music"] | 6 | 30 | 40 | 0 | 0 | ["/m/0155w", "/m/04rlf"] | |
QDTCAxyXt80 | This audio contains someone playing an acoustic piano along with an acoustic guitar strumming chords. Someone is playing a cajon with a fast paced groove and a tambourine. A horn takes the main melody in the midrange along with a male voice singing in a higher key. This song may be playing on the streets performed by buskers. | ["pop", "acoustic piano", "cajon", "horn", "acoustic guitar", "male voice singing", "tambourine", "uptempo"] | ["Brass instrument", "French horn"] | 6 | 140 | 150 | 0 | 0 | ["/m/01kcd", "/m/0319l"] | |
gsEk62Efbh4 | This salsa song contains percussive elements as maracas,cowbell and bongos creating a typical salsa rhythm spread across both sides of the speakers. An e-bass is playing a complex walking bassline. An acoustic piano is playing a melody up and down the scales along with backing vocals singing in harmony as a countermelody to the male lead voice singing in the midrange. This song may be playing in a latin bar. | ["salsa", "cowbell", "bongos", "maracas", "acoustic piano", "backing vocals", "male voice singing", "mid range", "uptempo"] | ["Music", "Music of Latin America", "Salsa music"] | 6 | 140 | 150 | 0 | 0 | ["/m/04rlf", "/m/0g293", "/m/0ln16"] | |
lmrzR9cSMRY | An acoustic piano is playing a melody along with a flute-sound and an acoustic guitar picking two notes repeatedly. Then the song breaks softly into a new part as the acoustic guitar and piano are fading out. In the background you can hear some insects chirping. Now an electric piano sound is playing a melody along with a male voice singing. His voice sounds sensitive. This song may be playing for a movie scene. | ["pop", "acoustic piano", "flute", "acoustic guitar", "electric piano", "male voice singing", "mid-range voice", "sensitive", "medium to uptempo", "background noises"] | ["Singing", "Music", "Sad music"] | 6 | 20 | 30 | 0 | 1 | ["/m/015lz1", "/m/04rlf", "/t/dd00033"] |
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 );