musiccaps
2 rows where aspect_list contains "male singer" and aspect_list contains "mid-range"
This data as json, CSV (advanced)
aspect_list (array) 16 ✖
- male singer · 2 ✖
- mid-range · 2 ✖
- acoustic drums 1
- acoustic kick 1
- amateur recording 1
- arpeggios 1
- brass section 1
- e-bass 1
- e-guitar 1
- keyboard 1
- medium tempo 1
- rock&roll 1
- synthesizer sounds 1
- synthpop 1
- uplifting mood 1
- uptempo 1
ytid ▼ | url | caption | aspect_list | audioset_names | author_id | start_s | end_s | is_balanced_subset | is_audioset_eval | audioset_ids |
---|---|---|---|---|---|---|---|---|---|---|
ktw_J6ZW0MM | A male voice is singing with reverb and delay in his voice. An acoustic drum is playing a faster groove on the piano, a tambourine can be heard. An electric bass is playing repeating notes without a lot of changes. A brass section is repeating a theme while keyboards and a guitar are playing along. This song may be playing live in-between an entertainment-show. | ["rock&roll", "acoustic drums", "e-bass", "brass section", "e-guitar", "keyboard", "male singer", "mid-range", "uptempo", "uplifting mood", "amateur recording"] | ["Singing", "Country", "Sampler", "Folk music", "Music", "Pop music", "Song"] | 6 | 30 | 40 | 1 | 1 | ["/m/015lz1", "/m/01lyv", "/m/01v1d8", "/m/02w4v", "/m/04rlf", "/m/064t9", "/m/074ft"] | |
nc6h6rC3wdk | A male voice is singing with a mid-melody. Different synthesizer sounds are playing arpeggios being used as bassline and other sounds as melody in the mid range and higher register. An acoustic sounding kick is playing on every beat. This song may be playing in a synth retro movie. | ["synthpop", "male singer", "mid-range", "synthesizer sounds", "arpeggios", "acoustic kick", "medium tempo"] | ["Music of Africa", "Music", "Tender music"] | 6 | 30 | 40 | 1 | 1 | ["/m/0164x2", "/m/04rlf", "/t/dd00034"] |
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 );