musiccaps
2 rows where aspect_list contains "male voices", aspect_list contains "piano" and aspect_list contains "slow tempo"
This data as json, CSV (advanced)
aspect_list (array) 15 ✖
- male voices · 2 ✖
- piano · 2 ✖
- slow tempo · 2 ✖
- barbershop quartet 1
- bass 1
- double bass 1
- minimal instruments 1
- no percussion 1
- pop song 1
- romantic song 1
- sad melody 1
- slow jazz song 1
- synth sounds 1
- trumpets 1
- vocal harmony 1
ytid ▼ | url | caption | aspect_list | audioset_names | author_id | start_s | end_s | is_balanced_subset | is_audioset_eval | audioset_ids |
---|---|---|---|---|---|---|---|---|---|---|
-XkbErI_7EU | This slow jazz song features male voices singing the main melody in harmony. This is accompanied by percussion playing a simple beat. The double bass plays the root notes of the chords. Trumpets play a fill in harmony in between lines. A piano plays an arpeggiated chord at the end of the first line. This song has a romantic mood. This song can be played in a classic romantic movie. | ["slow jazz song", "barbershop quartet", "trumpets", "double bass", "vocal harmony", "male voices", "piano", "slow tempo", "romantic song"] | ["Brass instrument", "French horn"] | 0 | 50 | 60 | 0 | 0 | ["/m/01kcd", "/m/0319l"] | |
oynXCFZWxnI | This slow song features a male voice singing the main melody at a comfortable pitch. The tone of the voice is emotional. This is accompanied by a bass playing the root notes of the chords. After one line, a synth swell is played. A piano plays the backing chords. The mood of this song is sad. This song can be played in a sad scene in a movie. | ["pop song", "piano", "male voices", "bass", "synth sounds", "sad melody", "no percussion", "slow tempo", "minimal instruments"] | ["Echo", "Music", "Sad music"] | 0 | 30 | 40 | 0 | 0 | ["/m/01jnbd", "/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 );