musiccaps
2 rows where aspect_list contains "acoustic" and aspect_list contains "intense"
This data as json, CSV (advanced)
aspect_list (array) 21 ✖
- acoustic · 2 ✖
- intense · 2 ✖
- arpeggiated harp 1
- atmospheric synthesiser 1
- cinematic 1
- distortion 1
- enigmatic 1
- grim 1
- haunting boys vocal 1
- hollow sound 1
- instrumental 1
- lead 1
- low quality 1
- minimal 1
- mystical 1
- oud 1
- serious 1
- sinister 1
- slow tempo 1
- suspenseful strings 1
- wind instrument 1
ytid ▼ | url | caption | aspect_list | audioset_names | author_id | start_s | end_s | is_balanced_subset | is_audioset_eval | audioset_ids |
---|---|---|---|---|---|---|---|---|---|---|
I1wakVlpP6M | The low quality recording features suspenseful strings and arpeggiated harp playing in the background while haunting boy vocal songs on top of it. At one point the vocal distorts a little bit, making the recording low quality. It sounds intense and suspenseful - like something you would hear in thriller movies. | ["arpeggiated harp", "suspenseful strings", "haunting boys vocal", "low quality", "cinematic", "intense", "distortion", "acoustic"] | ["New-age music", "Music"] | 4 | 30 | 40 | 0 | 1 | ["/m/02v2lh", "/m/04rlf"] | |
XzTBNfQ7_GA | This music is instrumental. The tempo is slow with an Oud lead with atmospheric synthesiser . The music uses minimal instrumentation to emphasise on the lead instrument. The hollow sound in the background is either a synthesiser or a wind instrument. The music is intense, grim, mysterious, suspenseful, sinister and enigmatic. | ["instrumental", "slow tempo", "oud", "acoustic", "intense", "wind instrument", "hollow sound", "serious", "sinister", "grim", "atmospheric synthesiser", "minimal", "lead", "grim", "enigmatic", "mystical"] | ["Traditional music", "Music"] | 7 | 30 | 40 | 0 | 1 | ["/m/02p0sh1", "/m/04rlf"] |
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 );