musiccaps
2 rows where aspect_list contains "dark" and aspect_list contains "sad"
This data as json, CSV (advanced)
aspect_list (array) 19 ✖
- dark · 2 ✖
- sad · 2 ✖
- slow tempo 2
- ambient 1
- atmospheric synthesiser 1
- cinematic 1
- depressed 1
- digital drums 1
- dramatic 1
- gloomy 1
- grim 1
- instrumental 1
- intense 1
- intense electric guitar 1
- orchestral 1
- paper wrapper 1
- sombre 1
- sound of metal clanging 1
- string section 1
ytid ▼ | url | caption | aspect_list | audioset_names | author_id | start_s | end_s | is_balanced_subset | is_audioset_eval | audioset_ids |
---|---|---|---|---|---|---|---|---|---|---|
8MF6nFj02sM | This audio contains a string section playing a sad/melancholic piece. A violin/viola is playing the lead melody while celli and upright basses being played with a bow are supporting the melody with chords. The lead melody is panned to the right side of the speakers. This song may be playing in a sad and dramatic movie scene. | ["cinematic", "orchestral", "sad", "dramatic", "dark", "string section", "slow tempo"] | ["Cello", "Double bass", "Violin, fiddle", "Bowed string instrument"] | 6 | 80 | 90 | 0 | 0 | ["/m/01xqw", "/m/02fsn", "/m/07y_7", "/m/0l14_3"] | |
negr4U79PUE | This music is a grim instrumental. The tempo is slow with a sombre electric guitar melody with atmospheric synthesiser and mood digital drums. The music is serious, intense, melancholy, pensive, cheerless, sinister and dark. | ["instrumental", "slow tempo", "intense electric guitar", "atmospheric synthesiser", "digital drums", "ambient", "dark", "sombre", "grim", "intense", "depressed", "sad", "sound of metal clanging", "paper wrapper", "gloomy"] | ["Bass guitar", "Music", "Harmonic"] | 7 | 270 | 280 | 0 | 1 | ["/m/018vs", "/m/04rlf", "/m/0b9m1"] |
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 );