musiccaps
2 rows where aspect_list contains "upbeat" and audioset_ids contains "/m/0z9c"
This data as json, CSV (advanced)
ytid ▼ | url | caption | aspect_list | audioset_names | author_id | start_s | end_s | is_balanced_subset | is_audioset_eval | audioset_ids |
---|---|---|---|---|---|---|---|---|---|---|
YErpnsceZw8 | This is a live performance by a female vocal quartet. They harmonise their voices and sing in a vibrant and cheerful way. They sing in French. Later, we hear two violins playing in sync as well as an accordion. The recording quality of the audio is poor. | ["live recording", "live performance", "female singing quarter", "poor audio quality", "violins", "accordion", "cheerful", "happy", "upbeat", "harmonies", "vintage european"] | ["Music", "Musical instrument", "Violin, fiddle", "Classical music", "Bowed string instrument", "A capella"] | 3 | 50 | 60 | 0 | 0 | ["/m/04rlf", "/m/04szw", "/m/07y_7", "/m/0ggq0m", "/m/0l14_3", "/m/0z9c"] | |
nYO8n62Piys | This is an acapella version of a swing jazz music piece that was performed with various layers of a vocal synth software called vocaloid. Three different harmonies can be heard from this vocal synth. There is a bass guitar playing a walking bass line in the background. The rhythmic background consists of finger clicks and a swing jazz beat performed with brushes on a snare drum. The atmosphere is cheerful but eerie. This piece could be used in the soundtrack of an arcade/analog type video game. It could also work well in the soundtrack of an anime. | ["acapella", "vocaloid", "swing jazz", "female synth vocal", "harmony singing", "bass guitar", "finger click", "snare drum", "brush", "eerie", "cheerful", "upbeat"] | ["Music", "Vocal music", "A capella", "Happy music"] | 9 | 70 | 80 | 0 | 0 | ["/m/04rlf", "/m/0y4f8", "/m/0z9c", "/t/dd00031"] |
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 );