musiccaps
171 rows where audioset_names contains "Speech" sorted by aspect_list
This data as json, CSV (advanced)
audioset_names (array) >30 ✖
- Speech · 71 ✖
- Music 69
- Musical instrument 21
- Plucked string instrument 17
- Guitar 14
- Acoustic guitar 6
- Electronic tuner 5
- Music for children 5
- Scary music 5
- Strum 5
- Didgeridoo 4
- Electronic music 4
- Inside, small room 4
- Middle Eastern music 4
- Bass guitar 3
- Independent music 3
- New-age music 3
- Orchestra 3
- Scratching (performance technique) 3
- Singing 3
- Blues 2
- Dial tone 2
- Happy music 2
- Hip hop music 2
- Mandolin 2
- Music of Latin America 2
- Opera 2
- Ska 2
- Tender music 2
- Traditional music 2
- …
ytid | url | caption | aspect_list ▼ | audioset_names | author_id | start_s | end_s | is_balanced_subset | is_audioset_eval | audioset_ids |
---|---|---|---|---|---|---|---|---|---|---|
S9-i_pqoUCw | The low quality recording features an aggressive male vocal talking over synth pad chords, sustained, mellow female vocals and reverberant percussion. It sounds suspenseful and intense. The recording is noisy and in mono. | ["low quality", "aggressive male vocal", "synth pad chords", "mellow sustained female vocals", "suspenseful", "intense", "noisy", "mono", "reverberant percussions"] | ["Music", "Speech", "Scary music"] | 4 | 70 | 80 | 0 | 0 | ["/m/04rlf", "/m/09x0r", "/t/dd00037"] | |
yGXohnxCLCA | The low quality recording features an ambient song that contains a flat male vocal softly talking over mellow strings and soft sea waves sounds. It sounds relaxing and calming - like something you would hear at a yoga session. | ["low quality", "ambient", "relaxing", "flat male vocal", "mellow strings", "soft sea waves", "relaxing", "calming"] | ["Carnatic music", "New-age music", "Music", "Speech"] | 4 | 60 | 70 | 0 | 0 | ["/m/015vgc", "/m/02v2lh", "/m/04rlf", "/m/09x0r"] | |
DW3z-ByrfWY | The low quality recording features a flat male vocal talking over digital synth melody, followed by stuttering buzzy noise. The recording is in mono and very noisy. | ["low quality", "buzzy", "noisy", "mono", "stuttering", "digital synth melody", "flat male vocal"] | ["Didgeridoo", "Music", "Speech"] | 4 | 380 | 390 | 0 | 0 | ["/m/02bxd", "/m/04rlf", "/m/09x0r"] | |
QT1SjY9mQxc | The low quality recording features a classical song that consists of a suspenseful brass melody, sustained strings and dynamic low percussion roll, after which there is an alarm sound. It sounds suspenseful, dramatic and intense. | ["low quality", "classical", "alarm sound", "suspenseful brass melody", "sustained strings", "dynamic low percussion roll", "suspenseful", "dramatic", "intense"] | ["Music", "Speech", "Scary music"] | 4 | 20 | 30 | 0 | 0 | ["/m/04rlf", "/m/09x0r", "/t/dd00037"] | |
YK1AEw1kf28 | The low quality recording features a classical song that consists of passionate male opera vocal singing over wide strings melody, wide brass melody and woodwinds melody, over which there is a fruity male vocal talking. It sounds passionate, epic and powerful - like something for commercial. | ["low quality", "classical", "fruity male vocal", "passionate male opera vocal", "wide strings melody", "wide brass melody", "woodwinds melody", "passionate", "epic", "powerful", "commercial"] | ["Music", "Opera", "Orchestra", "Speech", "Classical music"] | 4 | 60 | 70 | 0 | 0 | ["/m/04rlf", "/m/05lls", "/m/05pd6", "/m/09x0r", "/m/0ggq0m"] | |
NZ2kFIaW05k | The low quality recording features an electric guitar melody played over a playback that consists of groovy bass, punchy snare and shimmering cymbals. At the end of the loop, there is a flat male vocal talking. It sounds groovy, fun and the recording is noisy and slightly distorted. | ["low quality", "electric guitar melody", "groovy bass", "punchy snare", "shimmering cymbals", "groovy", "fun", "happy", "flat male vocal", "distorted", "noisy"] | ["Blues", "Bass guitar", "Guitar", "Music", "Musical instrument", "Rhythm and blues", "Speech", "Harmonic", "Plucked string instrument"] | 4 | 450 | 460 | 0 | 0 | ["/m/0155w", "/m/018vs", "/m/0342h", "/m/04rlf", "/m/04szw", "/m/06j6l", "/m/09x0r", "/m/0b9m1", "/m/0fx80y"] | |
ia6-da2KdI0 | The low quality recording features an electro song playing in the background, while there is a muffled male vocal being interviewed. It sounds muffled and loud. The recording is noisy and in mono. | ["low quality", "electro", "muffled male vocal", "muffled", "loud", "noisy", "mono", "interview"] | ["Music", "Speech", "Music of Latin America"] | 4 | 30 | 40 | 0 | 0 | ["/m/04rlf", "/m/09x0r", "/m/0g293"] | |
4LZSSya3ZZQ | The low quality recording features a flat male vocal talking over an acoustic guitar solo melody playing in the background. It sounds like a tutorial and the recording is in mono. | ["low quality", "flat male vocal", "acoustic guitar solo melody", "tutorial", "mono"] | ["Bass guitar", "Guitar", "Music", "Musical instrument", "Strum", "Speech", "Plucked string instrument"] | 4 | 30 | 40 | 0 | 0 | ["/m/018vs", "/m/0342h", "/m/04rlf", "/m/04szw", "/m/07s0s5r", "/m/09x0r", "/m/0fx80y"] | |
0K-zyeLuKho | The low quality recording features a guitar tutorial that consists of a flat male vocal talking and counting the rhythm over an arpeggiated acoustic guitar melody. The recording is mono and noisy. | ["low quality", "flat male vocal", "arpeggiated acoustic guitar melody", "tutorial", "noisy", "mono"] | ["Guitar", "Music", "Musical instrument", "Strum", "Speech", "Plucked string instrument"] | 4 | 30 | 40 | 0 | 0 | ["/m/0342h", "/m/04rlf", "/m/04szw", "/m/07s0s5r", "/m/09x0r", "/m/0fx80y"] | |
bciw4Tqp6h4 | The low quality recording features a flat male talking over background music that consists of a saxophone melody played over shimmering hi hats, snappy rimshots, groovy piano melody, mellow bells melody and simple bass. It sounds happy, fun and easygoing - like something kids would listen to. | ["low quality", "flat male vocal", "background music", "saxophone melody", "snappy rimshots", "shimmering hi hats", "groovy piano melody", "mellow bells melody", "simple bass", "happy", "fun", "easygoing"] | ["Music", "Music for children", "Plop", "Speech"] | 4 | 80 | 90 | 0 | 0 | ["/m/04rlf", "/m/05fw6t", "/m/07qyrcz", "/m/09x0r"] | |
Uc_1PzGr5xw | The low quality recording features a tutorial where in the beginning there is a banjo guitar melody over which a passionate male vocalist is singing. In the second half of the loop, a flat male vocal is talking. The recording is noisy, in mono and it sounds passionate and emotional. | ["low quality", "flat male vocal", "banjo guitar melody", "passionate male vocal", "passionate", "emotional", "tutorial", "noisy", "mono"] | ["Banjo", "Music", "Musical instrument", "Speech", "Plucked string instrument"] | 4 | 10 | 20 | 0 | 0 | ["/m/018j2", "/m/04rlf", "/m/04szw", "/m/09x0r", "/m/0fx80y"] | |
zNAHQYshxZk | The low quality recording features a flat male vocal talking, after which there is a scratching vinyl sound - sort of like a tutorial on how to scratch a vinyl. The recording is mono and noisy. | ["low quality", "flat male vocal", "dj vinyl scratching", "noisy", "mono", "tutorial"] | ["Scratching (performance technique)", "Electronic music", "Music", "Speech"] | 4 | 310 | 320 | 0 | 0 | ["/m/01hgjl", "/m/02lkt", "/m/04rlf", "/m/09x0r"] | |
CKO35LsM0XI | The low quality recording features an indie rock song that consists of passionate female vocal singing over energetic drums, electric guitar solo melody and groovy bass, over which there is a flat, nasal and muffled male vocal narrating. The song sounds energetic and uplifting. | ["low quality", "flat male vocal", "indie rock", "passionate female vocal", "energetic drums", "electric guitar solo melody", "groovy bass guitar", "energetic", "uplifting", "muffled", "nasal"] | ["Music", "Independent music", "Speech"] | 4 | 30 | 40 | 0 | 0 | ["/m/04rlf", "/m/05rwpb", "/m/09x0r"] | |
4q-eGdrqiIw | The low quality recording features flat male vocals talking over rock songs playing in the background. It sounds like a documentary about music. The recording is muffled, noisy and in mono, as it was probably recorded with a phone. | ["low quality", "flat male vocals", "rock", "passionate female vocal", "mono", "noisy", "muffled", "documentary"] | ["Music", "Speech", "Exciting music"] | 4 | 30 | 40 | 0 | 0 | ["/m/04rlf", "/m/09x0r", "/t/dd00035"] | |
BN63M3_lPCQ | The low quality recording features a folk song playing in the background while the flat male vocalist is speaking. The song contains shimmering shakers, acoustic rhythm guitar, wooden percussion and harmonica melody. The song sounds happy, joyful and soulful. | ["low quality", "folk", "flat male vocal", "shimmering shakers", "acoustic rhythm guitar", "wooden percussions", "harmonica melody", "happy", "joyful", "soulful"] | ["Traditional music", "Music", "Speech"] | 4 | 170 | 180 | 0 | 0 | ["/m/02p0sh1", "/m/04rlf", "/m/09x0r"] | |
zWEznZ40k2Q | The low quality recording features a kids song that features a shimmering bell melody, mellow cowbell and girl vocals singing over it. The recording is in mono and noisy - the audio is really crackling. It sounds fun and happy, like something that kids would listen to. | ["low quality", "girls vocal", "shimmering bells", "kids song", "mellow cowbell", "crackling sound", "noisy", "mono", "fun", "happy"] | ["Music", "Music for children", "Chink, clink", "Speech"] | 4 | 30 | 40 | 0 | 0 | ["/m/04rlf", "/m/05fw6t", "/m/07q7njn", "/m/09x0r"] | |
4Gow6qZcNZI | The low quality recording features a tutorial where a flat male vocalist is talking, after which a groovy bass guitar is playing. The recording is noisy and in mono. | ["low quality", "groovy bass guitar", "flat male vocal", "noisy", "mono", "tutorial"] | ["Bass guitar", "Guitar", "Music", "Musical instrument", "Speech", "Electronic tuner", "Plucked string instrument"] | 4 | 390 | 400 | 0 | 0 | ["/m/018vs", "/m/0342h", "/m/04rlf", "/m/04szw", "/m/09x0r", "/m/0b_fwt", "/m/0fx80y"] | |
eX1Hynef5Rc | The low quality recording features a hip hop song that contains a phone dialing sound effects, alongside filtered female vocal talking as the user is busy on the phone. In the second half of the loop, there are punchy kicks and snare hits playing. It sounds groovy and energetic overall. | ["low quality", "hip hop", "noisy", "mono", "punchy kick", "punchy snare", "phone dialing sound effects", "filtered female vocal", "user busy sound effect", "energetic", "groovy"] | ["Dial tone", "Music", "Speech", "Hip hop music"] | 4 | 0 | 10 | 0 | 0 | ["/m/015jpf", "/m/04rlf", "/m/09x0r", "/m/0glt670"] | |
ChqJYrmQIN4 | The low quality recording features a live performance of a folk song that consists of an accordion melody playing over groovy bass, shimmering hi hats, punchy snare and electric guitar melody. There are crowd chattering noises in the background. It sounds passionate and groovy. | ["low quality", "live performance", "crowd chattering", "folk", "groovy bass", "accordion melody", "electric guitar melody", "shimmering hi hats", "punchy snare", "passionate", "groovy"] | ["Singing", "Traditional music", "Music", "Musical instrument", "Orchestra", "Speech", "Music of Latin America", "Accordion"] | 4 | 50 | 60 | 0 | 0 | ["/m/015lz1", "/m/02p0sh1", "/m/04rlf", "/m/04szw", "/m/05pd6", "/m/09x0r", "/m/0g293", "/m/0mkg"] | |
4QJktFv916o | The low quality recording features a metal song that consists of female opera vocal singing over double pedal kick, punchy snare, energetic cymbals, wide electric guitar melody and groovy bass guitar. It sounds aggressive, energetic and upbeat. | ["low quality", "metal", "punchy snare", "double pedal kick", "female opera vocal", "wide electric guitar melody", "groovy bass", "energetic cymbals", "aggressive", "upbeat", "energetic"] | ["Music", "Speech", "Angry music"] | 4 | 170 | 180 | 0 | 0 | ["/m/04rlf", "/m/09x0r", "/t/dd00036"] | |
GcOOmVSM8Uw | The low quality recording features, in the first half of the loop, a mono and noisy recording of a punk live performance with some crowd cheering noises. It sounds energetic and the recording suddenly fades out, transitioning into the second part of the loop which features a side synth pad that sounds suspenseful. | ["low quality", "mono", "noisy", "crowd cheering", "fade out", "wide synth pad", "suspenseful", "energetic", "punk", "live performance"] | ["Whale vocalization", "Music", "Rock music", "Speech"] | 4 | 110 | 120 | 0 | 0 | ["/m/032n05", "/m/04rlf", "/m/06by7", "/m/09x0r"] | |
GW6pti04qIo | The low quality recording features a tutorial where a flat male vocal is talking, followed by acoustic rhythm guitar chords. The recording is mono and noisy. | ["low quality", "mono", "noisy", "flat male vocal", "acoustic rhythm guitar chords", "tutorial"] | ["Guitar", "Acoustic guitar", "Music", "Musical instrument", "Speech", "Electronic tuner", "Plucked string instrument"] | 4 | 130 | 140 | 0 | 0 | ["/m/0342h", "/m/042v_gx", "/m/04rlf", "/m/04szw", "/m/09x0r", "/m/0b_fwt", "/m/0fx80y"] | |
51bsCRv6kI0 | The low quality recording features a flat male vocal talking, after which a jazz live performance recording starts playing. It sounds like an interview and the recording is mono and noisy. | ["low quality", "mono", "noisy", "flat male vocal", "jazz", "interview"] | ["Music", "Middle Eastern music", "Speech"] | 4 | 30 | 40 | 0 | 0 | ["/m/04rlf", "/m/06j64v", "/m/09x0r"] | |
ATDi-irUEWc | The low quality recording features a muffled male vocal speaking, right after the didgeridoo tone. The recording is noisy and in mono. | ["low quality", "muffled male vocal", "didgeridoo tone", "noisy", "mono"] | ["Didgeridoo", "Speech"] | 4 | 30 | 40 | 0 | 0 | ["/m/02bxd", "/m/09x0r"] | |
ieEPKa3HiGo | The low quality recording features a tutorial where a flat male vocalist is talking, after which he plays an arpeggiated acoustic guitar melody. The recording is extremely noisy. | ["low quality", "noisy", "arpeggiated acoustic guitar", "flat male vocal", "tutorial"] | ["Music", "Steel guitar, slide guitar", "Speech", "Plucked string instrument"] | 4 | 30 | 40 | 0 | 0 | ["/m/04rlf", "/m/06w87", "/m/09x0r", "/m/0fx80y"] | |
yWU0zNEy2_I | The low quality recording features a didgeridoo melody playing outdoors. There are also some crowd chattering, water fountains and birds chirping sounds. The recording is noisy, as it was probably recorded with a phone. | ["low quality", "noisy", "birds chirping", "crowd talking", "water fountain sounds", "didgeridoo melody"] | ["Didgeridoo", "Music", "Musical instrument", "Speech"] | 4 | 90 | 100 | 0 | 0 | ["/m/02bxd", "/m/04rlf", "/m/04szw", "/m/09x0r"] | |
sUjAb0SfppQ | The low quality recording features a tutorial where a flat male vocalist talks, followed by echoing, uptempo electric guitar melody. The recording is really noisy and the actual sound is leaning towards the right channel - which makes the stereo image unbalanced. | ["low quality", "noisy", "flat male vocal", "tutorial", "echoing uptempo electric guitar melody", "unbalanced stereo"] | ["Tapping (guitar technique)", "Guitar", "Acoustic guitar", "Music", "Musical instrument", "Speech", "Plucked string instrument"] | 4 | 430 | 440 | 0 | 0 | ["/m/01glhc", "/m/0342h", "/m/042v_gx", "/m/04rlf", "/m/04szw", "/m/09x0r", "/m/0fx80y"] | |
hM88FG1_D5Q | The low quality recording features harmonizing male vocals singing over a song played on playback, followed by a flat male vocal talking. At the end of the recording, there is a male laughter. It sounds fun and the recording is noisy. | ["low quality", "noisy", "harmonizing male vocals", "flat male vocal", "laughing", "playback", "fun"] | ["Music", "Speech", "Vocal music"] | 4 | 190 | 200 | 0 | 0 | ["/m/04rlf", "/m/09x0r", "/m/0y4f8"] | |
bBy0NCoCEHc | The low quality recording features a live performance of a traditional song and it consists of a bell melody, followed by wooden percussion. There are some flat male vocals talking, after which there are harmonizing male vocals singing over it. It sounds passionate, even though the recording is noisy. | ["low quality", "noisy", "live performance", "traditional", "bells melody", "wooden percussions", "flat mel vocal", "harmonizing male vocals", "passionate"] | ["Folk music", "Music", "Rattle (instrument)", "Speech"] | 4 | 540 | 550 | 0 | 0 | ["/m/02w4v", "/m/04rlf", "/m/05r5wn", "/m/09x0r"] | |
oSDZZHN77PI | The low quality recording features a tutorial where a flat male vocalist is talking after a clean electric guitar chord is played. Judging by the short snippet at the end of the loop, there is a guitar pedal effect that changes the preset of the guitar sound. The recording is noisy and in mono. | ["low quality", "noisy", "mono", "clean electric guitar chords", "flat male vocal", "guitar pedal effect", "tutorial"] | ["Guitar", "Music", "Musical instrument", "Speech", "Electronic tuner", "Plucked string instrument", "Inside, small room"] | 4 | 80 | 90 | 0 | 0 | ["/m/0342h", "/m/04rlf", "/m/04szw", "/m/09x0r", "/m/0b_fwt", "/m/0fx80y", "/t/dd00125"] | |
8UhdwnsckJ8 | The low quality recording features a tutorial that contains a flat male vocal talking over acoustic guitar strummed chords. The recording is noisy and in mono. | ["low quality", "noisy", "mono", "flat male vocal", "acoustic guitar strummed chords", "tutorial"] | ["Guitar", "Acoustic guitar", "Music", "Musical instrument", "Strum", "Speech", "Plucked string instrument"] | 4 | 30 | 40 | 0 | 0 | ["/m/0342h", "/m/042v_gx", "/m/04rlf", "/m/04szw", "/m/07s0s5r", "/m/09x0r", "/m/0fx80y"] | |
bPYbRSI16IY | The low quality recording features a filter modulated synth bass, after which there is a short snippet of flat male vocals talking over sea waves sounds in the background. The recording is mono and noisy. | ["low quality", "noisy", "mono", "flat male vocal", "sea waves sound", "filter modulated acid synth bass"] | ["Didgeridoo", "Music", "Speech"] | 4 | 0 | 10 | 0 | 0 | ["/m/02bxd", "/m/04rlf", "/m/09x0r"] | |
q7sK_xrJz-k | The low quality recording features a flat male vocal talking over electric guitar melody and sustained strings, with some metallic impact sound and stuttering vocal sound effect. It sounds funny and the recording is noisy and in mono. | ["low quality", "noisy", "mono", "flat male vocal", "stuttering vocal sound effect", "sustained strings", "electric guitar melody", "metallic impact", "funny"] | ["Bell", "Music", "Speech"] | 4 | 310 | 320 | 0 | 0 | ["/m/0395lw", "/m/04rlf", "/m/09x0r"] | |
US3ZL2zhXgI | The low quality recording features a flat male vocal talking over ukulele melody. It sounds like a tutorial and the recording is noisy and in mono. | ["low quality", "noisy", "mono", "flat male vocal", "ukulele melody", "tutorial"] | ["Guitar", "Music", "Musical instrument", "Ukulele", "Speech", "Plucked string instrument"] | 4 | 180 | 190 | 0 | 0 | ["/m/0342h", "/m/04rlf", "/m/04szw", "/m/07xzm", "/m/09x0r", "/m/0fx80y"] | |
V5HMIxuAtv8 | The low quality recording features a live performance of a harmonizing mixed choir, introduced by a fruity male vocal. There is a footstep and crowd clapping sound right after introduction. The recording is a bit noisy, in mono and it sounds passionate, emotional and soulful. | ["low quality", "noisy", "mono", "footstep sound", "fruity male vocal", "crowd clapping", "mixed harmonizing choir", "emotional", "passionate", "soulful", "live performance"] | ["Singing", "Music", "Opera", "/m/05zppz", "Speech", "Choir", "/t/dd00003"] | 4 | 30 | 40 | 0 | 0 | ["/m/015lz1", "/m/04rlf", "/m/05lls", "/m/05zppz", "/m/09x0r", "/m/0l14jd", "/t/dd00003"] | |
3QqVP0odOw4 | The low quality recording features a commercial music that consists of a funny processed male vocal, after which there is a harmonizing female vocal singing over punchy kick, brass melody, wooden percussion and echoing brass melody. It sounds addictive - like every commercial music should sound. | ["low quality", "pop", "funny processed male vocal", "brass melody", "punchy kick", "wooden percussions", "echoing brass melody", "harmonizing female vocal", "addictive", "commercial music"] | ["Music", "Middle Eastern music", "Speech"] | 4 | 260 | 270 | 0 | 0 | ["/m/04rlf", "/m/06j64v", "/m/09x0r"] | |
0khKvVDyYV4 | The low quality recording features an in-game audio recording that features an echoing female exhale sound, shimmering hi hats, claps, shimmering bells melody and groovy bass guitar. In the second half of the loop, the song changes and there is a sweet female vocal humming a melody. It sounds exciting, happy and fun. | ["low quality", "popping sounds", "echoing female exhale sound", "shimmering hi hats", "happy", "fun", "sweet female vocal", "humming", "claps", "punchy kick", "shimmering bells melody", "groovy bass guitar", "in game audio", "exciting"] | ["Music", "Speech", "Happy music"] | 4 | 240 | 250 | 0 | 0 | ["/m/04rlf", "/m/09x0r", "/t/dd00031"] | |
9ohu45KlgYA | The low quality recording features a reverberant flat male vocal singing over sustained strings melody, mellow piano melody, shimmering bells melody, shimmering hi hats and groovy bass. It sounds emotional, mellow and soft. | ["low quality", "reverberant flat male vocal", "sustained strings melody", "mellow piano melody", "shimmering bells", "shimmering hi hats", "groovy bass", "emotional", "mellow", "soft"] | ["Music", "Speech", "Tender music"] | 4 | 120 | 130 | 0 | 0 | ["/m/04rlf", "/m/09x0r", "/t/dd00034"] | |
b-Y-AjW6MJ0 | The low quality recording features a rock song that consists of a flat male vocal and flat female vocal talking, followed by punchy kick and snare hits, shimmering hi hats, energetic crash hits, wide electric guitar chords, groovy bass guitar and synth lead melody. It sounds energetic. | ["low quality", "rock", "flat female vocal", "flat male vocal", "energetic crash cymbal", "groovy bass guitar", "wide electric guitar chords", "synth lead melody", "shimmering hi hats", "punchy kick", "punchy snare", "energetic"] | ["Music", "Independent music", "Speech"] | 4 | 0 | 10 | 0 | 0 | ["/m/04rlf", "/m/05rwpb", "/m/09x0r"] | |
AJROvxlmo40 | The low quality recording features suspenseful strings chords layered with a reversed crash riser, after which there is a flat female vocal talking. It sounds suspenseful and intense. | ["low quality", "suspenseful strings chords", "phone message sound effect", "flat female vocal", "suspenseful", "intense", "reversed crash riser"] | ["Music", "Speech", "Scary music", "Inside, small room"] | 4 | 570 | 580 | 0 | 0 | ["/m/04rlf", "/m/09x0r", "/t/dd00037", "/t/dd00125"] | |
YtYjdkTK5oY | The low quality recording features a synth melody and a lot of synth sound effects, over which there is a funny boy vocal talking. The synth melody continues to play in the second part of the loop where shimmering bells, snaps layered with snappy rimshots and harmonizing kids' vocals singing over them, appear. It sounds happy, joyful and fun - like something kids would listen to. | ["low quality", "synth melody", "synth sound effects", "funny boy vocal", "harmonizing kids vocals", "shimmering bells", "snaps", "snappy rimshots", "fun", "happy", "joyful"] | ["Music", "Music for children", "Ding", "Speech", "Boing"] | 4 | 0 | 10 | 0 | 0 | ["/m/04rlf", "/m/05fw6t", "/m/07phxs1", "/m/09x0r", "/t/dd00121"] | |
mU6cfEWw5Og | The low quality recording features a flat male vocal talking, after which there is a shimmering tambourine being played. The recording is noisy and the stereo image is unbalanced, as the audio is slightly leaning towards the right channel of the stereo image. | ["low quality", "unbalanced stereo", "flat male vocal", "shimmering tambourine", "tutorial", "noisy"] | ["Music", "Musical instrument", "Tambourine", "Speech", "Percussion"] | 4 | 180 | 190 | 0 | 0 | ["/m/04rlf", "/m/04szw", "/m/07brj", "/m/09x0r", "/m/0l14md"] | |
Pn8HqUbNQAc | A male guitar player plays a guitar riff followed by an introduction of a guitar effects flanger pedal. The video has an instrumental solo of a guitar playing rhythm and no other instrumentation. The soundtrack has a poor audio quality. | ["male guitar teacher", "guitar pedal demonstration", "poor audio quality", "guitarist", "home video", "guitar player", "electric guitar solo", "youtube gear demonstration", "instrumental", "average audio quality", "amplifier", "flanger unit", "energetic", "exciting", "gadget porn"] | ["Effects unit", "Guitar", "Music", "Musical instrument", "Chorus effect", "Speech", "Plucked string instrument", "Distortion"] | 1 | 30 | 40 | 0 | 0 | ["/m/02rr_", "/m/0342h", "/m/04rlf", "/m/04szw", "/m/07m2kt", "/m/09x0r", "/m/0fx80y", "/m/0g12c5"] | |
AtJ2RXQ98kY | A male singer sings this cool melody with backup singers in vocal harmony. The tempo is medium with a groovy drumming rhythm, guitar accompaniment, piano accompaniment, percussive bass line and ambient crowd noises. The song is a modern Asian pop song. | ["male singer", "backup singers", "asian pop hits", "bleeding crowd noise", "rapping vocals", "vocal harmony", "exciting", "enthusiastic", "groovy drumming rhythm", "percussive bass line", "piano accompaniment", "guitar rhythm", "people talking ambient sounds", "energetic", "youthful", "pop hits", "aisi an pop"] | ["Blues", "Disco", "Music", "Speech"] | 1 | 30 | 40 | 0 | 0 | ["/m/0155w", "/m/026z9", "/m/04rlf", "/m/09x0r"] | |
bZJoTauRldE | A male singer sings this passionate vocal. The song is medium tempo with a groovy bass line, steady drumming rhythm and a violin playing a solo. The song is a live performance by a folk singer. The song has a bad audio quality issue. | ["male singer", "screaming", "poor audio quality", "wedding music", "live band", "arabic folk singer", "excited vocals", "medium tempo", "groovy bass line", "steady drumming rhythm", "crowd noise", "ambient street noise", "folk singer", "live audience", "live performance", "violin playing solo"] | ["Jazz", "Music", "Orchestra", "Speech"] | 1 | 0 | 10 | 0 | 0 | ["/m/03_d0", "/m/04rlf", "/m/05pd6", "/m/09x0r"] | |
B9K58KYq-Cs | This is a meditation track. There is a mellow sounding ambient synth in the background. A female voice can be heard speaking gently in the Spanish language. The general atmosphere of the track is calm. | ["meditation", "ambient synth", "female voice", "speech", "spanish", "mellow", "calm"] | ["New-age music", "Music", "Speech"] | 9 | 320 | 330 | 0 | 0 | ["/m/02v2lh", "/m/04rlf", "/m/09x0r"] | |
i70a79YhlMk | This is the live performance of a Mexican folk music piece. In the beginning, there is a female voice giving an introductory speech in the Spanish language. Then, the arpa jarocha (which is a Mexican harp) and the ukulele start playing a lively and relaxed tune. The atmosphere is vibrant. This piece could be used in the soundtrack of a Mexican soap opera during scenes of calmer temperament. | ["mexican folk music", "live performance", "female voice", "introduction", "spanish", "arpa jarocha", "ukulele", "lively", "relaxed", "joyful", "vibrant"] | ["Harp", "Music", "Mandolin", "Musical instrument", "Speech", "Bowed string instrument"] | 9 | 30 | 40 | 0 | 0 | ["/m/03m5k", "/m/04rlf", "/m/04rzd", "/m/04szw", "/m/09x0r", "/m/0l14_3"] | |
HQ9HlWProm0 | This is a clip of a tutorial where we have a male teacher playing a minor scale on a nylon string guitar. The energy of the video is calm. | ["minor scale", "acoustic guitar arpeggio", "nylon string guitar", "male speaking", "male guide", "tutorial"] | ["Flamenco", "Guitar", "Acoustic guitar", "Music", "Mandolin", "Musical instrument", "Strum", "Speech", "Plucked string instrument"] | 3 | 30 | 40 | 0 | 0 | ["/m/0326g", "/m/0342h", "/m/042v_gx", "/m/04rlf", "/m/04rzd", "/m/04szw", "/m/07s0s5r", "/m/09x0r", "/m/0fx80y"] | |
NQXQsVawPhU | This is an excerpt from a music show. There is a female voice narrating an event that took place. In the background, there is hip-hop music playing. A male vocal can be heard rapping. The melody is being played by a synth sound. There is a strong bass in the piece. The rhythm is played by the electronic drums. This piece could be used as an advertisement jingle for a sportswear or automobile company. | ["music show", "female voice", "narrating", "hip-hop music", "male vocal", "rapping", "synth", "strong bass", "electronic drums", "urban sound"] | ["Music", "Speech", "Hip hop music"] | 9 | 30 | 40 | 0 | 0 | ["/m/04rlf", "/m/09x0r", "/m/0glt670"] | |
GAoGADilmV8 | Ominous orchestral music with long held string notes, bowed string bass, electronic cymbal roll and concert bass drum. The mood is eerie. | ["ominous", "orchestral", "panned hard right", "eerie", "held strings", "bowed string bass", "electronic cymbal roll", "concert bass drum"] | ["Music", "Speech", "Scary music", "Inside, small room"] | 8 | 450 | 460 | 0 | 0 | ["/m/04rlf", "/m/09x0r", "/t/dd00037", "/t/dd00125"] | |
q87TmUmVg0Y | This is a live performance of a pop rock music piece. Two male vocals are singing melodically at the same time. There is a piano playing an upbeat melody while the bass guitar plays a simple bass line in the background. The piece has a joyful aura to it. This piece could be used in the soundtrack of a sit-com during the scenes of a character happily walking through the city. | ["pop rock", "live performance", "male vocals", "melodic singing", "piano", "bass guitar", "playful", "joyful", "upbeat"] | ["Singing", "Music", "Ska", "Speech"] | 9 | 130 | 140 | 0 | 0 | ["/m/015lz1", "/m/04rlf", "/m/06rqw", "/m/09x0r"] | |
Hij_QxDkIJI | The Pop song features an echoing synth keys melody that consists of a passionate female vocal singing over punchy kick, synth bells melody, echoing synth keys melody and shimmering hi hats. It sounds emotional and passionate. | ["pop", "echoing synth keys melody", "shimmering hi hats", "passionate female vocal", "punchy kick", "synth bells melody", "emotional", "passionate"] | ["Music", "Song", "Speech", "Soul music"] | 4 | 30 | 40 | 0 | 0 | ["/m/04rlf", "/m/074ft", "/m/09x0r", "/m/0gywn"] | |
RxBFh-zdid4 | This is a product review video. There is a male voice describing the product. In the background music, there is a very generic jingle that contains an acoustic guitar, a bass guitar, an acoustic drum beat and bells. If the track can be isolated from the piece, it could be used as an advertisement jingle. | ["product review", "male voice", "description", "background music", "jingle", "generic", "acoustic guitar", "bass guitar", "bells", "acoustic drums"] | ["Music", "Music for children", "Speech"] | 9 | 30 | 40 | 0 | 0 | ["/m/04rlf", "/m/05fw6t", "/m/09x0r"] | |
7cw7rDLcujI | This clip features quirky sounds. In the foreground, the sound of a male narrator is played. In the background, sliding whistles are played. Some other quirky sounds are played which are comedic. A random melody is played on a keyboard. The mood of this song is funny. These sounds can be played in a comedy clip. | ["quirky sounds", "cartoon whistles", "comedic sounds", "keyboard sounds", "male narration", "cartoon sounds"] | ["Music", "Music for children", "Speech"] | 0 | 30 | 40 | 0 | 0 | ["/m/04rlf", "/m/05fw6t", "/m/09x0r"] | |
vhTWW5Bx15Q | This is a radio program recording from Romania. There is a male vocal rapping Romanian while another is beatboxing. Then, the rapper starts talking in a radio announcement voice. This recording could be sampled for use in beat-making. | ["radio program", "romanian rap", "male vocal", "rapping", "talking", "beatboxing"] | ["Beatboxing", "Speech", "Vocal music"] | 9 | 140 | 150 | 0 | 0 | ["/m/02cz_7", "/m/09x0r", "/m/0y4f8"] | |
LaaC_q3QDUE | The recording contains two parts. One being a song with digital drums with a sub bass on the kick and a finger snapping sound used as a snare. A steeldrum sample is playing a repeating melody while a male voice is rapping in a higher pitch along to backing vocals creating a cheerful atmosphere. Then the song stops and you can hear mobile phones ringing. Two male voices are talking to each other. Then the recording stops with a beeping sound. This recording may be playing in a movie scene. | ["rap", "mobile phones ringing", "male voices talking", "backgroundnoises", "male voice rapping", "higher register", "medium tempo"] | ["Dial tone", "Music of Asia", "Music", "Speech"] | 6 | 90 | 100 | 0 | 0 | ["/m/015jpf", "/m/028sqc", "/m/04rlf", "/m/09x0r"] | |
2zrPFxxT1VM | This song starts with a male narrator speaking a line. This is followed by a female voice singing the main melody and each line is repeated by male and female voices. This song has a repetitive melody. This song has a call and response pattern. This is accompanied by an acoustic guitar playing chords and riffs at the end of lines. The percussion is played on a tabla. This song has a religious chant feel. This song can be played in a religious gathering. | ["religious chanting", "acoustic guitar", "tabla", "female main voice", "male and female voices", "moderate tempo", "call and response", "gospel feel", "male narrator voice"] | ["New-age music", "Music", "Middle Eastern music", "Speech", "Happy music"] | 0 | 30 | 40 | 0 | 0 | ["/m/02v2lh", "/m/04rlf", "/m/06j64v", "/m/09x0r", "/t/dd00031"] | |
1Is1xfDjZrw | A deeper male voice is talking for a moment before changing to another male voice talking about something. In the background you can hear a professional recording containing an e-bass playing single long notes along with an organ and an acoustic piano playing chords in the midrange. An acoustic drum is holding a simple beat in the background. This song may be playing in a gospel church band. | ["rockballad", "male voices talking", "background music", "acoustic drums", "e-bass", "acoustic piano", "organ", "slower tempo"] | ["Music", "Speech", "Tender music"] | 6 | 30 | 40 | 0 | 0 | ["/m/04rlf", "/m/09x0r", "/t/dd00034"] | |
T78nMdsJMmk | This is an R&B music piece from a sit-com soundtrack. Initially, there is a male voice narrating what is going on in the episode. Then the piece starts playing with a high pitched male vocal at the forefront. The melody is being played by the electric guitar and the bass guitar while the rhythmic background consists of an acoustic drum beat. The atmosphere is urban. | ["sit-com soundtrack", "male narrator", "r&b music", "male vocal", "high pitch singing", "electric guitar", "bass guitar", "acoustic drums", "groovy", "urban"] | ["Music", "Ska", "Speech"] | 9 | 170 | 180 | 0 | 0 | ["/m/04rlf", "/m/06rqw", "/m/09x0r"] | |
OoJGMj5H7Wk | This is a recording of one note being played on the guitar, followed by some string bending. There is then a dialogue between male Japanese speakers. | ["sitar", "string bend technique", "japanese dialogue", "japanese speaking", "live recording"] | ["Music", "Musical instrument", "Speech", "Plucked string instrument", "Sitar"] | 3 | 440 | 450 | 0 | 0 | ["/m/04rlf", "/m/04szw", "/m/09x0r", "/m/0fx80y", "/m/0jtg0"] | |
19Pp9QEw17U | This is the recording of a slide guitar lesson. There is a male instructor playing blues on the steel guitar while speaking and breathing over his performance at the same time. | ["slide guitar lesson", "blues", "male voice", "speaking", "breathing"] | ["Guitar", "Acoustic guitar", "Music", "Musical instrument", "Strum", "Speech", "Plucked string instrument"] | 9 | 30 | 40 | 0 | 0 | ["/m/0342h", "/m/042v_gx", "/m/04rlf", "/m/04szw", "/m/07s0s5r", "/m/09x0r", "/m/0fx80y"] | |
WvEtOYCShfM | This is an informational piece. There is a male voice narrating the details from the history of a Somali musician. In the end, we can hear briefly what the music of this musician sounded like. | ["somali music", "male voice", "narration", "music history"] | ["Music", "Middle Eastern music", "Speech"] | 9 | 60 | 70 | 0 | 0 | ["/m/04rlf", "/m/06j64v", "/m/09x0r"] | |
WT2iyJmKkc8 | The song is an instrumental followed by the DJ talking about his lessons. The tempo is medium with disc scratching, steady drumming rhythm, various clapping percussion, modulated vocal samples, and a percussive bass line. The song is an electronic dance tune. | ["song fade", "dj techniques", "dj talking", "youtube music lessons", "online tutorials", "learn music online", "turntables", "vinyls", "techno dance tune", "silence", "groovy rhythm", "clapping percussions", "steady drumming", "percussive bass line", "disc scratching tones", "screaming noise", "youtube dj lessons", "dj techniques", "online classes", "instrumental music", "modulated vocal samples"] | ["Scratching (performance technique)", "Electronic music", "Music", "Speech"] | 1 | 120 | 130 | 0 | 0 | ["/m/01hgjl", "/m/02lkt", "/m/04rlf", "/m/09x0r"] | |
T2zoWLYzEpo | This song contains female voices singing in a soul fashion along to a piano and trumpets playing a finale. An acoustic drum is playing a closing cymbal hit at the end. Then the crowd starts clapping and cheering. This song may be playing as part of a movie scene. | ["soul/r&b", "female voices singing", "acoustic piano", "acoustic drums", "trumpets", "crowd cheering/clapping"] | ["Music", "Pop music", "Zing", "Speech"] | 6 | 310 | 320 | 0 | 0 | ["/m/04rlf", "/m/064t9", "/m/07p78v5", "/m/09x0r"] | |
6YXjJ6ABnZU | A male singer sings this rapping vocals with a backup singer. The song is medium tempo with a groovy drum rhythm, disc scratching sounds, strong bass line and string accompaniment. The song is groovy and has a dance rhythm. The song audio quality is poor. | ["techno pop music", "male vocals", "rapping vocals", "dance party", "all night party", "discotheque", "dance floor", "dance rhythm", "energetic", "exciting", "medium tempo", "dj turntable", "ambient noises", "poor audio quality", "dance music", "electronic dance music", "groovy music", "dj face off", "disc scratching noises"] | ["Scratching (performance technique)", "Electronic music", "Music", "Speech"] | 1 | 20 | 30 | 0 | 0 | ["/m/01hgjl", "/m/02lkt", "/m/04rlf", "/m/09x0r"] | |
XPGtOugQ69U | This techno song starts off with a synth playing a melody followed by another synth playing a burst of two chords. The two chord bursts are accompanied by percussion playing an outro roll. The instruments pause and a male voice starts to narrate a few lines. After two lines, the pitch of the voice is lowered in pitch to reach a bass pitch. This voice fades away to silence. This song can be played in a movie featuring a robot. | ["techno song", "dj song", "synth bursts", "male voice", "vocal effect", "explicit lyrics", "programmed percussion", "moderate tempo"] | ["Drum and bass", "Electronic music", "Music", "Independent music", "Speech"] | 0 | 290 | 300 | 0 | 0 | ["/m/0283d", "/m/02lkt", "/m/04rlf", "/m/05rwpb", "/m/09x0r"] | |
B9IAl-ygE2k | This techno song features a male voice narrating a line. The song starts off with programmed percussion playing the kick and sleigh bells on alternate counts of the bar. A sliding sound is heard in the background like a sleigh on snow. The volume of the sliding sound increases in volume toward the end. A vinyl scratch is played two times. Toward the end, the instruments pause and a male voice narrates a line. This song can be played in a promotional video about a Christmas DJ party. | ["techno song", "male voice", "programmed percussion", "sleigh bells", "sliding sound", "vinyl scratching", "no voices instrumental"] | ["Christmas music", "Christian music", "Music", "Speech"] | 0 | 10 | 20 | 0 | 0 | ["/m/0140xf", "/m/02mscn", "/m/04rlf", "/m/09x0r"] | |
itT0_RhSipQ | The soundtrack is mysterious and builds anticipation. The tempo is medium with male actors vocalising a monologue, along with a terse string section harmony. The soundtrack builds anticipation and fear. The audio quality is bad. | ["tense music", "movie soundtrack", "bad audio quality", "animated movie soundtrack", "children’s movie", "great adventure", "scary", "monsters", "vocal monologue", "deteriorated audio quality", "sunday cartoons", "breathy villainous voice", "male actor voice", "building tension", "scary", "mysterious", "string section harmony", "no percussion instruments"] | ["Music", "Speech", "Scary music"] | 1 | 410 | 420 | 0 | 0 | ["/m/04rlf", "/m/09x0r", "/t/dd00037"] | |
II1oyaWPiD0 | This is the recording of a trombone lesson. The male instructor is playing a note on the trombone and then speaking in an instructive manner in the Japanese language. The click of the metronome can be heard in the background. This recording can be sampled for use in beat-making. | ["trombone lesson", "male voice", "japanese language", "instructive speaking", "metronome click"] | ["Brass instrument", "Finger snapping", "Music", "Musical instrument", "Trumpet", "Speech"] | 9 | 160 | 170 | 0 | 0 | ["/m/01kcd", "/m/025_jnm", "/m/04rlf", "/m/04szw", "/m/07gql", "/m/09x0r"] | |
_KaRkSyELy4 | The low quality recording features a tutorial where a fruity male vocalist is talking in-between electric guitar chords. There is a very buzzy guitar amp in the background and the recording is very noisy. | ["tutorial", "fruity male vocal", "speaking", "electric guitar chords", "low quality", "buzzy guitar amp", "noisy"] | ["Guitar", "Music", "Musical instrument", "Speech", "Electronic tuner", "Plucked string instrument"] | 4 | 490 | 500 | 0 | 0 | ["/m/0342h", "/m/04rlf", "/m/04szw", "/m/09x0r", "/m/0b_fwt", "/m/0fx80y"] | |
AY_yCk4eTTI | This is a tutorial video recording on how to tune an acoustic guitar to drop D tuning. There is a female voice speaking in an instructive manner as she is plucking the chords and tuning the acoustic guitar. | ["tutorial", "tuning", "acoustic guitar", "female voice", "instructive speaking", "plucking"] | ["Guitar", "Acoustic guitar", "Music", "Musical instrument", "Speech", "Electronic tuner", "Plucked string instrument", "Inside, small room"] | 9 | 60 | 70 | 0 | 0 | ["/m/0342h", "/m/042v_gx", "/m/04rlf", "/m/04szw", "/m/09x0r", "/m/0b_fwt", "/m/0fx80y", "/t/dd00125"] |
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 );