Two videos, and what the API returned
Two public videos from YouTube, analyzed by the API. For each one you get the video, the file the API returned, the same file on a timeline, and questions that a model answers from the file alone.
berlin-busker.mp4
A handheld phone clip of a street musician in Berlin. One take, 3 minutes 34 seconds.
The declared type is video/footage. The API wrote the file below from the video. Nothing in it is edited.
berlin-busker.mp4
berlin-busker.mp4.analyzemedia12.6 KB
{
"format": "analyzemedia",
"version": "0.1",
"type": "video/footage",
"generated": {
"at": "2026-09-15T03:09:55.453Z",
"by": "analyzemedia-api 0.1",
"models": {
"geometry": "opencv orb + ransac",
"music": "librosa",
"speech": "deepgram nova-3",
"vision": "gemini-3.7-flash",
"audio": "gemini-3.7-flash",
"recognition": "acrcloud"
}
},
"source": {
"name": "berlin-busker.mp4",
"bytes": 50294174,
"sha256": "41a53ab67b1058da221d3321438c0e958e3c3eda0a89d7ed892c5fdd9d8ae1e5",
"quickHash": "dac719b1af5d63cb9bb1ac212842f3b42e7a5dd5851e47bc81a7d96d6d10df45",
"container": "mov,mp4,m4a,3gp,3g2,mj2",
"duration": 213.693243,
"video": {
"codec": "h264",
"width": 1280,
"height": 720,
"fps": 29.97002997002997,
"rotation": 0,
"hdr": false,
"colorTransfer": "bt709",
"colorPrimaries": "bt709",
"pixelFormat": "yuv420p",
"bitRate": 1748439
},
"audio": {
"codec": "aac",
"channels": 2,
"sampleRate": 44100,
"bitRate": 128010
}
},
"summary": "On a pedestrianized city street, a female busker (Person A) stands behind a microphone and performs with an acoustic guitar. Pedestrians walk past, some cycling and some dropping money into her open guitar case, while a man in a white shirt and black trousers watches from the right sidewalk. She continues singing and playing her acoustic guitar throughout the entire performance.",
"camera": {
"support": "handheld",
"jitter": 0.002,
"zoom": 1.564,
"centreZoom": 0.984,
"pan": 0.2,
"tilt": -0.1,
"moves": [
{
"s": 0.2,
"e": 1.5,
"kind": "tilt down",
"amount": 6.5,
"unit": "% of height per s"
},
{
"s": 7.6,
"e": 10.4,
"kind": "tilt down",
"amount": 17.2,
"unit": "% of height per s"
},
{
"s": 10.5,
"e": 12.5,
"kind": "tilt up",
"amount": 18.4,
"unit": "% of height per s"
}
]
},
"picture": {
"palette": [ "#707070", "#505050", "#303030", "#907070" ],
"warmth": 0.048,
"saturation": 0.172,
"tonalRange": "mid",
"luma": 0.412,
"contrast": 0.177,
"sharpness": 1903,
"clippedHighlights": 0.024,
"crushedBlacks": 0.004,
"frameChange": 0.151
},
"form": {
"size": "medium",
"angle": "eye level",
"lens": "normal",
"depthOfField": "deep",
"lightKey": "flat",
"lightQuality": "soft",
"lightSource": "daylight",
"timeOfDay": "day",
"interior": "exterior",
"setting": "pedestrian street"
},
"people": [
{
"label": "A",
"description": "Young woman with dirty-blonde hair tied back in a low bun, wearing a grey sleeveless button-up mini dress and flat brown sandals, playing an acoustic guitar and singing into a stand microphone.",
"size": "medium",
"position": "center",
"facesCamera": true,
"eyeline": "camera",
"speaking": true
}
],
"clothing": "Grey sleeveless button-front mini dress and brown flat sandals.",
"composition": "Centered framing on the busker with ample headroom and street depth visible in the background.",
"description": "A female street musician stands centered on a paved urban pedestrian street, playing acoustic guitar and singing into a microphone. Pedestrians and cyclists occasionally pass in front of and behind her while she performs.",
"objects": [
"acoustic guitar",
"microphone stand",
"amplifier",
"guitar case",
"red and white barrier",
"bicycles",
"car"
],
"details": [
"A sign bearing 'Alice Hills' rests on the ground beside an amplifier and open guitar case.",
"A blue passenger car is parked in the street behind the barrier."
],
"quality": [],
"text": [
{
"s": 0,
"e": 213.69,
"text": "Alice Hills",
"where": "bottom centre"
},
{
"s": 0,
"e": 213.69,
"text": "BERLIN WALKING TOURS",
"where": "middle right"
}
],
"actions": [
{
"s": 0,
"e": 213.69,
"name": "A performs music on the street",
"who": [ "A" ],
"text": "A stands in place holding her acoustic guitar, strumming and singing into the stand microphone. She looks toward the audience and down at her instrument as passersby walk through the scene. She continues to sing and accompany herself on guitar until the clip concludes.",
"camera": "Handheld eye-level shot steadily zooming in slightly on A."
}
],
"moments": [
{
"t": 0,
"kind": "begins",
"text": "A is seen playing guitar and singing on the sidewalk."
},
{
"t": 94.5,
"kind": "other",
"text": "A woman in a green dress bends down to put money in the guitar case."
},
{
"t": 169,
"kind": "other",
"text": "A man in shorts walks past and tosses coins into the guitar case."
},
{
"t": 213.69,
"kind": "ends",
"text": "The performance take cuts out."
}
],
"environment": [
{
"s": 8,
"e": 12.5,
"kind": "foreground",
"text": "A cyclist and a pedestrian walk directly in front of the camera, briefly obstructing the view."
},
{
"s": 84,
"e": 85.5,
"kind": "foreground",
"text": "A woman in a striped shirt walks past directly in front of the lens."
},
{
"s": 104,
"e": 106,
"kind": "foreground",
"text": "A woman in a white cardigan walks across the foreground."
},
{
"s": 112,
"e": 213.69,
"kind": "background",
"text": "A man dressed in a white collared shirt and dark trousers leans against a barrier to the right."
}
],
"speech": {
"language": "ru",
"speakers": [
{
"id": 0,
"person": "A"
}
],
"paragraphs": [
{
"s": 58.820004,
"e": 73.62,
"speaker": 0,
"sentences": [
{
"s": 58.820004,
"e": 73.62,
"text": "И"
}
]
}
],
"words": [
{
"w": "И",
"s": 58.820004,
"e": 73.62,
"confidence": 0.24658203,
"speaker": 0
}
],
"fillers": [],
"silences": [],
"loudness": {
"integrated": -15.9,
"truePeak": 0,
"range": 4.8
}
},
"music": {
"heard": [
{
"s": 0,
"e": 213.7,
"text": "medium tempo synth-pop track featuring electronic percussion, synthesizers, bass, and female singing vocals"
}
],
"songs": [
{
"label": "A",
"pieces": [
{
"s": 0,
"e": 60
},
{
"s": 60,
"e": 165
}
],
"seconds": 165,
"tempo": 112.3,
"key": "C# major",
"keyConfidence": 0.84,
"recognition": null
},
{
"label": "B",
"pieces": [
{
"s": 165,
"e": 214
}
],
"seconds": 49,
"tempo": 112.3,
"key": "C# major",
"keyConfidence": 0.87,
"recognition": null
}
],
"beats": [ 0.16, 0.72, 1.25, 1.79, 2.32, 2.83, 3.37, 3.9, 4.46, 5.02, 5.57, 6.13, 6.69, 7.24, 7.83, 8.38, 8.94, 9.47, 10.01, 10.57, 11.19, 11.75, 12.28, 12.79, 13.31, 13.79, 14.28, 14.81, 15.37, 15.91, 16.46, 17.02, 17.58, 18.18, 18.74, 19.3, 19.85, 20.39, 20.92, 21.46, 21.99, 22.57, 23.13, 23.66, 24.24, 24.75, 25.33, 25.91, 26.49, 27.05, 27.61, 28.14, 28.68, 29.23, 29.77, 30.33, 30.88, 31.44, 32.02, 32.58, 33.13, 33.67, 34.2, 34.74, 35.32, 35.85, 36.41, 36.97, 37.5, 38.06, 38.64, 39.2, 39.78, 40.33, 40.89, 41.45, 42, 42.59, 43.14, 43.7, 44.23, 44.77, 45.3, 45.84, 46.37, 46.9, 47.44, 47.97, 48.51, 49.04, 49.57, 50.13, 50.64, 51.18, 51.71, 52.24, 52.78, 53.31, 53.87, 54.4, 54.96, 55.54, 56.1, 56.63, 57.17, 57.72, 58.28, 58.84, 60.72, 61.25, 61.88, 62.37, 62.9, 63.44, 64.02, 64.6, 65.13, 65.67, 66.18, 66.71, 67.24, 67.8, 68.34, 68.89, 69.43, 69.96, 70.52, 71.1, 71.63, 72.21, 72.77, 73.33, 73.89, 74.42, 74.98, 75.53, 76.07, 76.53, 77.14, 77.67, 78.25, 78.81, 79.39, 79.92, 80.46, 81.01, 81.48, 81.94, 82.43, 82.96, 83.45, 84.06, 84.59, 85.15, 85.68, 86.24, 86.82, 87.35, 87.89, 88.51, 89.05, 89.56, 90.09, 90.58, 91.09, 91.58, 92.09, 92.6, 93.13, 93.69, 94.23, 94.78, 95.29, 95.85, 96.39, 96.92, 97.48, 98.01, 98.57, 99.1, 99.64, 100.19, 100.75, 101.29, 101.87, 102.4, 102.96, 103.49, 104.03, 104.58, 105.12, 105.65, 106.21, 106.76, 107.3, 107.83, 108.37, 108.9, 109.44, 109.97, 110.55, 111.08, 111.62, 112.18, 112.71, 113.24, 113.82, 114.38, 114.92, 115.47, 116.03, 116.56, 117.12, 117.68, 118.26, 118.82, 119.37, 119.91, 120.4, 120.88, 121.37, 121.86, 122.39, 122.95, 123.48, 124.04, 124.57, 125.11, 125.67, 126.2, 126.73, 127.31, 127.87, 128.43, 128.99, 129.5, 129.98, 130.47, 130.98, 131.49, 132.03, 132.56, 133.1, 133.63, 134.19, 134.75, 135.33, 135.86, 136.42, 136.93, 137.51, 138.02, 138.6, 139.16, 139.67, 140.25, 140.78, 141.32, 141.9, 142.43, 142.96, 143.52, 144.06, 144.61, 145.15, 145.7, 146.24, 146.77, 147.31, 147.86, 148.42, 148.98, 149.51, 150.05, 150.6, 151.12, 151.65, 152.18, 152.72, 153.25, 153.79, 154.3, 154.74, 155.16, 155.69, 156.22, 156.73, 157.25, 157.8, 158.36, 158.92, 159.5, 160.05, 160.61, 161.17, 161.68, 162.21, 162.79, 163.31, 163.84, 164.37, 164.93, 165.56, 166.04, 166.65, 167.21, 167.74, 168.3, 168.88, 169.46, 169.99, 170.53, 171.06, 171.59, 172.13, 172.69, 173.24, 173.78, 174.31, 174.85, 175.43, 175.98, 176.52, 177.07, 177.61, 178.14, 178.7, 179.23, 179.81, 180.33, 180.86, 181.39, 181.9, 182.44, 183.04, 183.58, 184.13, 184.67, 185.2, 185.78, 186.36, 186.9, 187.43, 187.96, 188.52, 189.06, 189.59, 190.12, 190.68, 191.24, 191.77, 192.28, 192.84, 193.33, 193.84, 194.33, 194.84, 195.35, 195.86, 196.42, 196.95, 197.48, 198.02, 198.55, 199.13, 199.67, 200.22, 200.76, 201.29, 201.83, 202.38, 202.96, 203.52, 204.03, 204.57, 205.1, 205.66, 206.22, 206.77, 207.31, 207.84, 208.33, 208.86, 209.44, 209.98, 210.51, 211.05, 211.6 ]
},
"events": [
{
"t": 0,
"e": 213.69,
"kind": "action",
"text": "A performs music on the street [A]: A stands in place holding her acoustic guitar, strumming and singing into the stand microphone. She looks toward the audience and down at her instrument as passersby walk through the scene. She continues to sing and accompany herself on guitar until the clip concludes."
},
{
"t": 0,
"kind": "moment",
"text": "begins: A is seen playing guitar and singing on the sidewalk."
},
{
"t": 0,
"e": 213.69,
"kind": "text",
"text": "\"Alice Hills\" (bottom centre)"
},
{
"t": 0,
"e": 213.69,
"kind": "text",
"text": "\"BERLIN WALKING TOURS\" (middle right)"
},
{
"t": 0,
"e": 60,
"kind": "music",
"text": "song A, 112.3 bpm, C# major"
},
{
"t": 0.2,
"e": 1.5,
"kind": "move",
"text": "tilt down 6.5 % of height per s"
},
{
"t": 7.6,
"e": 10.4,
"kind": "move",
"text": "tilt down 17.2 % of height per s"
},
{
"t": 8,
"e": 12.5,
"kind": "environment",
"text": "foreground: A cyclist and a pedestrian walk directly in front of the camera, briefly obstructing the view."
},
{
"t": 10.5,
"e": 12.5,
"kind": "move",
"text": "tilt up 18.4 % of height per s"
},
{
"t": 58.82,
"e": 73.62,
"kind": "speech",
"text": "A: И"
},
{
"t": 60,
"e": 165,
"kind": "music",
"text": "song A, 112.3 bpm, C# major"
},
{
"t": 84,
"e": 85.5,
"kind": "environment",
"text": "foreground: A woman in a striped shirt walks past directly in front of the lens."
},
{
"t": 94.5,
"kind": "moment",
"text": "other: A woman in a green dress bends down to put money in the guitar case."
},
{
"t": 104,
"e": 106,
"kind": "environment",
"text": "foreground: A woman in a white cardigan walks across the foreground."
},
{
"t": 112,
"e": 213.69,
"kind": "environment",
"text": "background: A man dressed in a white collared shirt and dark trousers leans against a barrier to the right."
},
{
"t": 165,
"e": 214,
"kind": "music",
"text": "song B, 112.3 bpm, C# major"
},
{
"t": 169,
"kind": "moment",
"text": "other: A man in shorts walks past and tosses coins into the guitar case."
},
{
"t": 213.69,
"kind": "moment",
"text": "ends: The performance take cuts out."
}
]
}Paste the file into an assistant and ask about the video.
The file on a timeline
measuredobservedmixedderivedBars are spans. Thin marks are instants.
Questions answered from the file
Is the camera steady?
Watched berlin-busker.mp4 (1m 04s · 60,000 tokens)
I would need to watch the whole clip.
Read berlin-busker.mp4.analyzemedia (0.4s · 4,000 tokens)
It is handheld with low jitter (0.002) and a slow zoom in to 1.56x. There are three tilts in the first 13 seconds and no pans.
When do people walk in front of the camera?
Watched berlin-busker.mp4 (1m 04s · 60,000 tokens)
I would have to scrub through it.
Read berlin-busker.mp4.analyzemedia (0.4s · 4,000 tokens)
Three times: a cyclist and a pedestrian from 8.0 to 12.5 seconds, a woman in a striped shirt at 84.0 to 85.5, and a woman in a white cardigan at 104.0 to 106.0.
Is the music a known song?
Watched berlin-busker.mp4 (1m 04s · 60,000 tokens)
I cannot identify music from the audio.
Read berlin-busker.mp4.analyzemedia (0.4s · 4,000 tokens)
No. Two songs were measured, both at 112.3 BPM in C sharp major, and neither matched the recognition catalog. The transcript found no spoken words, only singing.
curtain-bangs.mp4
A vertical short by a hair stylist, cut together over a music track. 60 seconds.
The declared type is video/edit. The API wrote the file below from the video. Nothing in it is edited.
curtain-bangs.mp4
curtain-bangs.mp4.analyzemedia52.2 KB
{
"format": "analyzemedia",
"version": "0.1",
"type": "video/edit",
"generated": {
"at": "2026-09-15T03:12:41.525Z",
"by": "analyzemedia-api 0.1",
"models": {
"geometry": "opencv orb + ransac",
"music": "librosa",
"speech": "deepgram nova-3",
"vision": "gemini-3.7-flash",
"audio": "gemini-3.7-flash",
"recognition": "acrcloud"
}
},
"source": {
"name": "curtain-bangs.mp4",
"bytes": 27801820,
"sha256": "e13db492a8a6bca5216f0345a91aac0e3e1c1d20633205b861906df10b8f3dd8",
"quickHash": "584ac55337fb5e154954dfd9fda218007b81f7862e7d5cdef314cf99d1ee00be",
"container": "mov,mp4,m4a,3gp,3g2,mj2",
"duration": 59.953991,
"video": {
"codec": "h264",
"width": 720,
"height": 1280,
"fps": 30,
"rotation": 0,
"hdr": false,
"colorTransfer": "bt709",
"colorPrimaries": "smpte170m",
"pixelFormat": "yuv420p",
"bitRate": 3576383
},
"audio": {
"codec": "aac",
"channels": 2,
"sampleRate": 44100,
"bitRate": 127752
}
},
"summary": "In a studio with a metallic foil backdrop and purple lighting, hairstylist Brad Mondo demonstrates a step-by-step technique to cut curtain bangs and face-framing layers at home using a blonde mannequin head. He partitions the wet hair into triangle sections, crosses them over to opposite sides, secures them with elastic bands, and trims the ends before cutting sliding angles down the sides. After blow-drying the hair, he reveals the final styled curtain bangs and invites viewers to try the technique at home.",
"scenes": [
{
"id": 1,
"s": 0,
"e": 51.2,
"place": "studio with silver foil backdrop",
"who": [ "A" ],
"text": "Hairstylist Brad Mondo introduces and demonstrates his method for cutting curtain bangs and face framing layers at home using a blonde mannequin head. He lists the necessary tools, parts the hair, sections two triangles at the front hairline, crosses them over, secures each with an elastic band at mouth level, and snips them off. He then demonstrates slide cutting along the sides to blend face-framing layers before transitioning to dry the hair.",
"cuts": [
{
"t": 1,
"kind": "cut",
"to": "close-up of the mannequin hair being combed"
},
{
"t": 1.9,
"kind": "cut",
"to": "clipping back the sides of the mannequin hair"
},
{
"t": 2.8,
"kind": "cut",
"to": "A demonstrating the two sections pulled outward"
},
{
"t": 4.2,
"kind": "cut",
"to": "close-up of the elastic band on the hair section"
},
{
"t": 5.4,
"kind": "cut",
"to": "A cutting the secured strand with scissors"
},
{
"t": 5.9,
"kind": "punch-in",
"to": "punch-in on the scissors finishing the cut"
},
{
"t": 6.7,
"kind": "punch-out",
"to": "punch-out as A throws away the cut hair"
},
{
"t": 8.6,
"kind": "cut",
"to": "close-up of the hair cutting scissors"
},
{
"t": 9.9,
"kind": "punch-out",
"to": "A showing the purple styling comb"
},
{
"t": 11,
"kind": "punch-in",
"to": "close-up of the clear elastic band"
},
{
"t": 12,
"kind": "cut",
"to": "close-up of the wet hair on the mannequin"
},
{
"t": 13.2,
"kind": "cut",
"to": "combing the middle part on the mannequin"
},
{
"t": 14.3,
"kind": "punch-out",
"to": "separating the crown hair sections"
},
{
"t": 16.1,
"kind": "cut",
"to": "lifting top hair to create front section"
},
{
"t": 16.9,
"kind": "cut",
"to": "A pointing with comb and explaining the sectioning"
},
{
"t": 20.3,
"kind": "cut",
"to": "measuring two inches back with the comb"
},
{
"t": 21.2,
"kind": "cut",
"to": "sectioning diagonally to the eyebrow"
},
{
"t": 23.2,
"kind": "cut",
"to": "securing side hair with clip"
},
{
"t": 24.9,
"kind": "cut",
"to": "drawing second triangle section on opposite side"
},
{
"t": 26.4,
"kind": "cut",
"to": "clipping back the second side section"
},
{
"t": 28.8,
"kind": "punch-in",
"to": "punch-in on the clipped mannequin head"
},
{
"t": 30.8,
"kind": "cut",
"to": "combing the front triangle sections smooth"
},
{
"t": 31.9,
"kind": "cut",
"to": "view of the two front triangle sections"
},
{
"t": 32.8,
"kind": "cut",
"to": "A standing behind mannequin explaining crossover step"
},
{
"t": 33.7,
"kind": "cut",
"to": "combing the hair section to the opposite side"
},
{
"t": 34.2,
"kind": "punch-in",
"to": "punch-in on the crossed-over hair held in fingers"
},
{
"t": 35,
"kind": "cut",
"to": "final comb stroke through crossed section"
},
{
"t": 35.6,
"kind": "cut",
"to": "wrapping elastic band around the hair strand"
},
{
"t": 37.3,
"kind": "punch-in",
"to": "punch-in on sliding the elastic to the mouth level"
},
{
"t": 38.8,
"kind": "cut",
"to": "fine-tuning the elastic position"
},
{
"t": 40,
"kind": "cut",
"to": "view of the secured hair strand ready to cut"
},
{
"t": 41,
"kind": "cut",
"to": "pointing to the elastic band cutoff point"
},
{
"t": 42,
"kind": "cut",
"to": "A cutting the hair below the elastic band"
},
{
"t": 43.7,
"kind": "cut",
"to": "A tossing cut hair and speaking to camera"
},
{
"t": 47.7,
"kind": "cut",
"to": "combing the second section to the opposite side"
},
{
"t": 50.6,
"kind": "cut",
"to": "holding the crossed strand with comb"
}
],
"layout": {
"kind": "full"
}
},
{
"id": 2,
"s": 51.2,
"e": 59.95,
"place": "studio with silver foil backdrop",
"who": [ "A" ],
"text": "After blow-drying, Brad Mondo displays the styled curtain bangs on the mannequin head from various angles. He admires the final result, expresses his enthusiasm, and encourages viewers to try the technique at home and share their reaction videos.",
"cuts": [
{
"t": 53.3,
"kind": "wipe",
"to": "cutting the second section below the elastic"
},
{
"t": 55.1,
"kind": "cut",
"to": "releasing the cut curtain bangs on the mannequin"
},
{
"t": 56.4,
"kind": "cut",
"to": "A pointing at the cut bangs and explaining layers"
},
{
"t": 58.2,
"kind": "cut",
"to": "combing the side face-framing section"
},
{
"t": 59,
"kind": "cut",
"to": "slide cutting down the face-framing strand"
},
{
"t": 59.6,
"kind": "cut",
"to": "completing slide cut down to the ends"
}
],
"layout": {
"kind": "full"
}
}
],
"captions": null,
"overlays": [],
"people": [
{
"label": "A",
"description": "Young man with short wavy light brown and blonde hair, fair skin, wearing a black leather biker jacket, a chunky silver chain necklace, and black rings on his fingers."
}
],
"sfx": [],
"pacing": {
"cuts": 43,
"cutsPerMinute": 43.03,
"scenes": 2,
"shortestScene": 8.75,
"longestScene": 51.2,
"meanShot": 1.36
},
"speech": {
"language": "en",
"speakers": [
{
"id": 0,
"person": "A"
}
],
"paragraphs": [
{
"s": 0,
"e": 13.695,
"speaker": 0,
"sentences": [
{
"s": 0,
"e": 0.88,
"text": "Hi, beautiful."
},
{
"s": 0.88,
"e": 5.3599997,
"text": "I'm gonna show you a completely new way to easily cut your own curtain bangs at home."
},
{
"s": 5.3599997,
"e": 7.7599998,
"text": "Let's call this one the Bramondo curtain bang."
},
{
"s": 7.7599998,
"e": 8.88,
"text": "I'm gonna get into trouble, aren't I?"
},
{
"s": 8.88,
"e": 13.695,
"text": "All you need is hair cutting scissors, a comb, a couple elastics, and a head of wet hair."
}
]
},
{
"s": 13.695001,
"e": 35.32,
"speaker": 0,
"sentences": [
{
"s": 13.695001,
"e": 16.895,
"text": "First, you're gonna part your hair in the middle or wherever you usually part your hair."
},
{
"s": 16.895,
"e": 26.255001,
"text": "Then we're gonna make two little triangle sections on the front of the hairline going from about two inches back from the front of the hairline down to the side of the end of the eyebrow."
},
{
"s": 26.255001,
"e": 29,
"text": "Next, you're gonna comb that section to the opposite side."
},
{
"s": 29,
"e": 33.96,
"text": "After that, put in an elastic and pull the elastic down to about the corner of your mouth."
},
{
"s": 33.96,
"e": 35.32,
"text": "Next, cut the hair."
}
]
},
{
"s": 35.32,
"e": 48.015,
"speaker": 0,
"sentences": [
{
"s": 35.32,
"e": 35.88,
"text": "Beautiful."
},
{
"s": 35.88,
"e": 37.96,
"text": "And we'll do the same thing on the opposite side."
},
{
"s": 37.96,
"e": 40.92,
"text": "Pull the section over, put an elastic in, cut the hair."
},
{
"s": 40.92,
"e": 42.335003,
"text": "That is literally it."
},
{
"s": 42.335003,
"e": 48.015,
"text": "If you wanna also have some face framing layers, which I always recommend, it looks great with curtain bangs, do that now."
}
]
},
{
"s": 48.015,
"e": 55.243,
"speaker": 0,
"sentences": [
{
"s": 48.015,
"e": 50.815002,
"text": "And this one's hard to explain, so just look at what I'm doing and try to copy it."
},
{
"s": 50.815002,
"e": 52.575,
"text": "Now I'll blow dry the hair and voila."
},
{
"s": 52.575,
"e": 53.375,
"text": "Oh my god."
},
{
"s": 53.375,
"e": 53.935,
"text": "It's gorgeous."
},
{
"s": 54.203003,
"e": 55.243,
"text": "So easy to do."
}
]
},
{
"s": 55.243,
"e": 60.043,
"speaker": 0,
"sentences": [
{
"s": 55.243,
"e": 56.123,
"text": "It looks stunning."
},
{
"s": 56.123,
"e": 56.843002,
"text": "I'm obsessed."
},
{
"s": 56.843002,
"e": 59.563,
"text": "And if you try this at home, make a video so I can react to it."
},
{
"s": 59.563,
"e": 60.043,
"text": "Good luck."
}
]
}
],
"words": [
{
"w": "Hi,",
"s": 0,
"e": 0.39999998,
"confidence": 0.9904785,
"speaker": 0
},
{
"w": "beautiful.",
"s": 0.39999998,
"e": 0.88,
"confidence": 0.9592285,
"speaker": 0
},
{
"w": "I'm",
"s": 0.88,
"e": 1.12,
"confidence": 1,
"speaker": 0
},
{
"w": "gonna",
"s": 1.12,
"e": 1.1999999,
"confidence": 0.9921875,
"speaker": 0
},
{
"w": "show",
"s": 1.1999999,
"e": 1.36,
"confidence": 0.99902344,
"speaker": 0
},
{
"w": "you",
"s": 1.36,
"e": 1.52,
"confidence": 1,
"speaker": 0
},
{
"w": "a",
"s": 1.52,
"e": 1.68,
"confidence": 0.99902344,
"speaker": 0
},
{
"w": "completely",
"s": 1.68,
"e": 2.08,
"confidence": 1,
"speaker": 0
},
{
"w": "new",
"s": 2.08,
"e": 2.3999999,
"confidence": 1,
"speaker": 0
},
{
"w": "way",
"s": 2.3999999,
"e": 2.6399999,
"confidence": 1,
"speaker": 0
},
{
"w": "to",
"s": 2.6399999,
"e": 2.96,
"confidence": 0.9970703,
"speaker": 0
},
{
"w": "easily",
"s": 2.96,
"e": 3.36,
"confidence": 1,
"speaker": 0
},
{
"w": "cut",
"s": 3.36,
"e": 3.6799998,
"confidence": 1,
"speaker": 0
},
{
"w": "your",
"s": 3.6799998,
"e": 3.9199998,
"confidence": 1,
"speaker": 0
},
{
"w": "own",
"s": 3.9199998,
"e": 4.08,
"confidence": 1,
"speaker": 0
},
{
"w": "curtain",
"s": 4.08,
"e": 4.48,
"confidence": 0.99902344,
"speaker": 0
},
{
"w": "bangs",
"s": 4.48,
"e": 4.88,
"confidence": 0.9980469,
"speaker": 0
},
{
"w": "at",
"s": 4.88,
"e": 5.04,
"confidence": 1,
"speaker": 0
},
{
"w": "home.",
"s": 5.04,
"e": 5.3599997,
"confidence": 1,
"speaker": 0
},
{
"w": "Let's",
"s": 5.3599997,
"e": 5.6,
"confidence": 1,
"speaker": 0
},
{
"w": "call",
"s": 5.6,
"e": 5.8399997,
"confidence": 1,
"speaker": 0
},
{
"w": "this",
"s": 5.8399997,
"e": 6,
"confidence": 1,
"speaker": 0
},
{
"w": "one",
"s": 6,
"e": 6.24,
"confidence": 1,
"speaker": 0
},
{
"w": "the",
"s": 6.24,
"e": 6.56,
"confidence": 0.921875,
"speaker": 0
},
{
"w": "Bramondo",
"s": 6.56,
"e": 7.12,
"confidence": 0.7351074,
"speaker": 0
},
{
"w": "curtain",
"s": 7.12,
"e": 7.44,
"confidence": 0.9614258,
"speaker": 0
},
{
"w": "bang.",
"s": 7.44,
"e": 7.7599998,
"confidence": 0.9980469,
"speaker": 0
},
{
"w": "I'm",
"s": 7.7599998,
"e": 7.9199996,
"confidence": 0.9941406,
"speaker": 0
},
{
"w": "gonna",
"s": 7.9199996,
"e": 8,
"confidence": 0.9838867,
"speaker": 0
},
{
"w": "get",
"s": 8,
"e": 8.08,
"confidence": 0.99121094,
"speaker": 0
},
{
"w": "into",
"s": 8.08,
"e": 8.24,
"confidence": 0.9526367,
"speaker": 0
},
{
"w": "trouble,",
"s": 8.24,
"e": 8.559999,
"confidence": 0.97753906,
"speaker": 0
},
{
"w": "aren't",
"s": 8.559999,
"e": 8.72,
"confidence": 0.99853516,
"speaker": 0
},
{
"w": "I?",
"s": 8.72,
"e": 8.88,
"confidence": 0.9995117,
"speaker": 0
},
{
"w": "All",
"s": 8.88,
"e": 9.04,
"confidence": 1,
"speaker": 0
},
{
"w": "you",
"s": 9.04,
"e": 9.2,
"confidence": 1,
"speaker": 0
},
{
"w": "need",
"s": 9.2,
"e": 9.28,
"confidence": 0.99902344,
"speaker": 0
},
{
"w": "is",
"s": 9.28,
"e": 9.5199995,
"confidence": 1,
"speaker": 0
},
{
"w": "hair",
"s": 9.5199995,
"e": 9.76,
"confidence": 0.8178711,
"speaker": 0
},
{
"w": "cutting",
"s": 9.76,
"e": 10,
"confidence": 0.9921875,
"speaker": 0
},
{
"w": "scissors,",
"s": 10,
"e": 10.48,
"confidence": 0.99853516,
"speaker": 0
},
{
"w": "a",
"s": 10.48,
"e": 10.639999,
"confidence": 1,
"speaker": 0
},
{
"w": "comb,",
"s": 10.639999,
"e": 11.12,
"confidence": 1,
"speaker": 0
},
{
"w": "a",
"s": 11.12,
"e": 11.28,
"confidence": 0.9980469,
"speaker": 0
},
{
"w": "couple",
"s": 11.28,
"e": 11.44,
"confidence": 0.99902344,
"speaker": 0
},
{
"w": "elastics,",
"s": 11.44,
"e": 12,
"confidence": 0.8598633,
"speaker": 0
},
{
"w": "and",
"s": 12.095,
"e": 12.335,
"confidence": 0.99902344,
"speaker": 0
},
{
"w": "a",
"s": 12.335,
"e": 12.575001,
"confidence": 0.9902344,
"speaker": 0
},
{
"w": "head",
"s": 12.575001,
"e": 12.735001,
"confidence": 0.9980469,
"speaker": 0
},
{
"w": "of",
"s": 12.735001,
"e": 12.895,
"confidence": 1,
"speaker": 0
},
{
"w": "wet",
"s": 12.895,
"e": 13.215,
"confidence": 1,
"speaker": 0
},
{
"w": "hair.",
"s": 13.215,
"e": 13.695,
"confidence": 0.9995117,
"speaker": 0
},
{
"w": "First,",
"s": 13.695001,
"e": 13.935,
"confidence": 0.9980469,
"speaker": 0
},
{
"w": "you're",
"s": 13.935,
"e": 14.095,
"confidence": 0.99902344,
"speaker": 0
},
{
"w": "gonna",
"s": 14.095,
"e": 14.175,
"confidence": 0.9892578,
"speaker": 0
},
{
"w": "part",
"s": 14.175,
"e": 14.335,
"confidence": 0.9550781,
"speaker": 0
},
{
"w": "your",
"s": 14.335,
"e": 14.415,
"confidence": 0.99609375,
"speaker": 0
},
{
"w": "hair",
"s": 14.415,
"e": 14.575001,
"confidence": 1,
"speaker": 0
},
{
"w": "in",
"s": 14.575001,
"e": 14.655001,
"confidence": 0.9941406,
"speaker": 0
},
{
"w": "the",
"s": 14.655001,
"e": 14.815001,
"confidence": 0.99902344,
"speaker": 0
},
{
"w": "middle",
"s": 14.815001,
"e": 15.135,
"confidence": 1,
"speaker": 0
},
{
"w": "or",
"s": 15.135,
"e": 15.375,
"confidence": 0.9550781,
"speaker": 0
},
{
"w": "wherever",
"s": 15.375,
"e": 15.775001,
"confidence": 0.9970703,
"speaker": 0
},
{
"w": "you",
"s": 15.775001,
"e": 15.935,
"confidence": 0.9892578,
"speaker": 0
},
{
"w": "usually",
"s": 15.935,
"e": 16.095001,
"confidence": 0.99902344,
"speaker": 0
},
{
"w": "part",
"s": 16.095001,
"e": 16.335,
"confidence": 0.9980469,
"speaker": 0
},
{
"w": "your",
"s": 16.335,
"e": 16.495,
"confidence": 0.99902344,
"speaker": 0
},
{
"w": "hair.",
"s": 16.495,
"e": 16.895,
"confidence": 0.98657227,
"speaker": 0
},
{
"w": "Then",
"s": 16.895,
"e": 17.135,
"confidence": 1,
"speaker": 0
},
{
"w": "we're",
"s": 17.135,
"e": 17.295,
"confidence": 0.9807129,
"speaker": 0
},
{
"w": "gonna",
"s": 17.295,
"e": 17.455,
"confidence": 0.9951172,
"speaker": 0
},
{
"w": "make",
"s": 17.455,
"e": 17.615,
"confidence": 0.99902344,
"speaker": 0
},
{
"w": "two",
"s": 17.615,
"e": 17.855,
"confidence": 1,
"speaker": 0
},
{
"w": "little",
"s": 17.855,
"e": 18.255001,
"confidence": 0.99902344,
"speaker": 0
},
{
"w": "triangle",
"s": 18.255001,
"e": 18.735,
"confidence": 0.9980469,
"speaker": 0
},
{
"w": "sections",
"s": 18.735,
"e": 19.295,
"confidence": 1,
"speaker": 0
},
{
"w": "on",
"s": 19.295,
"e": 19.535,
"confidence": 1,
"speaker": 0
},
{
"w": "the",
"s": 19.535,
"e": 19.615,
"confidence": 0.99902344,
"speaker": 0
},
{
"w": "front",
"s": 19.615,
"e": 19.775,
"confidence": 1,
"speaker": 0
},
{
"w": "of",
"s": 19.775,
"e": 19.855,
"confidence": 0.99902344,
"speaker": 0
},
{
"w": "the",
"s": 19.855,
"e": 20.015,
"confidence": 0.99902344,
"speaker": 0
},
{
"w": "hairline",
"s": 20.015,
"e": 20.415,
"confidence": 0.9946289,
"speaker": 0
},
{
"w": "going",
"s": 20.415,
"e": 20.815,
"confidence": 0.5961914,
"speaker": 0
},
{
"w": "from",
"s": 20.815,
"e": 21.055,
"confidence": 0.99902344,
"speaker": 0
},
{
"w": "about",
"s": 21.055,
"e": 21.295,
"confidence": 1,
"speaker": 0
},
{
"w": "two",
"s": 21.295,
"e": 21.535,
"confidence": 1,
"speaker": 0
},
{
"w": "inches",
"s": 21.535,
"e": 21.935001,
"confidence": 1,
"speaker": 0
},
{
"w": "back",
"s": 21.935001,
"e": 22.255001,
"confidence": 1,
"speaker": 0
},
{
"w": "from",
"s": 22.255001,
"e": 22.494999,
"confidence": 0.99902344,
"speaker": 0
},
{
"w": "the",
"s": 22.494999,
"e": 22.654999,
"confidence": 0.9941406,
"speaker": 0
},
{
"w": "front",
"s": 22.654999,
"e": 22.815,
"confidence": 1,
"speaker": 0
},
{
"w": "of",
"s": 22.815,
"e": 22.895,
"confidence": 0.99902344,
"speaker": 0
},
{
"w": "the",
"s": 22.895,
"e": 22.975,
"confidence": 0.99902344,
"speaker": 0
},
{
"w": "hairline",
"s": 22.975,
"e": 23.375,
"confidence": 0.9980469,
"speaker": 0
},
{
"w": "down",
"s": 23.375,
"e": 23.935001,
"confidence": 0.9428711,
"speaker": 0
},
{
"w": "to",
"s": 23.935001,
"e": 24.255001,
"confidence": 1,
"speaker": 0
},
{
"w": "the",
"s": 24.255001,
"e": 24.494999,
"confidence": 0.9243164,
"speaker": 0
},
{
"w": "side",
"s": 24.494999,
"e": 24.895,
"confidence": 1,
"speaker": 0
},
{
"w": "of",
"s": 24.895,
"e": 25.135,
"confidence": 1,
"speaker": 0
},
{
"w": "the",
"s": 25.135,
"e": 25.215,
"confidence": 0.99902344,
"speaker": 0
},
{
"w": "end",
"s": 25.215,
"e": 25.455,
"confidence": 1,
"speaker": 0
},
{
"w": "of",
"s": 25.455,
"e": 25.535,
"confidence": 0.9980469,
"speaker": 0
},
{
"w": "the",
"s": 25.535,
"e": 25.695,
"confidence": 1,
"speaker": 0
},
{
"w": "eyebrow.",
"s": 25.695,
"e": 26.255001,
"confidence": 0.9996745,
"speaker": 0
},
{
"w": "Next,",
"s": 26.255001,
"e": 26.575,
"confidence": 0.99902344,
"speaker": 0
},
{
"w": "you're",
"s": 26.52,
"e": 26.84,
"confidence": 0.9970703,
"speaker": 0
},
{
"w": "gonna",
"s": 26.84,
"e": 27,
"confidence": 0.98535156,
"speaker": 0
},
{
"w": "comb",
"s": 27,
"e": 27.24,
"confidence": 0.9716797,
"speaker": 0
},
{
"w": "that",
"s": 27.24,
"e": 27.4,
"confidence": 0.9980469,
"speaker": 0
},
{
"w": "section",
"s": 27.4,
"e": 27.720001,
"confidence": 0.99609375,
"speaker": 0
},
{
"w": "to",
"s": 27.720001,
"e": 27.960001,
"confidence": 1,
"speaker": 0
},
{
"w": "the",
"s": 27.960001,
"e": 28.04,
"confidence": 0.99902344,
"speaker": 0
},
{
"w": "opposite",
"s": 28.04,
"e": 28.6,
"confidence": 1,
"speaker": 0
},
{
"w": "side.",
"s": 28.6,
"e": 29,
"confidence": 0.9995117,
"speaker": 0
},
{
"w": "After",
"s": 29,
"e": 29.32,
"confidence": 1,
"speaker": 0
},
{
"w": "that,",
"s": 29.32,
"e": 29.64,
"confidence": 0.99853516,
"speaker": 0
},
{
"w": "put",
"s": 29.64,
"e": 29.880001,
"confidence": 1,
"speaker": 0
},
{
"w": "in",
"s": 29.880001,
"e": 30.04,
"confidence": 0.9892578,
"speaker": 0
},
{
"w": "an",
"s": 30.04,
"e": 30.2,
"confidence": 0.97802734,
"speaker": 0
},
{
"w": "elastic",
"s": 30.2,
"e": 30.84,
"confidence": 0.99902344,
"speaker": 0
},
{
"w": "and",
"s": 30.84,
"e": 31.16,
"confidence": 0.76123047,
"speaker": 0
},
{
"w": "pull",
"s": 31.16,
"e": 31.400002,
"confidence": 0.99902344,
"speaker": 0
},
{
"w": "the",
"s": 31.400002,
"e": 31.560001,
"confidence": 0.9951172,
"speaker": 0
},
{
"w": "elastic",
"s": 31.560001,
"e": 32.04,
"confidence": 1,
"speaker": 0
},
{
"w": "down",
"s": 32.04,
"e": 32.28,
"confidence": 1,
"speaker": 0
},
{
"w": "to",
"s": 32.28,
"e": 32.52,
"confidence": 0.99609375,
"speaker": 0
},
{
"w": "about",
"s": 32.52,
"e": 32.760002,
"confidence": 0.9951172,
"speaker": 0
},
{
"w": "the",
"s": 32.760002,
"e": 32.84,
"confidence": 0.99902344,
"speaker": 0
},
{
"w": "corner",
"s": 32.84,
"e": 33.24,
"confidence": 1,
"speaker": 0
},
{
"w": "of",
"s": 33.24,
"e": 33.32,
"confidence": 1,
"speaker": 0
},
{
"w": "your",
"s": 33.32,
"e": 33.48,
"confidence": 0.99902344,
"speaker": 0
},
{
"w": "mouth.",
"s": 33.48,
"e": 33.96,
"confidence": 0.9995117,
"speaker": 0
},
{
"w": "Next,",
"s": 33.96,
"e": 34.52,
"confidence": 0.9970703,
"speaker": 0
},
{
"w": "cut",
"s": 34.52,
"e": 34.760002,
"confidence": 1,
"speaker": 0
},
{
"w": "the",
"s": 34.760002,
"e": 34.84,
"confidence": 0.99902344,
"speaker": 0
},
{
"w": "hair.",
"s": 34.84,
"e": 35.32,
"confidence": 0.99853516,
"speaker": 0
},
{
"w": "Beautiful.",
"s": 35.32,
"e": 35.88,
"confidence": 0.9951172,
"speaker": 0
},
{
"w": "And",
"s": 35.88,
"e": 36.04,
"confidence": 1,
"speaker": 0
},
{
"w": "we'll",
"s": 36.04,
"e": 36.28,
"confidence": 0.99902344,
"speaker": 0
},
{
"w": "do",
"s": 36.28,
"e": 36.36,
"confidence": 0.99902344,
"speaker": 0
},
{
"w": "the",
"s": 36.36,
"e": 36.52,
"confidence": 0.99902344,
"speaker": 0
},
{
"w": "same",
"s": 36.52,
"e": 36.760002,
"confidence": 1,
"speaker": 0
},
{
"w": "thing",
"s": 36.760002,
"e": 37,
"confidence": 1,
"speaker": 0
},
{
"w": "on",
"s": 37,
"e": 37.16,
"confidence": 0.99902344,
"speaker": 0
},
{
"w": "the",
"s": 37.16,
"e": 37.32,
"confidence": 0.9980469,
"speaker": 0
},
{
"w": "opposite",
"s": 37.32,
"e": 37.64,
"confidence": 0.99902344,
"speaker": 0
},
{
"w": "side.",
"s": 37.64,
"e": 37.96,
"confidence": 0.99853516,
"speaker": 0
},
{
"w": "Pull",
"s": 37.96,
"e": 38.2,
"confidence": 0.9980469,
"speaker": 0
},
{
"w": "the",
"s": 38.2,
"e": 38.36,
"confidence": 0.7763672,
"speaker": 0
},
{
"w": "section",
"s": 38.36,
"e": 38.6,
"confidence": 0.9980469,
"speaker": 0
},
{
"w": "over,",
"s": 38.6,
"e": 38.92,
"confidence": 0.8334961,
"speaker": 0
},
{
"w": "put",
"s": 38.92,
"e": 39.16,
"confidence": 0.9863281,
"speaker": 0
},
{
"w": "an",
"s": 39.16,
"e": 39.32,
"confidence": 0.96435547,
"speaker": 0
},
{
"w": "elastic",
"s": 39.32,
"e": 39.72,
"confidence": 0.9980469,
"speaker": 0
},
{
"w": "in,",
"s": 39.72,
"e": 40.2,
"confidence": 0.97509766,
"speaker": 0
},
{
"w": "cut",
"s": 40.2,
"e": 40.36,
"confidence": 0.9741211,
"speaker": 0
},
{
"w": "the",
"s": 40.36,
"e": 40.52,
"confidence": 0.99316406,
"speaker": 0
},
{
"w": "hair.",
"s": 40.52,
"e": 40.92,
"confidence": 0.9692383,
"speaker": 0
},
{
"w": "That",
"s": 40.92,
"e": 41.16,
"confidence": 0.9873047,
"speaker": 0
},
{
"w": "is",
"s": 41.16,
"e": 41.96,
"confidence": 0.98291016,
"speaker": 0
},
{
"w": "literally",
"s": 41.775,
"e": 41.855003,
"confidence": 0.9370117,
"speaker": 0
},
{
"w": "it.",
"s": 41.855003,
"e": 42.335003,
"confidence": 0.99902344,
"speaker": 0
},
{
"w": "If",
"s": 42.335003,
"e": 42.495003,
"confidence": 0.99902344,
"speaker": 0
},
{
"w": "you",
"s": 42.495003,
"e": 42.655003,
"confidence": 1,
"speaker": 0
},
{
"w": "wanna",
"s": 42.655003,
"e": 42.895,
"confidence": 0.97314453,
"speaker": 0
},
{
"w": "also",
"s": 42.895,
"e": 43.295002,
"confidence": 0.99902344,
"speaker": 0
},
{
"w": "have",
"s": 43.295002,
"e": 43.615,
"confidence": 1,
"speaker": 0
},
{
"w": "some",
"s": 43.615,
"e": 43.775,
"confidence": 0.9980469,
"speaker": 0
},
{
"w": "face",
"s": 43.775,
"e": 44.015003,
"confidence": 0.9951172,
"speaker": 0
},
{
"w": "framing",
"s": 44.015003,
"e": 44.335003,
"confidence": 0.87841797,
"speaker": 0
},
{
"w": "layers,",
"s": 44.335003,
"e": 44.735,
"confidence": 0.9890137,
"speaker": 0
},
{
"w": "which",
"s": 44.735,
"e": 44.895,
"confidence": 1,
"speaker": 0
},
{
"w": "I",
"s": 44.895,
"e": 45.055,
"confidence": 1,
"speaker": 0
},
{
"w": "always",
"s": 45.055,
"e": 45.455,
"confidence": 1,
"speaker": 0
},
{
"w": "recommend,",
"s": 45.455,
"e": 46.015,
"confidence": 0.8779297,
"speaker": 0
},
{
"w": "it",
"s": 46.015,
"e": 46.095,
"confidence": 0.9970703,
"speaker": 0
},
{
"w": "looks",
"s": 46.095,
"e": 46.335003,
"confidence": 1,
"speaker": 0
},
{
"w": "great",
"s": 46.335003,
"e": 46.495003,
"confidence": 0.99902344,
"speaker": 0
},
{
"w": "with",
"s": 46.495003,
"e": 46.655003,
"confidence": 0.9980469,
"speaker": 0
},
{
"w": "curtain",
"s": 46.655003,
"e": 46.895,
"confidence": 0.99902344,
"speaker": 0
},
{
"w": "bangs,",
"s": 46.895,
"e": 47.215,
"confidence": 0.91764325,
"speaker": 0
},
{
"w": "do",
"s": 47.215,
"e": 47.455,
"confidence": 0.9951172,
"speaker": 0
},
{
"w": "that",
"s": 47.455,
"e": 47.615,
"confidence": 1,
"speaker": 0
},
{
"w": "now.",
"s": 47.615,
"e": 48.015,
"confidence": 0.96875,
"speaker": 0
},
{
"w": "And",
"s": 48.015,
"e": 48.095,
"confidence": 0.99902344,
"speaker": 0
},
{
"w": "this",
"s": 48.095,
"e": 48.255,
"confidence": 0.99902344,
"speaker": 0
},
{
"w": "one's",
"s": 48.255,
"e": 48.415,
"confidence": 0.9663086,
"speaker": 0
},
{
"w": "hard",
"s": 48.415,
"e": 48.575,
"confidence": 1,
"speaker": 0
},
{
"w": "to",
"s": 48.575,
"e": 48.655003,
"confidence": 0.99902344,
"speaker": 0
},
{
"w": "explain,",
"s": 48.655003,
"e": 49.055,
"confidence": 0.779541,
"speaker": 0
},
{
"w": "so",
"s": 49.055,
"e": 49.135002,
"confidence": 0.9902344,
"speaker": 0
},
{
"w": "just",
"s": 49.135002,
"e": 49.295002,
"confidence": 1,
"speaker": 0
},
{
"w": "look",
"s": 49.295002,
"e": 49.455,
"confidence": 0.9951172,
"speaker": 0
},
{
"w": "at",
"s": 49.455,
"e": 49.615,
"confidence": 0.6538086,
"speaker": 0
},
{
"w": "what",
"s": 49.615,
"e": 49.695,
"confidence": 0.99902344,
"speaker": 0
},
{
"w": "I'm",
"s": 49.695,
"e": 49.855003,
"confidence": 1,
"speaker": 0
},
{
"w": "doing",
"s": 49.855003,
"e": 50.015,
"confidence": 1,
"speaker": 0
},
{
"w": "and",
"s": 50.015,
"e": 50.175003,
"confidence": 0.9707031,
"speaker": 0
},
{
"w": "try",
"s": 50.175003,
"e": 50.335,
"confidence": 0.9980469,
"speaker": 0
},
{
"w": "to",
"s": 50.335,
"e": 50.415,
"confidence": 0.9980469,
"speaker": 0
},
{
"w": "copy",
"s": 50.415,
"e": 50.575,
"confidence": 1,
"speaker": 0
},
{
"w": "it.",
"s": 50.575,
"e": 50.815002,
"confidence": 0.9995117,
"speaker": 0
},
{
"w": "Now",
"s": 50.815002,
"e": 50.895,
"confidence": 0.99902344,
"speaker": 0
},
{
"w": "I'll",
"s": 50.895,
"e": 51.135002,
"confidence": 0.95874023,
"speaker": 0
},
{
"w": "blow",
"s": 51.135002,
"e": 51.215,
"confidence": 1,
"speaker": 0
},
{
"w": "dry",
"s": 51.215,
"e": 51.375,
"confidence": 0.97265625,
"speaker": 0
},
{
"w": "the",
"s": 51.375,
"e": 51.535004,
"confidence": 0.9980469,
"speaker": 0
},
{
"w": "hair",
"s": 51.535004,
"e": 51.695,
"confidence": 1,
"speaker": 0
},
{
"w": "and",
"s": 51.695,
"e": 52.015,
"confidence": 0.53515625,
"speaker": 0
},
{
"w": "voila.",
"s": 52.015,
"e": 52.575,
"confidence": 0.98254395,
"speaker": 0
},
{
"w": "Oh",
"s": 52.575,
"e": 52.815002,
"confidence": 0.99902344,
"speaker": 0
},
{
"w": "my",
"s": 52.815002,
"e": 52.975002,
"confidence": 0.9614258,
"speaker": 0
},
{
"w": "god.",
"s": 52.975002,
"e": 53.375,
"confidence": 0.9645996,
"speaker": 0
},
{
"w": "It's",
"s": 53.375,
"e": 53.615,
"confidence": 0.9995117,
"speaker": 0
},
{
"w": "gorgeous.",
"s": 53.615,
"e": 53.935,
"confidence": 0.9350586,
"speaker": 0
},
{
"w": "So",
"s": 54.203003,
"e": 54.523003,
"confidence": 0.99121094,
"speaker": 0
},
{
"w": "easy",
"s": 54.523003,
"e": 54.763,
"confidence": 1,
"speaker": 0
},
{
"w": "to",
"s": 54.763,
"e": 54.923,
"confidence": 1,
"speaker": 0
},
{
"w": "do.",
"s": 54.923,
"e": 55.243,
"confidence": 0.9980469,
"speaker": 0
},
{
"w": "It",
"s": 55.243,
"e": 55.403,
"confidence": 1,
"speaker": 0
},
{
"w": "looks",
"s": 55.403,
"e": 55.643,
"confidence": 0.9951172,
"speaker": 0
},
{
"w": "stunning.",
"s": 55.643,
"e": 56.123,
"confidence": 0.9995117,
"speaker": 0
},
{
"w": "I'm",
"s": 56.123,
"e": 56.363003,
"confidence": 0.96875,
"speaker": 0
},
{
"w": "obsessed.",
"s": 56.363003,
"e": 56.843002,
"confidence": 0.9785156,
"speaker": 0
},
{
"w": "And",
"s": 56.843002,
"e": 56.923,
"confidence": 1,
"speaker": 0
},
{
"w": "if",
"s": 56.923,
"e": 57.083,
"confidence": 0.99902344,
"speaker": 0
},
{
"w": "you",
"s": 57.083,
"e": 57.163002,
"confidence": 1,
"speaker": 0
},
{
"w": "try",
"s": 57.163002,
"e": 57.323,
"confidence": 0.9941406,
"speaker": 0
},
{
"w": "this",
"s": 57.323,
"e": 57.483,
"confidence": 0.9951172,
"speaker": 0
},
{
"w": "at",
"s": 57.483,
"e": 57.643,
"confidence": 0.99902344,
"speaker": 0
},
{
"w": "home,",
"s": 57.643,
"e": 57.883,
"confidence": 0.99853516,
"speaker": 0
},
{
"w": "make",
"s": 57.883,
"e": 58.043,
"confidence": 1,
"speaker": 0
},
{
"w": "a",
"s": 58.043,
"e": 58.123,
"confidence": 1,
"speaker": 0
},
{
"w": "video",
"s": 58.123,
"e": 58.363,
"confidence": 1,
"speaker": 0
},
{
"w": "so",
"s": 58.363,
"e": 58.683002,
"confidence": 0.8339844,
"speaker": 0
},
{
"w": "I",
"s": 58.683002,
"e": 58.843002,
"confidence": 1,
"speaker": 0
},
{
"w": "can",
"s": 58.843002,
"e": 58.923,
"confidence": 1,
"speaker": 0
},
{
"w": "react",
"s": 58.923,
"e": 59.243,
"confidence": 1,
"speaker": 0
},
{
"w": "to",
"s": 59.243,
"e": 59.323,
"confidence": 1,
"speaker": 0
},
{
"w": "it.",
"s": 59.323,
"e": 59.563,
"confidence": 1,
"speaker": 0
},
{
"w": "Good",
"s": 59.563,
"e": 59.803,
"confidence": 1,
"speaker": 0
},
{
"w": "luck.",
"s": 59.803,
"e": 60.043,
"confidence": 0.9995117,
"speaker": 0
}
],
"silences": [],
"loudness": {
"integrated": -14.2,
"truePeak": 2.3,
"range": 2.9
}
},
"music": {
"songs": [
{
"label": "A",
"pieces": [
{
"s": 0,
"e": 60
}
],
"seconds": 60,
"tempo": 123,
"key": "G major",
"keyConfidence": 0.32,
"recognition": null,
"text": "medium-tempo electronic track with synthesizers, bass, and electronic percussion, with no vocals"
}
],
"beats": [ 0.12, 0.58, 1.07, 1.51, 1.97, 2.41, 2.9, 3.41, 3.9, 4.37, 4.81, 5.34, 5.87, 6.41, 6.92, 7.41, 7.92, 8.48, 9.03, 9.57, 10.05, 10.54, 11.03, 11.54, 12.05, 12.52, 12.98, 13.49, 14, 14.47, 14.95, 15.44, 15.93, 16.37, 16.83, 17.3, 17.72, 18.13, 18.58, 19.02, 19.48, 19.99, 20.5, 20.99, 21.48, 21.99, 22.5, 22.96, 23.41, 23.89, 24.4, 24.92, 25.4, 25.87, 26.31, 26.73, 27.17, 27.61, 28.07, 28.54, 28.96, 29.4, 29.86, 30.37, 30.91, 31.39, 31.86, 32.37, 32.79, 33.3, 33.76, 34.27, 34.71, 35.2, 35.71, 36.25, 36.76, 37.22, 37.71, 38.24, 38.71, 39.17, 39.59, 40.05, 40.5, 40.98, 41.47, 41.98, 42.45, 42.91, 43.35, 43.86, 44.3, 44.77, 45.21, 45.7, 46.21, 46.72, 47.25, 47.74, 48.23, 48.74, 49.3, 49.78, 50.27, 50.76, 51.29, 51.76, 52.27, 52.76, 53.29, 53.78, 54.27, 54.73, 55.19, 55.66, 56.05, 56.52, 57.07, 57.56, 58.05, 58.51, 58.98, 59.47 ]
},
"events": [
{
"t": 0,
"e": 51.2,
"kind": "scene",
"text": "scene 1: studio with silver foil backdrop"
},
{
"t": 0,
"e": 13.7,
"kind": "speech",
"text": "A: Hi, beautiful. I'm gonna show you a completely new way to easily cut your own curtain bangs at home. Let's call this one the Bramondo curtain bang. I'm gonna get into trouble, aren't I? All you need is hair cutting scissors, a comb, a couple elastics, and a head of wet hair."
},
{
"t": 0,
"e": 60,
"kind": "music",
"text": "medium-tempo electronic track with synthesizers, bass, and electronic percussion, with no vocals"
},
{
"t": 1,
"kind": "cut",
"text": "cut, to: close-up of the mannequin hair being combed"
},
{
"t": 1.9,
"kind": "cut",
"text": "cut, to: clipping back the sides of the mannequin hair"
},
{
"t": 2.8,
"kind": "cut",
"text": "cut, to: A demonstrating the two sections pulled outward"
},
{
"t": 4.2,
"kind": "cut",
"text": "cut, to: close-up of the elastic band on the hair section"
},
{
"t": 5.4,
"kind": "cut",
"text": "cut, to: A cutting the secured strand with scissors"
},
{
"t": 5.9,
"kind": "cut",
"text": "punch-in, to: punch-in on the scissors finishing the cut"
},
{
"t": 6.7,
"kind": "cut",
"text": "punch-out, to: punch-out as A throws away the cut hair"
},
{
"t": 8.6,
"kind": "cut",
"text": "cut, to: close-up of the hair cutting scissors"
},
{
"t": 9.9,
"kind": "cut",
"text": "punch-out, to: A showing the purple styling comb"
},
{
"t": 11,
"kind": "cut",
"text": "punch-in, to: close-up of the clear elastic band"
},
{
"t": 12,
"kind": "cut",
"text": "cut, to: close-up of the wet hair on the mannequin"
},
{
"t": 13.2,
"kind": "cut",
"text": "cut, to: combing the middle part on the mannequin"
},
{
"t": 13.7,
"e": 35.32,
"kind": "speech",
"text": "A: First, you're gonna part your hair in the middle or wherever you usually part your hair. Then we're gonna make two little triangle sections on the front of the hairline going from about two inches back from the front of the hairline down to the side of the end of the eyebrow. Next, you're gonna comb that section to the opposite side. After that, put in an elastic and pull the elastic down to about the corner of your mouth. Next, cut the hair."
},
{
"t": 14.3,
"kind": "cut",
"text": "punch-out, to: separating the crown hair sections"
},
{
"t": 16.1,
"kind": "cut",
"text": "cut, to: lifting top hair to create front section"
},
{
"t": 16.9,
"kind": "cut",
"text": "cut, to: A pointing with comb and explaining the sectioning"
},
{
"t": 20.3,
"kind": "cut",
"text": "cut, to: measuring two inches back with the comb"
},
{
"t": 21.2,
"kind": "cut",
"text": "cut, to: sectioning diagonally to the eyebrow"
},
{
"t": 23.2,
"kind": "cut",
"text": "cut, to: securing side hair with clip"
},
{
"t": 24.9,
"kind": "cut",
"text": "cut, to: drawing second triangle section on opposite side"
},
{
"t": 26.4,
"kind": "cut",
"text": "cut, to: clipping back the second side section"
},
{
"t": 28.8,
"kind": "cut",
"text": "punch-in, to: punch-in on the clipped mannequin head"
},
{
"t": 30.8,
"kind": "cut",
"text": "cut, to: combing the front triangle sections smooth"
},
{
"t": 31.9,
"kind": "cut",
"text": "cut, to: view of the two front triangle sections"
},
{
"t": 32.8,
"kind": "cut",
"text": "cut, to: A standing behind mannequin explaining crossover step"
},
{
"t": 33.7,
"kind": "cut",
"text": "cut, to: combing the hair section to the opposite side"
},
{
"t": 34.2,
"kind": "cut",
"text": "punch-in, to: punch-in on the crossed-over hair held in fingers"
},
{
"t": 35,
"kind": "cut",
"text": "cut, to: final comb stroke through crossed section"
},
{
"t": 35.32,
"e": 48.02,
"kind": "speech",
"text": "A: Beautiful. And we'll do the same thing on the opposite side. Pull the section over, put an elastic in, cut the hair. That is literally it. If you wanna also have some face framing layers, which I always recommend, it looks great with curtain bangs, do that now."
},
{
"t": 35.6,
"kind": "cut",
"text": "cut, to: wrapping elastic band around the hair strand"
},
{
"t": 37.3,
"kind": "cut",
"text": "punch-in, to: punch-in on sliding the elastic to the mouth level"
},
{
"t": 38.8,
"kind": "cut",
"text": "cut, to: fine-tuning the elastic position"
},
{
"t": 40,
"kind": "cut",
"text": "cut, to: view of the secured hair strand ready to cut"
},
{
"t": 41,
"kind": "cut",
"text": "cut, to: pointing to the elastic band cutoff point"
},
{
"t": 42,
"kind": "cut",
"text": "cut, to: A cutting the hair below the elastic band"
},
{
"t": 43.7,
"kind": "cut",
"text": "cut, to: A tossing cut hair and speaking to camera"
},
{
"t": 47.7,
"kind": "cut",
"text": "cut, to: combing the second section to the opposite side"
},
{
"t": 48.02,
"e": 55.24,
"kind": "speech",
"text": "A: And this one's hard to explain, so just look at what I'm doing and try to copy it. Now I'll blow dry the hair and voila. Oh my god. It's gorgeous. So easy to do."
},
{
"t": 50.6,
"kind": "cut",
"text": "cut, to: holding the crossed strand with comb"
},
{
"t": 51.2,
"e": 59.95,
"kind": "scene",
"text": "scene 2: studio with silver foil backdrop"
},
{
"t": 53.3,
"kind": "cut",
"text": "wipe, to: cutting the second section below the elastic"
},
{
"t": 55.1,
"kind": "cut",
"text": "cut, to: releasing the cut curtain bangs on the mannequin"
},
{
"t": 55.24,
"e": 60.04,
"kind": "speech",
"text": "A: It looks stunning. I'm obsessed. And if you try this at home, make a video so I can react to it. Good luck."
},
{
"t": 56.4,
"kind": "cut",
"text": "cut, to: A pointing at the cut bangs and explaining layers"
},
{
"t": 58.2,
"kind": "cut",
"text": "cut, to: combing the side face-framing section"
},
{
"t": 59,
"kind": "cut",
"text": "cut, to: slide cutting down the face-framing strand"
},
{
"t": 59.6,
"kind": "cut",
"text": "cut, to: completing slide cut down to the ends"
}
]
}Paste the file into an assistant and ask about the video.
The file on a timeline
measuredobservedmixedderivedBars are spans. Thin marks are instants.
Questions answered from the file
How fast is it cut?
Watched curtain-bangs.mp4 (22s · 18,000 tokens)
I would have to count the cuts while watching.
Read curtain-bangs.mp4.analyzemedia (0.9s · 13,000 tokens)
43 cuts in 60 seconds, about 43 per minute, with a mean shot of 1.36 seconds. There are two scenes in the same studio: the demonstration from 0 to 51.2 seconds, then the reveal from 51.2 to 59.95.
What are the steps he describes?
Watched curtain-bangs.mp4 (22s · 18,000 tokens)
Let me listen to it again.
Read curtain-bangs.mp4.analyzemedia (0.9s · 13,000 tokens)
Part the hair in the middle, make two triangle sections at the front, cross each one over to the opposite side, secure it with an elastic at mouth level, cut below the elastic, then slide cut down the sides and blow dry. The transcript has one speaker, A, from 0 to 60 seconds.
Does it use captions or a known sound?
Watched curtain-bangs.mp4 (22s · 18,000 tokens)
I would need to check the audio and the screen.
Read curtain-bangs.mp4.analyzemedia (0.9s · 13,000 tokens)
The file records no captions and no overlays. One music track runs the whole 60 seconds: 123 BPM, G major, no vocals, and no match in the recognition catalog.
The same file as plain text
The API also returns a text rendering of the analysis for a model to read. This is the busker clip in that format.
VIDEO ANALYSIS berlin-busker.mp4
schema 1 · sha256 41a53ab67b1058da… · 50.3 MB
FILE (measured)
duration 03:33.7 (213.69s)
video h264 1280x720, 29.97 fps, 1.7 Mb/s, yuv420p, bt709
audio aac 2ch 44100 Hz, 128 kb/s
AUDIO (measured)
loudness -15.9 LUFS integrated, peak 0 dBFS, range 4.8 LU
silences 0
speech 14.8s in 1 utterances, 1 speaker, ru, 1 words, 0 fillers (deepgram nova-3)
PEOPLE (observed by video pass; only the subjects get labels)
A Young woman with dirty-blonde hair tied back in a low bun, wearing a grey sleeveless button-up mini dress and flat brown sandals, playing an acoustic guitar and singing into a stand microphone.
voices: speaker 0 = A
THE VIDEO (observed by video pass)
On a pedestrianized city street, a female busker (Person A) stands behind a microphone and performs with an acoustic guitar. Pedestrians walk past, some cycling and some dropping money into her open guitar case, while a man in a white shirt and black trousers watches from the right sidewalk. She continues singing and playing her acoustic guitar throughout the entire performance.
music: song A, 112.3 bpm, C# major, 00:00.0–01:00.0, 01:00.0–02:45.0
music: song B, 112.3 bpm, C# major, 02:45.0–03:34.0
SCENES 1 (consecutive shots at one place; place and description observed by the video pass, everything measured is marked)
═══ scene 1 00:00.0–03:33.7 (213.7s) · unknown place · shots 1
camera (measured)
00:00.0–03:33.7 shot 1 opens handheld; tilt down 6.5%/s 00:00.2–00:01.5; tilt down 17.2%/s 00:07.6–00:10.4; tilt up 18.4%/s 00:10.5–00:12.5; occlusion 00:08.0–00:08.4; occlusion 01:24.1–01:25.3; occlusion 01:44.3–01:45.6 · medium, eye level, normal lens (observed)
what happens (observed)
00:00.0–03:33.7 A performs music on the street [A]: A stands in place holding her acoustic guitar, strumming and singing into the stand microphone. She looks toward the audience and down at her instrument as passersby walk through the scene. She continues to sing and accompany herself on guitar until the clip concludes. — camera: Handheld eye-level shot steadily zooming in slightly on A.
00:00.0 begins: A is seen playing guitar and singing on the sidewalk.
01:34.5 other: A woman in a green dress bends down to put money in the guitar case.
02:49.0 other: A man in shorts walks past and tosses coins into the guitar case.
said (transcript, measured in time)
00:58.8–01:13.6 A: И
on screen
00:00.0–03:33.7 scene text: "Alice Hills" [observed]
00:00.0–03:33.7 scene text: "BERLIN WALKING TOURS" [observed]
around the subjects
00:08.0–00:12.5 foreground: A cyclist and a pedestrian walk directly in front of the camera, briefly obstructing the view.
01:24.0–01:25.5 foreground: A woman in a striped shirt walks past directly in front of the lens.
01:44.0–01:46.0 foreground: A woman in a white cardigan walks across the foreground.
01:52.0–03:33.7 background: A man dressed in a white collared shirt and dark trousers leans against a barrier to the right.
SHOT DETAILS 1 (the per-shot form and measurements, for reference)
shot 1 00:00.0–03:33.7 (213.7s)
framing medium, eye level, normal lens, deep depth of field
camera handheld, jitter 0.0023, zoom in 1.564x; frame change 0.151; tilt down 6.5%/s 00:00.2–00:01.5; tilt down 17.2%/s 00:07.6–00:10.4; tilt up 18.4%/s 00:10.5–00:12.5; occlusion 00:08.0–00:08.4; occlusion 01:24.1–01:25.3; occlusion 01:44.3–01:45.6 (measured)
observed camera zoom in, handheld
colour #707070 #505050 #303030 #907070, neutral (0.048), saturation 0.172, mid, luma 0.412, contrast 0.177
light soft, key flat, daylight, exterior, day
picture sharpness 1903, clipped 0.024, crushed 0.004
setting pedestrian street
people A medium center, faces camera, eyeline camera, speaking
objects acoustic guitar, microphone stand, amplifier, guitar case, red and white barrier, bicycles, car
text "Alice Hills" bottom; "BERLIN WALKING TOURS" right
clothing Grey sleeveless button-front mini dress and brown flat sandals.
compose Centered framing on the busker with ample headroom and street depth visible in the background.
behind Paved street with parked bicycles, a red-and-white construction barrier, commercial storefronts, passing cars, and pedestrians.
frame A female street musician stands centered on a paved urban pedestrian street, playing acoustic guitar and singing into a microphone. Pedestrians and cyclists occasionally pass in front of and behind her while she performs.
· A sign bearing 'Alice Hills' rests on the ground beside an amplifier and open guitar case.
· A blue passenger car is parked in the street behind the barrier.
HEARD (observed by the audio pass on the full-resolution track)
00:00.0–03:33.7 music: medium tempo synth-pop track featuring electronic percussion, synthesizers, bass, and female singing vocals
A female vocalist sings over a medium tempo synthesizer and electronic percussion arrangement throughout the audio.
MUSIC (2 distinct songs, 214s with music; librosa (hpss, chroma, mfcc, beat tracking); presence given (music presence observed by the audio pass); properties measured here)
song A 112.3 bpm · C# major (confidence 0.84) · 165s · 00:00.0–01:00.0, 01:00.0–02:45.0
not in the recognition catalogue (ACRCloud); library or royalty-free music, or too quiet under the voice
song B 112.3 bpm · C# major (confidence 0.87) · 49s · 02:45.0–03:34.0
not in the recognition catalogue (ACRCloud); library or royalty-free music, or too quiet under the voice
beats 388 (first 0.16 0.72 1.25 1.79 2.32 2.83 3.37 3.90…)
TRANSCRIPT (paragraphs and sentences as segmented by the transcription service; times measured)
00:58.8–01:13.6 A
00:58.8–01:13.6 И
MERGED TIMELINE (everything, in time order: time, kind, what, producer)
00:00.0 cut shot 1: medium, zoom in, 1 person [geometry]
00:00.0 scene pedestrian street, exterior, day [shots]
00:00.0 person A center, looks at camera, speaking [shots]
00:00.0 moment begins: A is seen playing guitar and singing on the sidewalk. [video]
00:00.0–03:33.7 text scene text: "Alice Hills" [video]
00:00.0–03:33.7 text scene text: "BERLIN WALKING TOURS" [video]
00:00.0–01:00.0 music music: song A, 112.3 bpm, C# major [music]
00:00.0–03:33.7 action A performs music on the street [A]: A stands in place holding her acoustic guitar, strumming and singing into the stand microphone. She looks toward the audience and down at her instrument as passersby walk through the scene. She continues to sing and accompany herself on guitar until the clip concludes. [video]
00:00.2–00:01.5 move tilt down 6.5 % of height per s [geometry]
00:07.6–00:10.4 move tilt down 17.2 % of height per s [geometry]
00:08.0–00:08.4 move occlusion, up to 10% of the matches [geometry]
00:08.0–00:12.5 environment foreground: A cyclist and a pedestrian walk directly in front of the camera, briefly obstructing the view. [video]
00:10.5–00:12.5 move tilt up 18.4 % of height per s [geometry]
00:58.8–01:13.6 speech A: "И" [transcript]
01:00.0–02:45.0 music music: song A, 112.3 bpm, C# major [music]
01:24.0–01:25.5 environment foreground: A woman in a striped shirt walks past directly in front of the lens. [video]
01:24.1–01:25.3 move occlusion, up to 12% of the matches [geometry]
01:34.5 moment other: A woman in a green dress bends down to put money in the guitar case. [video]
01:44.0–01:46.0 environment foreground: A woman in a white cardigan walks across the foreground. [video]
01:44.3–01:45.6 move occlusion, up to 9% of the matches [geometry]
01:52.0–03:33.7 environment background: A man dressed in a white collared shirt and dark trousers leans against a barrier to the right. [video]
02:45.0–03:34.0 music music: song B, 112.3 bpm, C# major [music]
02:49.0 moment other: A man in shorts walks past and tosses coins into the guitar case. [video]
03:33.7 moment ends: The performance take cuts out. [video]
PRODUCERS
ffmpeg ffmpeg 8 (scene select, silencedetect, ebur128) + pixel statistics
geometry OpenCV ORB keypoints + RANSAC similarity between consecutive proxy frames: cuts, punch-ins, camera support, pans, tilts, zooms
transcript deepgram nova-3
video gemini-3.7-flash, agentic media processing, with the cut list, transcript, place and time as context, asked as video/footage ({"promptTokenCount":1124,"candidatesTokenCount":1854,"thoughtsTokenCount":521,"toolUsePromptTokenCount":17269,"calls":1})
audioPass gemini-3.7-flash, audio only, full audio resolution ({"promptTokenCount":5418,"candidatesTokenCount":102,"thoughtsTokenCount":491,"toolUsePromptTokenCount":0,"calls":1})
music librosa (hpss, chroma, mfcc, beat tracking); presence given (music presence observed by the audio pass); properties measured here
recognitionACRCloud identify, 4 lookups of 12 s excerpts
timings probe 0.1s, place and time 0s, proxies 19.1s, cuts 0.5s, geometry 34.5s, shots 0.2s, audio 0.5s, deepgram 2.1s, audio pass 5.7s, video pass 48.1s, music 11.6s, recognise 12.1s
COST (per call, at list prices)
transcript deepgram nova-3 3.56 min $0.0153
video pass gemini-3.7-flash 1 call, 1,124 in + 17,269 tool, 1,854 out + 521 thinking $0.0227
audio pass gemini-3.7-flash 1 call, 5,418 in, 102 out + 491 thinking $0.0063
music recognition acrcloud identify 4 lookups $0.0000 (billed per ACRCloud plan, not priced here)
ffmpeg, geometry, pixels, geocoding local / free $0.0000
total $0.0124 per minute of video $0.0443
list prices, 2026-09 (Gemini Flash $0.75 in / $3.75 out per M tokens, thoughts billed as output; Deepgram Nova-3 $0.0043/min)