NYC Street Interview

The recipe

Reference images

The 4 reference assets every scene below draws character, product or set continuity from.

Riley (Interviewer)

character

Photorealistic 30-year-old American woman on a busy NYC sidewalk holding a handheld mic — shoulder-length wavy chestnut brown hair, hazel-brown eyes, light freckles, beauty mark above the left lip, unzipped medium-wash denim jacket over a fitted black graphic tee, dark blue high-waisted straight-leg jeans, white low-top sneakers, small gold hoop earrings. Generated first and reused as the interviewer reference in every shot.

Kai (Stranger #1)

character

Photorealistic 27-year-old Asian-American man — messy black hair under a faded heather-grey beanie, light patchy beard, dark grey-black geometric tattoo sleeves, oversized washed-burgundy hoodie, baggy black cargo pants, scuffed white Converse, iced cold-brew coffee in hand. Stranger #1 reference.

Maya (Stranger #2)

character

Photorealistic 32-year-old Black-American woman — sleek shoulder-length dark brown hair with warm highlights, tailored deep camel-tan blazer over an ivory silk shell, slim black tailored ankle trousers, pointed-toe black pumps, tan leather tote and takeaway coffee. Stranger #2 reference.

Marco (Stranger #3)

character

Photorealistic 29-year-old Latino-American man — muscular athletic build, short dark brown hair in a low fade, well-groomed stubble, heather-grey athletic tee with an unzipped black technical jacket, black tapered joggers, chunky running sneakers, protein shaker in hand. Stranger #3 reference.

Scene-by-scene breakdown

Every image prompt, video prompt and voiceover line used to build this video, in order. Copy any block and swap in your own subject.

1. 1

   Kai — Abandoned Subway Story

   10s
   Uses: Riley (Interviewer)Uses: Kai (Stranger #1)

   Image prompt

   Candid documentary-style street interview photograph, vertical 9:16 orientation, NYC sidewalk setting at late afternoon golden hour. OTS (over-the-shoulder) street vlog framing. Riley — 30-year-old American woman with shoulder-length wavy chestnut brown hair, hazel-brown eyes, faint freckles, beauty mark above left lip, wearing the unzipped denim jacket over fitted black graphic tee, dark blue high-waisted straight-leg jeans, white sneakers — is partially visible at the LEFT EDGE of the frame from her shoulder/arm up, her right hand extended into the frame holding a small compact wireless handheld stick microphone — matte black sleek modern content-creator design with a small black foam ball windscreen on top, completely cable-free, no wire visible, comfortably gripped in her hand. Mic pointed toward Kai at chest height. Her face partially visible in three-quarter profile, lips slightly parted mid-question, warm friendly expression. MAIN SUBJECT center-frame: Kai — 27-year-old Asian-American man, messy black hair under a faded heather-grey beanie, light patchy beard with realistic uneven growth, dark brown eyes with natural asymmetry, faint dark under-eye shadows, visible skin pores and real skin texture, small scar near right eyebrow, warm-medium skin tone with faint cheek redness, no airbrushing. Wearing the oversized washed-burgundy hoodie with natural fabric creases and slight pilling, sleeves pushed up to forearms revealing detailed dark grey-black tribal/geometric tattoo sleeves with realistic ink fade and color variation, glimpse of black graphic tee at collar, baggy faded black cargo pants, scuffed white Converse Chuck Taylors, thin silver chain at neck, chunky black G-Shock watch on left wrist. Holding a clear plastic cup of iced cold-brew coffee with visible condensation in his left hand at hip height. Standing with weight on his left foot, casual slight slouch, body angled three-quarter toward Riley. Expression: mid-listen / about-to-answer — slight wry deadpan half-smile starting at one corner of his mouth, eyes glancing at Riley with quiet amusement, one eyebrow subtly raised. Background: recognizable NYC sidewalk — red-brick brownstone with black metal fire escapes, corner deli/coffee shop with faded signage, softly out-of-focus diverse pedestrians walking past, a yellow taxi blurred in motion mid-ground, black fire hydrant near the curb, stack of black trash bags pushed against the building, faint steam drifting from a subway grate, scattered dry leaves on the sidewalk. Late afternoon golden-hour sunlight slants in from camera-left bouncing warm uneven highlights off the brick walls, soft long shadows on the sidewalk. Real ambient daylight, no studio lighting, no rim light, no color gels, no glamour grading. Shot on Sony A7 IV, 35mm f/2.8, vertical 9:16 framing, shallow depth of field — Kai sharp, city softly blurred behind, faint natural film grain, real photojournalism aesthetic, candid mid-interview vibe. Real skin texture, real tattoo aging, real fabric wear, no AI-plastic look, no airbrushing, no smoothed skin.

   Video prompt

   Begin from the input frame — OTS street interview on a NYC sidewalk at golden hour. Riley stands partially visible on the left holding a black handheld mic extended toward Kai. Kai stands center-frame in burgundy hoodie and grey beanie. Camera holds steady with subtle natural handheld breath, an almost imperceptible drift — like a real iPhone or handheld DSLR shot by a content creator. 0-1.5s: Riley speaks from off-frame left in a warm friendly real American conversational voice — natural breath before the line, casual approachable energy, slight natural intonation lift on the word "wildest": "Hey — what's the wildest thing you've ever done?" Mic stays steady in frame. Kai listens, single natural blink, the corner of his mouth lifting subtly, eyes briefly flicking toward Riley. 1.5-9s: Kai answers. Slight casual shrug as he begins, eyes settle on Riley off-frame left. He delivers the line in a calm dry deadpan American conversational tone — real natural human voice with audible breath, throat catch, micro-pauses between phrases, slightly mumbled storytelling energy, real organic mouth shapes — NOT a polished voiceover read: "I broke into an abandoned subway station… lived down there for a week. Tattooed myself by flashlight." A barely-there knowing smirk lands fully on the final phrase. His left hand subtly raises the iced coffee a couple inches as he speaks, unconscious natural fidget. Background remains lively and authentic — softly blurred pedestrians continue walking past at natural unsynchronized rhythms, a yellow taxi drifts through the distant background, faint subway steam rises near the curb at right, golden-hour light flickers very subtly as people pass through it. Real urban audio bed underneath the dialogue — soft city traffic, a distant car honk, light footfall, faint conversation drift, ambient NYC murmur. CRITICAL VOICE DIRECTION — must sound 100% human, NOT AI voiceover. Both Riley and Kai must sound like real humans being filmed on the street with a hand mic. Natural breath, real throat sounds, slight verbal imperfections, real intonation variation, real human conversational cadence with micro-pauses, real emotion in the voice. Kai = slightly lower vocal register, dry deadpan Brooklyn-creative delivery with a hint of vocal fry, casual relaxed pace. Riley = warm bright friendly conversational lift, slightly higher register, no broadcast-perfect pronunciation. NO AI synthesizer cadence, NO robotic pacing, NO uniform smooth vowels, NO flat affect, NO over-enunciation, NO broadcast voiceover tone. Visible real skin texture preserved, real tattoo aging, natural micro-blinks (2-3 across the clip), natural weight shifts, slight subtle head movement during speech. Realistic handheld documentary cinematography. No robotic motion, no plastic skin, no synthetic smoothness, no over-perfect lip sync, no exaggerated theatrical gestures, no over-staged performance. Real street vlog energy — looks and sounds like a TikTok/Instagram street interview clip shot today on a real handheld setup.

2. 2

   Maya — The Boyfriend's Dad

   10s
   Uses: Riley (Interviewer)Uses: Maya (Stranger #2)

   Image prompt

   Candid documentary-style street interview photograph, vertical 9:16 orientation, NYC sidewalk at late afternoon golden hour. OTS (over-the-shoulder) street vlog framing. DIFFERENT CORNER LOCATION from previous shot — wider open sidewalk with a NYC corner bodega/produce stand visible in the mid-background (wooden crates of fresh fruit and flowers spilling onto the sidewalk, hand-painted signage), a portion of metal sidewalk construction scaffolding visible at the left edge of the background (classic NYC construction sheds with green netting), a slightly different brownstone facade with greyer red-brown brick and white window trim, a faded green awning of a tailor/dry cleaner across the street. Riley — 30-year-old American woman, shoulder-length wavy chestnut brown hair, hazel-brown eyes, faint freckles, beauty mark above left lip, wearing the same unzipped denim jacket over fitted black graphic tee, dark blue high-waisted straight-leg jeans, white sneakers — partially visible at the LEFT EDGE of frame from her shoulder/arm up, right hand extended into frame holding her same black handheld microphone with a foam windscreen pointed toward Maya at chest height. Face partially visible in three-quarter profile, lips slightly parted mid-question, warm friendly expression. MAIN SUBJECT center-frame: Maya — 32-year-old Black-American woman, slim athletic build around 5'7" with heels. Sleek shoulder-length dark brown straight hair with subtle warm highlights catching the light, parted on the side, a few natural flyaways from city wind, glossy but not over-styled. Warm dark brown eyes with subtle natural asymmetry, faint laugh lines just starting at the outer corners, small natural beauty mark on right cheekbone, visible skin pores and real skin texture with faint sheen on T-zone, soft natural makeup, neutral matte lip, no airbrushing. Warm brown skin with healthy natural undertones, faint cheek redness from being outdoors. Expression — subtle mischievous half-smile at one corner of her mouth, one eyebrow raised slightly with knowing amusement, eyes alive and confident as if about to share something unexpected, head tilted slightly toward Riley, "you have no idea" energy. Wearing the tailored deep camel-tan single-button blazer with natural fabric creases over a fitted ivory silk shell with a delicate small gold pendant necklace at her collarbone, slim-fit black tailored ankle trousers, pointed-toe black leather pumps with realistic scuff marks, small gold hoop earrings, slim gold watch on left wrist, thin gold bangle. Holding a structured tan leather work tote bag in her left hand at her side and a NYC takeaway coffee cup with paper sleeve in her right hand at chest height, slightly raised mid-conversation. Standing confidently with weight on one foot, slight forward lean toward Riley. Background: the different NYC corner — softly out-of-focus diverse pedestrians walking past at natural unsynchronized rhythms, a yellow taxi mid-motion behind, a delivery cyclist crossing, a person with a tote bag, the produce stand with crates and flowers, scaffolding metal structure with green netting on the left, faint subway grate steam rising near the curb at right, scattered dry leaves on the sidewalk, a black fire hydrant. Late afternoon golden-hour sunlight slants from camera-left creating warm uneven highlights on the brick walls and long soft shadows. Real ambient daylight, no studio lighting, no rim light, no color gels, no glamour grading. Shot on Sony A7 IV, 35mm f/2.8, vertical 9:16 framing, shallow depth of field with Maya sharp and the city softly blurred, faint natural film grain, real photojournalism aesthetic, candid mid-interview vibe. Real skin texture, real fabric wear and creases, no AI-plastic look, no airbrushing, no smoothed skin.

   Video prompt

   OTS street interview, NYC sidewalk, golden hour. Riley partially visible left edge holding black mic toward Maya (center, tan blazer, white silk shell, dark straight hair, black trousers, pumps). Camera holds with subtle handheld breath, imperceptible drift toward Maya — real iPhone street vlog feel. 0-1.5s: Riley speaks off-frame left in a warm friendly real American conversational voice, natural breath, casual energy, slight lift on "wildest": "What's the wildest thing you've ever done?" Mic steady. Maya listens, natural blink, corner of mouth lifting into a knowing half-smile. 1.5-9s: Maya answers, casual confident posture. Delivers in a warm slightly amused American conversational tone — real human voice with breath, throat catch, micro-pauses, organic mouth shapes, NOT voiceover. Opens calm matter-of-fact, almost like she's reading a grocery list: "Hooked up with my boyfriend's dad." Small natural beat, quick knowing glance at Riley as the smirk grows, eyebrows lift slightly. Then with quiet pride, almost afterthought: "Married him a year later." Full mischievous smile lands on "year later," eyes crinkling, brief small laugh. Tote bag shifts subtly in her left hand. Background: softly blurred pedestrians, cyclist passes, yellow taxi drifts through, faint subway steam right, flower stand mid-ground, golden light flickering. Real NYC audio — soft traffic, distant honk, footfall, ambient murmur. CRITICAL VOICE — 100% HUMAN, NOT AI. Natural breath, throat sounds, verbal imperfections, real intonation variation, real cadence with micro-pauses, real emotion. Maya = mid-range warm conversational with confident amusement, unrushed pace, calm reveal energy. Riley = bright friendly lift. NO AI synth cadence, NO robotic pacing, NO uniform smooth vowels, NO flat affect, NO over-enunciation, NO voiceover tone. Real skin texture, 2-3 natural micro-blinks, natural weight shifts, subtle head movement. Handheld documentary cinematography. No plastic skin, no synthetic smoothness, no over-perfect lip sync, no exaggerated gestures, no staged performance. Real TikTok street interview vibe.

3. 3

   Marco — Running with the Bulls

   10s
   Uses: Riley (Interviewer)Uses: Marco (Stranger #3)

   Image prompt

   Candid documentary-style street interview photograph, vertical 9:16, NYC sidewalk at late afternoon golden hour. Two-shot framing with BOTH characters fully visible in the frame, standing about three feet apart on the sidewalk facing each other in three-quarter angles toward the camera. Riley on the LEFT — 30-year-old American woman, shoulder-length wavy chestnut brown hair with natural texture and visible flyaways, hazel-brown eyes with subtle natural asymmetry, faint freckles across her nose, small beauty mark above left lip, soft natural makeup, visible skin pores, no airbrushing. Wearing the unzipped medium-wash denim jacket with natural creases over a fitted black graphic tee, dark blue high-waisted straight-leg jeans, white low-top sneakers slightly scuffed, small gold hoop earrings, thin gold chain. Standing in three-quarter pose facing Marco, her right hand extended toward him holding the black handheld microphone with foam windscreen at his chest height. Warm friendly expression, lips slightly parted mid-question, eyes engaged on Marco, light laugh starting at the corner of her mouth. Marco on the RIGHT — 29-year-old Latino-American man, muscular athletic build, broad shoulders, around 5'11". Short dark brown hair in a clean low fade with textured top, naturally slept-in, a few damp strands at the hairline. Short well-groomed dark stubble with realistic uneven density. Warm dark brown eyes with subtle asymmetry, expressive thick eyebrows, small barely-visible scar on left brow, visible skin pores, faint natural sheen of sweat across his forehead, warm sun-tanned medium-brown skin, faint cheek redness, no retouching. Wide animated grin, eyes lit up mid-story, head pulled slightly back like he can't believe what he's saying. Wearing the fitted heather-grey athletic t-shirt with slight sweat marks, unzipped black lightweight technical jacket draped half off shoulders, fitted black tapered joggers, chunky white-and-grey running sneakers with realistic dirt on the soles, thin silver Cuban link chain at his neck, black Garmin sports watch on left wrist, small geometric tattoo visible on inner right forearm with realistic ink wear. Holding clear plastic shaker bottle with chocolate protein shake in his right hand at chest height, gesturing animatedly mid-line, left hand mid-gesture palm-up. Background: classic NYC halal food cart visible in the mid-background (silver mobile cart with bright yellow "HALAL" signage, faint smoke and steam rising from the grill, vendor in white apron working it), a wide crosswalk to the right with pedestrians mid-crossing, yellow traffic light on a pole, a different brick walkup with a hand-painted "PIZZA" awning visible on the left, a darker stretch of brownstone with shorter fire escapes than previous shots, a yellow taxi waiting at the light, softly out-of-focus pedestrians (guy with backpack, woman with stroller), faint subway grate steam at the right curb, scattered fall leaves on the cracked sidewalk. Late afternoon golden-hour sunlight slants from camera-left creating warm uneven highlights on the brick walls and long soft shadows. Real ambient daylight, no studio lighting, no rim light, no color gels, no glamour grading. Shot on Sony A7 IV, 35mm f/2.8, vertical 9:16 framing, shallow depth of field with both characters sharp and the city softly blurred behind, faint natural film grain, real photojournalism aesthetic, candid mid-interview vibe — looks like a real two-shot from a TikTok/Instagram street interview. Real skin texture, real sweat sheen, real fabric wear, real tattoo aging, no AI-plastic look, no airbrushing, no smoothed skin.

   Video prompt

   Two-shot street interview, NYC crosswalk corner, golden hour. Riley standing left in denim jacket holding black mic toward Marco. Marco standing right in grey tee, black jacket, protein shaker in right hand. Halal cart smoke and crosswalk behind both. Camera holds with subtle handheld breath, slight natural drift — real iPhone vlog feel. 0-1.5s: Riley speaks in a warm friendly real American conversational voice, natural breath, casual energy, mouth moving naturally, eyes on Marco, slight friendly smile: "What about you — wildest thing?" Mic steady. Marco listens, single blink, light smile starting one corner of mouth. 1.5-9.5s: Marco answers in a natural calm American conversational tone — real human voice with breath, throat texture, organic mouth shapes, like telling a friend a quick story, NOT performing, NOT voiceover: "Bro — I ran with the bulls in Spain. On a dare. Got tossed in the air, man. Went viral on Twitter. I have a scar." Straight through at natural pace, no dramatic beats, no laughing mid-line, no exaggerated facial movements, no hyped energy. Slight subtle smile on "scar," small natural shrug. Shaker stays steady, one small grip adjustment. Riley listens engaged, natural blink, faint amused smile growing. Background: softly blurred pedestrians at crosswalk, halal vendor with faint smoke, yellow taxi at light, woman with stroller, guy with backpack, golden light flickering. Real NYC audio — distant honk, halal sizzle, footfall, ambient murmur. CRITICAL VOICE — 100% HUMAN, NOT AI. Natural breath, throat sounds, verbal imperfections, real intonation, real grounded emotion. Marco = warm mid-low register, natural Latino-American conversational, calm confident delivery, NO performative excitement, NO mid-line laughing, NO theatrical pauses, NO overacting. Riley = bright friendly conversational lift. NO AI cadence, NO robotic pacing, NO flat affect, NO voiceover tone. Real skin texture, 2-3 natural micro-blinks per person, natural weight shifts, subtle head movement. Handheld documentary cinematography. No plastic skin, no synthetic smoothness, no over-perfect lip sync, no staged performance. Real TikTok street interview vibe — grounded, natural, calm.

Frequently asked questions

Related workflows

Build it with