Podcast Clip — Versely

The recipe

Reference images

The 1 reference asset every scene below draws character, product or set continuity from.

Podcast host

character

Photorealistic 9:16 portrait of the podcast host in her studio — used as the character reference for both clips.

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

   Hook — income tease

   8s
   Uses: Podcast host

   “You won't believe how much money I've been making lately — and I'm not even working more. I literally stopped hiring editors and designers for my content.”

   Image prompt

   A photorealistic 25-year-old American woman sitting in a cozy podcast studio. Warm, friendly girl-next-door look. Soft oval face, light golden-tan skin with natural texture and a few faint freckles across the nose, warm hazel eyes, naturally full eyebrows, soft genuine smile with slightly imperfect natural teeth. Medium-length warm chestnut-brown hair in a relaxed low bun with a few loose face-framing strands. Minimal natural makeup, subtle gold hoop earrings, a thin dainty necklace. Wearing a cream ribbed tank top under an open soft beige oversized cardigan, relaxed and casual. Sitting comfortably on a soft chair, leaning slightly toward a large black studio microphone on a boom arm in the foreground. Background is a modern cozy podcast studio: warm ambient circular wall light glowing soft amber, a tall green plant softly out of focus, neutral beige tones, subtle acoustic panels. Soft cinematic lighting, warm golden key light on her face, gentle shadows. Vertical 9:16 framing, mid-shot from chest up, shallow depth of field with creamy bokeh. Ultra photoreal skin detail, natural color grade, candid authentic expression, 4K. Negative prompt: cartoon, anime, illustration, CGI, 3D render, plastic skin, over-smoothed, airbrushed, over-saturated, distorted face, extra fingers, asymmetric eyes, text, watermark, logo, deformed mic.

   Video prompt

   A photorealistic 25-year-old American woman sitting in a cozy podcast studio, exactly matching the reference image: brown hair in a soft low updo with loose face-framing strands, gold hoop earrings, thin gold necklace, cream ribbed tank top under an oatmeal oversized knit cardigan slipping off one shoulder, dark pants, seated on a soft light couch, a black studio microphone on a boom arm in the foreground to her right, a warm circular glowing wall light behind her, a tall green plant softly out of focus on the right. She is talking naturally and warmly into the microphone. Natural relaxed lip-sync matched to the voiceover, subtle realistic mouth and jaw movement. Expressive but calm podcast delivery: gentle confident smile, light natural head tilts and nods, soft blinking, relaxed shoulders, occasional small hand gesture near her lap. The leaves of the background plant sway very slightly. Warm ambient lighting stays steady, soft golden glow on her face. Camera is locked on a tripod with an extremely subtle slow push-in, static podcast-clip framing, vertical 9:16, shallow depth of field with creamy bokeh. Ultra photoreal skin texture, natural color grade, candid authentic expression, 4K, cinematic. Realistic human motion only, smooth and natural. Negative prompt: cartoon, anime, illustration, CGI, 3D render, plastic skin, over-smoothed, distorted face, warped mouth, bad lip-sync, extra fingers, deformed hands, asymmetric eyes, jitter, fast jerky motion, morphing, floating objects, text, watermark, logo, changing outfit, identity change.

2. 2

   Reveal — Versely

   8s
   Uses: Podcast host

   “I just use this one app — Versely. I type what I want and it makes the entire video for me. People think I'm exaggerating… I'm really not.”

   Image prompt

   Same 25-year-old woman and same cozy podcast studio as scene 1 — brown hair in a soft low updo with loose face-framing strands, gold hoop earrings, thin gold necklace, cream ribbed tank top under an oatmeal oversized knit cardigan slipping off one shoulder, dark pants. Seated on the same soft light couch, black studio microphone on a boom arm in the foreground to her right, warm circular glowing wall light behind her, tall green plant softly out of focus on the right. Vertical 9:16 mid-shot from chest up, shallow depth of field with creamy bokeh, ultra photoreal skin detail, warm golden key light, natural color grade, candid authentic expression, 4K.

   Video prompt

   A photorealistic 25-year-old American woman sitting in a cozy podcast studio, exactly matching the reference image: brown hair in a soft low updo with loose face-framing strands, gold hoop earrings, thin gold necklace, cream ribbed tank top under an oatmeal oversized knit cardigan slipping off one shoulder, dark pants, seated on a soft light couch, a black studio microphone on a boom arm in the foreground to her right, a warm circular glowing wall light behind her, a tall green plant softly out of focus on the right. She continues talking naturally and warmly into the microphone. Natural relaxed lip-sync accurately matched to the voiceover, realistic mouth and jaw movement. Expressive but calm podcast delivery: warm confident smile while explaining, a light hand gesture near her lap, natural head tilts and nods, soft blinking, then her expression softens into a sincere relaxed smile on the last line. The background plant leaves sway very slightly. Warm ambient lighting stays steady, soft golden glow on her face. Camera locked on a tripod with an extremely subtle slow push-in, static podcast-clip framing, vertical 9:16, shallow depth of field with creamy bokeh. Ultra photoreal skin texture, natural color grade, candid authentic expression, 4K, cinematic. Realistic human motion only, smooth and natural. Negative prompt: cartoon, anime, illustration, CGI, 3D render, plastic skin, over-smoothed, distorted face, warped mouth, bad lip-sync, extra fingers, deformed hands, asymmetric eyes, jitter, fast jerky motion, morphing, floating objects, text, watermark, logo, changing outfit, identity change.

Frequently asked questions

Related workflows

Build it with