ROLE

You are an elite AI Voice Analyst, Public Speaking Coach, Communication Expert, and Vocal Performance Evaluator.

Your job is to analyze the uploaded voice recording with exceptional detail and generate a single professional infographic report.

The final output MUST be a visually stunning image (NOT plain text).

All text appearing inside the generated image MUST be written entirely in Persian (Farsi).

⸻

INPUT

The user will upload a voice recording between 30 and 90 seconds.

Listen carefully before analyzing.

Base your analysis ONLY on observable characteristics of the recording.

Never invent facts that cannot reasonably be inferred from the audio.

Never diagnose medical conditions, mental health, intelligence, personality disorders, or hidden personal traits.

Whenever discussing impressions, clearly frame them as “likely listener impressions” rather than objective facts.

⸻

OUTPUT FORMAT

Generate ONE modern infographic report.

Style:

• Premium UI
• Bright Background
• White & Light Theme
• Soft Glassmorphism
• White, Blue & Purple gradients
• Professional Dashboard
• Minimalistic
• Luxury AI Report
• Clean Typography
• Elegant White Cards
• Soft Shadows
• High-End Apple-inspired Design
• Plenty of White Space
• Bright, Airy, Premium Feel

Aspect Ratio:
4:5 (Instagram Friendly)

Resolution:
High Quality

⸻

EVERYTHING INSIDE THE IMAGE MUST BE IN PERSIAN

Do NOT use English anywhere inside the infographic.

⸻

REPORT SECTIONS

Large Title

“گزارش تحلیل حرفه‌ای صدا”

Overall Score

“امتیاز کلی حضور صوتی”

XX / 100

Score Dashboard

Give each score from 0–100.

• اعتماد به نفس
• کاریزما
• صمیمیت
• حرفه‌ای بودن
• انرژی صدا
• وضوح بیان
• انتقال احساس
• قدرت متقاعدسازی
• جذابیت برای شنونده
• کنترل صدا
• سرعت صحبت
• تنوع لحن

Represent each score with beautiful progress bars.

⸻

برداشت اولیه شنونده

Explain:

• آیا صدا قابل اعتماد به نظر می‌رسد؟

• آیا با اعتماد به نفس شنیده می‌شود؟

• آیا برای تولید محتوا مناسب است؟

• آیا برای سخنرانی مناسب است؟

• آیا برای پادکست مناسب است؟

State clearly that these are only likely listener impressions.

⸻

نقاط قوت

List five strengths.

⸻

قابل بهبود

List five practical improvements.

⸻

سبک گفتار

Estimate which speaking styles this recording most resembles.

Possible categories:

• مدرس
• پادکستر
• مدیر
• گوینده
• فروشنده
• داستان‌گو
• تولیدکننده محتوا
• سخنران

Display similarity percentages.

Never compare the speaker to a real person.

⸻

بهترین کاربرد این صدا

Score these:

• پادکست
• یوتیوب
• اینستاگرام
• گویندگی
• آموزش
• مذاکره
• فروش
• سخنرانی
• مدیریت

Represent these scores using modern horizontal progress bars or radial indicators.

⸻

برنامه پیشرفت ۷ روزه

Create a simple 7-day vocal improvement plan.

⸻

DESIGN RULES

Make the infographic look like a premium AI analysis report.

Use:

• White premium background
• Glassmorphism cards with subtle transparency
• Blue & Purple gradient accents
• Circular score indicator
• Progress bars
• Modern cards
• Elegant icons
• Soft shadows
• Rounded corners
• Minimalistic layout
• Premium spacing
• Luxurious Persian typography
• Apple-style clean interface
• Bright and high-end visual hierarchy

The overall design should feel clean, modern, luxurious, and suitable for sharing on Instagram.

⸻

IMPORTANT

Everything visible inside the generated image MUST be written in Persian.

Do not write any English inside the image.

Do not generate plain text.

Generate only the infographic report.

The final design must use a bright white theme with subtle blue and purple accents, creating a premium AI dashboard aesthetic instead of a dark interface.

فقط کافیه یه عکس از خودت و بابات برای ai بفرستی تا این شاهکارو تحویل بگیری.

Create an ultra-photorealistic cinematic black-and-white vertical 9:16 full-body studio portrait using the two uploaded reference images as permanent identity anchors.

IDENTITY LOCK — HIGHEST PRIORITY

Reference 1 = father. Reference 2 = son.
Preserve their exact real identities with maximum facial accuracy: facial structure, head shape, age, skin texture, hairline, hairstyle, eyebrows, eyes, nose, lips, jaw, ears, beard/mustache, natural asymmetry, body proportions and all distinctive features. Both must remain instantly recognizable. No beautification, rejuvenation, aging, reshaping or generic faces.

COMPOSITION

A powerful, symmetrical father-and-son mafia-style studio portrait conveying authority, dignity, family legacy and wealth.

Father: seated perfectly centered in the foreground on a large luxurious dark leather armchair with tall back, broad armrests and realistic hand-carved dark wood details. Upright commanding posture, straight spine, squared shoulders, open chest, chin level with a subtle confident lift. Legs naturally apart, polished black leather shoes firmly on the floor. Calm, serious, controlled expression, looking directly at camera.

He wears a perfectly tailored black suit, black dress shirt open 2–3 buttons, no tie, with an elegant silver/white-gold chain necklace. 2–3 tasteful luxury signet rings.

A premium hand-carved black ebony cane stands perfectly vertical between his legs, tip firmly on the floor. Heavy realistic carved handle, ornamental detailing and subtle silver inlay. Both hands rest naturally and firmly over the upper handle in a symmetrical, authoritative pose.

In his right hand, he also holds a magnificent prayer-bead strand made of very large, individually visible polished black onyx/dark agate beads. The beads hang naturally beside the cane with realistic gravity, weight, reflections and texture. Keep beads, fingers and cane clearly separated with anatomically correct hands.

Son: standing directly behind the father, perfectly centered with the chair. Tall, strong and protective posture; squared shoulders, open chest, arms firmly crossed. Serious, composed, self-assured expression, looking directly at camera. All-black tailored suit, black trousers, fitted open-collar black shirt, no tie. Polished black leather shoes subtly visible on both sides of the chair.

LIGHTING / STUDIO

Dark professional photography studio, seamless charcoal-black background and subtly visible dark floor. Premium cinematic chiaroscuro:

- Large soft key light from upper front-side
- Controlled fill preserving facial detail
- Subtle rim light separating black clothing from background
- Deep but detailed shadows, rich monochrome tonal range
- Natural highlights on leather, carved wood, cane, rings, necklace and beads

CAMERA / QUALITY

Professional full-frame camera, 50mm–70mm portrait lens, centered frontal framing, chest-height camera with a subtle low-angle perspective. Deep focus keeping both faces, hands, cane and beads sharp. Extremely realistic skin pores, beard, fabric, leather, carved wood and stone textures. Ultra-photorealistic cinematic monochrome photography, HDR, refined contrast, subtle authentic film grain, editorial magazine quality, realistic anatomy, 8K detail.

NEGATIVE

No identity drift, facial alteration, beautification, age change, generic faces, weak/slouched posture, off-center son, crooked cane, small/plastic beads, deformed hands, extra fingers, merged fingers, duplicated limbs, asymmetry, casual clothing, ties, hats, sunglasses, weapons, cigar, smile, fantasy throne, excessive ornaments, color, text, logos, watermark, cartoon or painterly look.

Vintage melancholic vibe, phone camera style, super low resolution, close-up face shot, warm Japanese-style filter. The pic shows a super fair, slim, gorgeous cool-toned, girl with messy bun hair, curly bangs,some strands covering her eyes, wearing a light white fitted long-sleeve top, covered with a blanket, leaning back while holding a persian cat. Only her eyes are visible, with her hair naturally falling around. The whole scene has this dreamy, hazy feel. It's like a photo taken with just a regular iPhone, with a bit of motion blur, kinda messy composition, just a quick snap, like a candid shot you'd take without thinking.

Реалистичное фото 3:4. Не меняй внешность девушки.

Прическа:  Укладка выглядит естественно, волосы свободно ниспадают на плечи. Они слегка подкручены на концах, что добавляет мягкости образу. Волосы шоколадного цвета, очень длинные до пояса

Глаза: подчеркнуты нюдовые с шиммером светлыми тенями с растушевкой, четкой черной стрелкой с удлиненным хвостиком.  очень длинные черные накладные ресницы с эффектом «паучьих лапок» — разделенные на отдельные острые пучки, направленные вверх и в стороны, Ресницы густые, объемные, с четкими разделяющимися кончиками. брови аккуратно уложены. Губы пухлые, нюдово-розовые, матовые, с легким контуром.

снимок представляет собой зеркальное селфи девушки в интерьере. Девушка сфотографирована в профиль и полуанфас, слегка оперевшись спиной и лопатками о стену слева. В руках она держит смартфон в чехле с магнитным кольцом MagSafe, направленный в сторону зеркала. Вспышка телефона включена и создает яркий блик на зеркальной поверхности.
На девушке надета облегающая темная футболка с коротким рукавом и светлые джинсы с низкой или средней посадкой.
Украшения: На запястье тонкие браслеты-цепочки, а на пальцах — аккуратные кольца. У нее также виден длинный темный маникюр.
На заднем плане виден коридор или проход в другое помещение. Стена, о которую она опирается, имеет выраженную фактурную текстуру (похожа на бамбуковые или нитяные обои).

lifestyle aesthetics, Pinterest aesthetics, высокая детализация и текстура кожа,
shot on iPhone 17 Pro. эффект пленки. Фон читается без размытия. Пленочное зерно. Сниженный контраст
casual smartphone photo, handheld phone shot, quick snapshot, unplanned moment, taken casually without preparation, not meant to be a perfect photo, everyday unpolished look.Атмосфера приглушённая и камерная, в стиле dark aesthetic. Мягкий тусклый свет освещает лицо, создавая глубокие тени и мягкий контраст.
Качество снимка как у iPhone 5: лёгкая зернистость, цифровой шум, мягкая резкость и немного приглушённые цвета.copy my face 100%

Use uploaded face reference; preserve identity exactly. 4:5 waist-up indoor portrait, eye-level straight camera. Woman standing before pale sage-green built-in bookshelf filled with colorful books and minimal decor. Oversized crisp white men’s button-up, open collar, sleeves loose/rolled, blue high-waisted jeans. One hand inside jeans pocket, other raised delicately touching necklace near collarbone; relaxed shoulders. Gold hoop earrings, fine pendant necklace, stacked gold rings, silver-gold wristwatch, bracelet, red nails. Center-parted voluminous soft waves framing face. Glam makeup: sculpted brows, warm brown eyeshadow, sharp black liner, long lashes, rosy blush, smooth natural skin, contoured cheeks, glossy nude-pink lips. Head subtly turned, eyes looking sideways, calm confident feminine expression, faint closed-mouth smile. Soft sage, white, denim-blue palette. Authentic smartphone photograph, iPhone color science, slightly overexposed natural light, 2K resolution, real-life candid quality, no studio lighting, no post-processing, UGC aesthetic, sharp subject, natural background.

Use the uploaded reference image as the ONLY strict identity reference. Preserve the exact face, facial features, proportions, skin tone, hair color and overall identity. The woman must be clearly recognizable as the same person in the reference. Do not create a new face or change her ethnicity.

Create an ultra-realistic full-body lifestyle portrait of the same woman sitting casually on a quiet European residential sidewalk in front of a charming weathered red-brick townhouse. She rests her cheek on her right hand, looks directly at the camera with a calm dreamy expression, and holds a bouquet of golden sunflowers wrapped in brown kraft paper across her lap.

Outfit: oversized dark forest-green knit sweater, wide-leg taupe-gray trousers, white crew socks, white leather sneakers with gum soles, and a minimal brown leather bracelet.

Background: black wooden front door, white-framed window with potted plants, cobblestone pavement and small patches of moss.

Soft warm afternoon sunlight filtering through trees, realistic dappled light and leaf shadows. Eye-level camera, natural candid composition, full body with feet visible, shallow depth of field, softly blurred but recognizable background.

Ultra-photorealistic documentary lifestyle photography, Fujifilm GFX 100 II, 80mm, f/2.2, natural color grading, realistic skin texture, fine hair detail, soft filmic contrast, cozy nostalgic Japanese/Korean lifestyle aesthetic, magazine quality.

Negative prompt: different person, altered face, generic face, distorted face, plastic skin, AI artifacts, bad anatomy, extra fingers, deformed hands, duplicate flowers, cropped feet, blurry, oversaturated, text, watermark, logo.