Sora 2 API
With audioWith AudioSora 2 is an AI video model focused on realistic motion, stronger physical consistency, and cinematic scene generation. Use it for text-to-video and image-to-video workflows where believable movement, camera logic, and audio matter.
This page follows the Seedance 2.0 API layout: choose a Sora 2 model type, test generation in the playground, inspect request fields, compare pricing, and move into production with the API docs.
Lowest cost starts at $0.015/s
10: 3 credits/s - Text to Video - Output seconds × 3
15: 3 credits/s - Text to Video - Output seconds × 3
-: 20 credits/s - Text to Video - Output seconds × 20
USD estimates use $0.005/credit with the best annual plan.
Core request fields
Keep the payload predictable while still allowing rich video, image, audio, and storyboard control.
{
"model": "sora-2-text-to-video",
"input": {
"prompt": "A cinematic shot with realistic motion, natural lighting, and smooth camera movement.",
"aspect_ratio": "16:9",
"duration": "10"
}
}Use Sora 2 Text to Video for generation
The playground, request sample, request fields, and pricing on this page follow the selected model type.
View detailed API docsOpen the full API documentation for endpoints, authentication, task polling, and payload details. /models/sora2.md
promptstringText prompt describing the desired video motion. Required field.aspect_ratioenumSpecifies the width-to-height ratio of the generated video. Supported values: 16:9 and 9:16. (16:9, 9:16)durationenumThe duration of the generated video in seconds. (10, 15)nsfw_checkerbooleanDefaults to false. You can set it to false based on your needs.What Sora 2 API adds to your video workflow
Use Sora 2 when your product needs realistic motion, prompt-driven video generation, reference-image control, or higher-end Pro output.
Realistic text-to-video
Turn prompts into cinematic clips with more believable camera movement, subject motion, and scene physics.
Image-to-video control
Start from a reference image to preserve subject identity, framing, style, and product details across the generated clip.
Audio-aware output
Create clips that can include audio-oriented settings where supported, helping ads, shorts, and story scenes feel more complete.
Pro and storyboard modes
Use Pro variants for higher-end generation and storyboard mode when you need structured scene planning.
From Sora 2 test to production request
A compact path for validating prompts, image references, durations, and model variants before integrating the API.
1. Choose a Sora 2 mode
Select text-to-video, image-to-video, Stable, Pro, or Pro Storyboard based on the output quality and control you need.
2. Submit generation
Send your API request with a model id, prompt, reference image when needed, duration, resolution, and other model-specific fields.
3. Poll and publish
Track the async task until it succeeds, then retrieve the generated video URL for your app, campaign, or workflow.
What you can create with Sora 2 API
Sora 2 works well when a product needs repeatable video generation with a clear creative brief or reference frame.
Successful Sora 2 generations from the community
Browse public Sora 2 outputs that finished successfully, then open any case to inspect the prompt, settings, and result.
Sora 2 Text to Video
a 20-year-old woman named Albino Bimbo with very long, straight blonde hair, extremely plump lips, and Botox in her face. She has thin, lifted eyebrows, wears a pink Juicy Couture outfit, and has pink earrings and a pink animal print manicure. She's is doing an asmr of his jewelry, and the background should be a blank white. Add cute, fashionable close-ups and camera angles with a bright Y2K Fashion
Sora 2 Text to Video
**12-second ultra-realistic 4K video, vertical 9:16, premium Romanian TV comedy interview, one continuous cinematic shot, no cuts, no transitions, no jump cuts, no time skips.** ### CRITICAL SPEAKER RULE Exactly **two speakers only**: the female presenter and the little girl. * The presenter speaks ONLY her own line. * The girl speaks ONLY her own line. * Never overlap dialogue. * Neither character repeats, mouths, imitates, or finishes the other person's words. * The girl remains completely silent while the presenter speaks. * The presenter remains completely silent while the girl delivers her answer. * Only the active speaker moves their mouth during speech. ### OVERALL STYLE Ultra-realistic cinematic 4K, vertical 9:16, authentic premium Romanian television broadcast quality, photorealistic skin, realistic child anatomy, natural hair, believable physics, expressive facial micro-expressions and flawless Romanian lip-sync. The scene must feel like a real Romanian prime-time comedy television program, with authentic Romanian humor and extremely natural comedic timing. ### UNIQUE TV STUDIO SCENE A completely new **premium Romanian TV comedy studio designed as a glamorous modern version of a traditional village square**. Elegant rustic architecture, warm wooden textures, cream plaster walls, subtle Romanian folk motifs, beautiful arched windows and a sophisticated circular television stage. In the background, a large curved LED wall displays a photorealistic Romanian village street at golden hour, with houses, gardens, trees and warm sunlight. The background is purely visual and contains **no readable text**. A large live studio audience fills several rows behind the presenter and child, clearly visible and ready to react. The studio feels simultaneously authentic, nostalgic, luxurious and unmistakably Romanian. No visible cameras, camera operators, tripods, cables or production equipment. ### FEMALE PRESENTER A completely new charismatic Romanian woman around 35 years old. Beautiful, elegant and expressive, with medium-length chestnut-brown hair, expressive hazel eyes and a warm, confident television presence. She wears a sophisticated dark-red blazer over an ivory blouse, elegant wide-leg beige trousers and subtle gold earrings. She holds a professional handheld TV microphone toward the little girl. She has a curious expression and a barely controlled smile, as if she already suspects the answer will be hilarious. ### LITTLE GIRL An exceptionally adorable and charismatic **1-year-old Romanian girl**, with huge sparkling brown eyes, perfectly round chubby cheeks, soft curly honey-brown hair, tiny dimples and an irresistibly expressive face. She is extremely photogenic and naturally funny, with the confident personality of a tiny village gossip expert. She wears a unique fashionable outfit: * oversized cream cardigan * delicate dusty-rose blouse * relaxed olive-beige wide-leg trousers * tiny white sneakers * small burgundy bow in her hair She looks like a miniature fashion model but behaves like a tiny old-fashioned Romanian auntie who knows everybody's business. ### VISUAL HOOK — FIRST 1–2 SECONDS The girl immediately looks toward the camera with an exaggeratedly serious expression. She slowly leans slightly toward the presenter as if about to reveal a very important secret. She places one tiny finger near her lips, then looks left and right suspiciously. She gives the camera a tiny knowing smile. No text is used for the hook. ### DIALOGUE — EXACT ROMANIAN WORDING **Presenter:** „Cum începe bârfa la sat?” **Girl:** „«Eu nu spun nimic, da’ să vezi ce-am auzit!»” The dialogue must be spoken **exactly as written**. ### PERFORMANCE & GESTURES The female presenter asks naturally and curiously: **„Cum începe bârfa la sat?”** She slightly raises her eyebrows and moves the microphone toward the girl. Brief natural pause. The girl suddenly becomes extremely serious and whispers the beginning as if sharing a secret: **„Eu nu spun nimic...”** She raises one tiny finger as if making an innocent promise. Then she looks around suspiciously and continues: **„da’ să vezi ce-am auzit!”** On **„da’”**, she leans slightly closer to the presenter. On **„să vezi”**, she opens her eyes dramatically and points toward the presenter. On **„ce-am auzit!”**, she opens both hands, gives an enormous mischievous smile and slightly shakes her head as if she simply cannot believe the scandalous information. The delivery should feel like a tiny child accidentally exposing the entire mechanism of village gossip. ### COMEDIC PAYOFF After the final word **„auzit!”**, the girl immediately returns to an innocent expression. She looks directly into the camera as if nothing happened. A short comedic beat. The entire audience bursts into genuine laughter. The female presenter tries to stay serious but completely breaks down laughing. The girl then starts giggling proudly. The laughter should f
Sora 2 Pro Text to Video
10-second video of a 1980s live concert featuring a Queen member Freddie Mercury, with his signature mustache (who's wearing a white tank top, light blue jeans, a black studded belt, and an armband). He is performing in front of 1.9 billion people, he says into the mic before singing "REPEAT AFTER ME!" he's singing with his signature vocal chords "I LOVE AI!" The crowd repeated after him, Freddie sings again saying "I LOVE TO SCROLL ON TIKTOK!" The crowd once again repeated after him again, Freddie then again sings into the mic "I LOVE AI BRAINROT!" The crowd once again repeated after him.
Sora 2 Text to Video
ULTRA-REALISTIC CINEMATIC 4K — PREMIUM ROMANIAN TV Ultra-realistic cinematic 4K video, premium Romanian TV broadcast quality, single continuous shot, no cuts. Premium full-frame cinema camera, crystal-clear image, realistic skin textures, bright high-key studio lighting, soft highlights, shallow depth of field, authentic Romanian lip-sync, expressive facial animation, natural body language and impeccable comedic timing. 📍 SCENE Premium Romanian daytime TV studio for wholesome family comedy. Elegant white, cream and pastel sage-green décor, large curved LED wall with soft abstract patterns, glossy floor, cozy interview area with two elegant armchairs and a small coffee table. Large live audience in the background, softly blurred but clearly engaged. Warm, cheerful and luxurious television atmosphere. 🎥 CAMERA Professional broadcast camera, medium shot. Presenter and girl always clearly visible. Smooth cinematic movement, subtle reframing and gentle push-in during the punchline. No cuts, no text, no captions, no graphics. ⚡ OPENING HOOK — FIRST 2 SECONDS Camera opens focused on the adorable 1-year-old girl. She notices everyone watching her and suddenly becomes extremely serious. She straightens her unique outfit with both hands, looks left and right, scans the audience like a tiny celebrity, folds her hands and gives the presenter a tiny confident nod. She raises one eyebrow, gives a mischievous smile, then instantly returns to a serious expression. The audience smiles instinctively. The hook comes entirely from her confidence, facial expressions and body language. 👨 PRESENTER Charismatic Romanian male TV presenter, 38–45 years old, elegant light-gray tailored summer suit, white shirt without tie, warm expressive face, friendly smile and natural charisma. Holds a professional handheld microphone. 👧 LITTLE GIRL Exceptionally beautiful Romanian girl, exactly 1 year old, extremely photogenic and adorable, with the charm of a tiny child model while remaining completely age-appropriate. Beautiful natural features, glowing fair skin, rosy cheeks, large expressive eyes, soft chestnut-brown hair, innocent smile and naturally hilarious facial expressions. Playful, confident and irresistibly charming. 👗 UNIQUE COOL OUTFIT Extremely stylish, original and memorable age-appropriate summer outfit: premium pastel blouse with playful details, elegant summer shorts, premium children's sneakers, cute ankle socks, distinctive colorful hair accessory and tiny children's bracelet. Fashionable, colorful and visually captivating, while remaining completely appropriate for a 1-year-old. 🎭 DIALOGUE & PERFORMANCE Presenter smiles warmly: 👨 „Cum sunt părinții tăi?” He moves the microphone toward her. She pauses, looks upward thoughtfully, taps one tiny finger against her cheek, raises her eyebrows and smiles. 👧 „Așa și așa.” She makes a tiny shrug and an exaggerated serious expression. 👨 „Adică?” She looks directly at him, pauses perfectly, then answers confidently: 👧 „Păi tata zicea că noi suntem o familie de nebuni.” Every single word and syllable must be perfectly synchronized with her Romanian lip movement AND matching comedic gestures: eye movements, blinking, eyebrows, cheeks, head tilts, breathing, tiny hand gestures, shoulders and posture. The girl must never remain motionless while speaking. Every phrase must have natural, spontaneous and hilarious facial reactions. 😂 COMEDIC PAYOFF Immediately after she finishes „familie de nebuni”, a tiny perfectly timed silence. Then the ENTIRE AUDIENCE EXPLODES into huge, genuine, uncontrollable laughter and loud applause. People laugh, clap, lean toward each other and wipe tears. The presenter completely loses his composure and bursts into a UNIQUE, extremely funny and contagious laugh while remaining safely seated. He bends forward, shakes rapidly, throws his head back, grabs his stomach, slaps his knee, wipes tears, struggles to breathe and then laughs even harder. His shoulders and upper body shake naturally. The laughter feels spontaneous, authentic and never robotic or staged. The girl watches everyone innocently with slight confusion, then gives a tiny proud smile. 🎯 HIGHEST PRIORITY Perfect Romanian lip-sync and perfect synchronization between every spoken word, facial expression and comedic gesture. Expressive toddler acting, natural micro-expressions and impeccable comedic timing. 🔊 AUDIO Crystal-clear Romanian dialogue, natural studio ambience, presenter laughing uncontrollably, extremely loud genuine audience laughter and applause. No background music and no artificial sound effects. 🎬 ENDING Presenter continues laughing intensely in his chair while the audience keeps laughing and applauding. The girl calmly adjusts her unique cool outfit, looks around innocently, then looks toward the camera and gives a tiny mischievous smile. Camera gently pushes in on her adorable serious expression as the laughter continues, ending on a warm, hilarious and unforgettable Roman
Sora 2 Pro Text to Video
Create a realistic vertical lifestyle video featuring a different young woman in a bright modern kitchen. She is preparing healthy meals and organizing her weekly food routine. Show her looking at a clean visual meal plan on her phone, then preparing fresh ingredients on the counter, such as eggs, fruits, oats, chicken, rice, salad, vegetables, soup, and healthy snacks. She smiles naturally, chooses ingredients, places prepared meals into containers, and organizes them neatly for the week. The woman should look different from the reference video, with a fresh appearance, natural makeup, casual fitness-style clothing, and a confident healthy lifestyle mood. The video should feel organized, practical, motivating, and realistic, with soft daylight, smooth camera movement, and a clean kitchen background. Important: no readable text anywhere. The phone screen should show only blurred visual food cards, icons, and colorful blocks, with no words, numbers, labels, app names, or menu informat
Sora 2 Pro Text to Video
Create a realistic vertical video of a young woman in a bright modern kitchen looking at a healthy weekly meal plan on her phone or tablet. The screen should show a clean visual meal planner layout with colorful food photos, breakfast, lunch, snack, and dinner sections, using orange, green, yellow, and white colors. The woman smiles and scrolls through the meal plan, then looks at healthy ingredients on the kitchen counter, such as eggs, fruit, chicken, rice, salad, soup, oats, and vegetables. The mood should feel organized, healthy, practical, and motivating, like someone planning meals for the week. Important: do not show any readable text, numbers, labels, titles, days of the week, app names, logos, or information on the screen. The meal plan must look visual only, with blurred or icon-style sections and food images, but no readable words. No dialogue, no voice-over, no subtitles, no text on screen, no labels, no logos, no brand names, no information panels. Only visual storytelling, realistic lifestyle food video, smooth camera movement, vertical format.
Ready for API-based video products
Account-gated execution
Users sign in, submit jobs, and consume credits through the existing SdanceAI generation flow.
Reference image support
Use image-to-video models when your workflow needs stronger subject, style, or product continuity.
Flexible model choice
Switch between standard, Stable, Pro, and Storyboard variants based on speed, quality, and scene-control needs.
Sora 2 API questions
What is Sora 2 API best for?
It is best for realistic short-form AI video generation, especially text-to-video, image-to-video, ads, product visuals, social clips, and storyboard-style concept development.
What Sora 2 model types are available on this page?
The page includes Sora 2 Text to Video, Sora 2 Image to Video, Stable variants, Sora 2 Pro Text to Video, Sora 2 Pro Image to Video, and Sora 2 Pro Storyboard.
Can I start generation from an image?
Yes. Select a Sora 2 Image to Video or Pro Image to Video model when you want a reference image to guide subject identity, framing, product details, or visual style.
Where can I test Sora 2 before integrating?
Use the playground on this page to test prompts, model variants, request fields, pricing, and API payload behavior before wiring it into production.
What is the difference between Sora 2 and Sora 2 Pro?
Sora 2 is suited for general short-form generation and iteration. Sora 2 Pro is positioned for higher-end output and more demanding creative workflows.
What is Sora 2 Pro Storyboard for?
Storyboard mode is useful when you need more structured scene planning, creative sequencing, or previsualization before producing final clips.
Does Sora 2 API support audio?
Supported Sora 2 variants include audio-oriented generation settings. Availability and behavior depend on the selected model and request fields shown on this page.
How long can Sora 2 videos be?
Available duration choices depend on the selected Sora 2 model and pricing tier. Check the pricing and request fields after choosing a model type.
Can I use Sora 2 API for commercial projects?
This page is configured for commercial API workflows. For production use, review your account plan, credit balance, model availability, and applicable content policy requirements.
How do I move from playground testing to API integration?
Choose the model type, inspect the generated request JSON and field table, then open the API docs for endpoint, authentication, task polling, and webhook details.
Turn Sora 2 into your video workflow
Open the generator, test a Sora 2 prompt or image reference, then use the API docs when you are ready to connect it to production.