Sora 2 是面向真实运动、物理一致性和电影感场景生成的 AI 视频模型。它适合文生视频和图生视频工作流，尤其适合需要自然动作、镜头逻辑和音频表现的场景。
本页沿用 Seedance 2.0 API 的结构：选择 Sora 2 模型类型，在 Playground 测试生成，查看请求字段和价格，再通过 API 文档接入生产环境。
最低成本从 $0.015/s
10: 3 积分/秒 - 文生视频 - 输出秒数 × 3
15: 3 积分/秒 - 文生视频 - 输出秒数 × 3
-: 20 积分/秒 - 文生视频 - 输出秒数 × 20
美元估算按最佳年付套餐 $0.005/积分 计算。
核心请求字段
保持请求结构可预测，同时保留视频、图片、音频和分镜控制能力。
{
"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"
}
}使用 Sora 2 Text to Video 生成
本页的 Playground、请求示例、请求字段和价格都会跟随当前选择的模型类型变化。
查看 API 详细文档打开完整 API 文档，查看接口、鉴权、任务轮询和 payload 细节。 /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.Sora 2 API 为视频工作流带来的能力
当产品需要真实运动、提示词驱动的视频生成、参考图片控制或更高阶的 Pro 输出时，可以使用 Sora 2。
真实文生视频
把提示词生成电影感短片，让镜头运动、主体动作和场景物理更可信。
图生视频控制
从参考图片开始生成，尽量保持主体身份、构图、风格和产品细节。
音频感知输出
在支持的模型中使用音频相关设置，让广告、短片和叙事场景更完整。
Pro 与 Storyboard 模式
需要更高阶生成时使用 Pro 版本，需要结构化场景规划时使用 Storyboard。
从 Sora 2 测试到生产请求
在接入 API 前，先快速验证提示词、参考图片、时长和不同模型版本的表现。
1. 选择 Sora 2 模式
根据质量和控制需求，选择文生视频、图生视频、Stable、Pro 或 Pro Storyboard。
2. 提交生成
使用模型 ID、提示词、必要的参考图片、时长、分辨率和其他模型字段发起 API 请求。
3. 轮询并发布
跟踪异步任务直到成功，然后获取生成视频 URL，用于应用、营销活动或内部工作流。
你可以用 Sora 2 API 创作什么
当产品需要基于明确创意 brief 或参考画面的可重复视频生成时，Sora 2 很适合接入。
社区公开的 Sora 2 成功案例
查看数据库中公开且已成功生成的 Sora 2 作品，打开案例可继续查看提示词、参数和生成结果。
Sora 2 Text to Video
Create a realistic vertical video of a tired young woman arriving home very hungry and with no energy. She opens the refrigerator, sees there is nothing healthy ready, and starts eating random unhealthy snacks just to satisfy her hunger quickly. Show her looking frustrated, tired, and unsatisfied, as if she is eating anything only because she has no better option. The scene should feel relatable and realistic, with a modern kitchen, soft evening lighting, casual clothes, and natural body language. No dialogue, no voice-over, no subtitles, no readable text, no logos, no labels, no app screens, no prices, no notifications. Only visual storytelling in vertical format.
Sora 2 Text to Video
Create a realistic vertical video of a tired young woman arriving home after a long day. She opens the refrigerator, looks disappointed, and realizes there is no healthy food ready. She looks at her phone as if she might order delivery, but instead opens a healthy recipe app. Her expression changes from frustrated to happy and relieved as she scrolls through colorful recipe images and chooses something easy to make. The mood should shift from tired and stressed to hopeful and motivated. Modern kitchen, soft evening light, realistic lifestyle style. No dialogue, no voice-over, no subtitles, no readable text, no app names, no logos, no labels, no prices, no notifications. Only visual storytelling in vertical format.
Sora 2 Text to Video
Create a realistic vertical video of a tired young woman arriving home after a long day, with low energy and a frustrated expression. She walks into the kitchen, opens the refrigerator, and looks disappointed because there is no healthy meal ready to eat. The fridge should look disorganized, with only a few random ingredients and no prepared food. She then looks at her phone as if thinking about ordering delivery, showing the feeling of spending more money than planned and choosing unhealthy food just to satisfy hunger quickly. The scene should feel relatable, natural, and emotional, with soft evening lighting, a modern kitchen, casual clothes, and realistic body language. Important: do not show any readable text, delivery app screens, prices, numbers, notifications, labels, logos, or written information anywhere in the video. No dialogue, no voice-over, no subtitles, no text on screen, no information panels.
Sora 2 Text to Video
Create a realistic vertical lifestyle video showing a tired young woman arriving home after a long day. She enters the kitchen looking exhausted, opens the refrigerator, and realizes there is nothing healthy ready to eat. She looks disappointed and hungry, then glances at her phone as if tempted to order delivery. Show a subtle emotional contrast: tiredness, lack of energy, an empty or disorganized fridge, and the feeling of wanting something quick but healthy. The scene should feel relatable, natural, and realistic, with soft evening lighting, a modern home kitchen, casual clothes, and smooth camera movement. Focus on her tired expression, the open refrigerator, her phone in hand, and the frustration of not having healthy food ready. Important: do not show any readable text, app screens, delivery app names, prices, labels, logos, notifications, or written information anywhere in the video. No dialogue, no voice-over, no subtitles, no text on screen, no information panels. Only visu
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
面向 API 视频产品构建
账户级执行
用户登录后提交任务，并通过现有 SdanceAI 生成流程消耗积分。
参考图片支持
当工作流需要更强的主体、风格或产品一致性时，可以选择图生视频模型。
灵活模型选择
可根据速度、质量和场景控制需求，在标准、Stable、Pro 和 Storyboard 版本间切换。
Sora 2 API 常见问题
Sora 2 API 最适合什么场景？
它适合真实感短视频生成，尤其是文生视频、图生视频、广告、产品视觉、社媒短片和分镜概念开发。
本页支持哪些 Sora 2 模型类型？
本页包含 Sora 2 Text to Video、Sora 2 Image to Video、Stable 版本、Sora 2 Pro Text to Video、Sora 2 Pro Image to Video 和 Sora 2 Pro Storyboard。
可以从图片开始生成视频吗？
可以。需要参考图片来控制主体身份、构图、产品细节或视觉风格时，请选择 Sora 2 Image to Video 或 Pro Image to Video。
接入前在哪里测试 Sora 2？
可以直接使用本页 Playground 测试提示词、模型版本、请求字段、价格和 API payload 行为。
Sora 2 和 Sora 2 Pro 有什么区别？
Sora 2 适合通用短片生成和快速迭代。Sora 2 Pro 更适合高质量输出和要求更高的创意工作流。
Sora 2 Pro Storyboard 用来做什么？
Storyboard 适合需要结构化场景规划、创意分镜或成片前预演的工作流。
Sora 2 API 支持音频吗？
支持的 Sora 2 版本包含音频相关生成设置。具体可用性和表现取决于当前选择的模型和本页展示的请求字段。
Sora 2 可以生成多长的视频？
可选时长取决于当前选择的 Sora 2 模型和价格档位。选择模型类型后，可以查看对应价格和请求字段。
Sora 2 API 可以用于商业项目吗？
本页面面向商用 API 工作流配置。生产环境使用前，请确认账户套餐、积分余额、模型可用性以及适用的内容政策要求。
如何从 Playground 测试切换到 API 接入？
先选择模型类型，查看生成的请求 JSON 和字段表，然后打开 API 文档查看接口、鉴权、任务轮询和 webhook 细节。