Sora 2 API
音声対応With AudioSora 2 はリアルな動き、物理的な一貫性、映画的なシーン生成を重視した AI 動画モデルです。自然な動作、カメラロジック、音声表現が重要なテキスト動画・画像から動画のワークフローに向いています。
このページは Seedance 2.0 API と同じ構成です。Sora 2 のモデルタイプを選び、Playground で生成を試し、リクエストフィールドと料金を確認してから API ドキュメントで本番連携へ進めます。
最低コスト $0.015/s
10: 3 クレジット/秒 - テキストから動画 - 出力秒数 × 3
15: 3 クレジット/秒 - テキストから動画 - 出力秒数 × 3
-: 20 クレジット/秒 - テキストから動画 - 出力秒数 × 20
USD 見積もりは最適な年額プランの $0.005/クレジットで計算しています。
主要リクエストフィールド
予測しやすい payload 構造を保ちながら、動画、画像、音声、Storyboard 制御に対応します。
{
"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"
}
}Sora 2 Text to Video で生成
Playground、リクエスト例、入力フィールド、料金は選択中のモデルタイプに連動します。
API 詳細ドキュメントを見るエンドポイント、認証、タスクのポーリング、payload の詳細を確認できます。 /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 が動画ワークフローに加える機能
リアルな動き、プロンプト駆動の動画生成、参照画像による制御、より高度な Pro 出力が必要なときに Sora 2 を利用できます。
リアルなテキスト動画
プロンプトから映画的な短尺クリップを生成し、カメラ、被写体、シーン物理をより自然に表現します。
画像から動画の制御
参照画像から始めることで、被写体、構図、スタイル、製品ディテールを保ちやすくなります。
音声を考慮した出力
対応モデルでは音声関連の設定を利用でき、広告、ショート動画、ストーリーシーンをより完成度高く作れます。
Pro と Storyboard
高品質な生成には Pro、構造化されたシーン設計には Storyboard モードを利用できます。
Sora 2 のテストから本番リクエストへ
API 統合前に、プロンプト、参照画像、長さ、モデルバリアントを素早く検証できます。
1. Sora 2 モードを選択
必要な品質と制御に合わせて、テキスト動画、画像から動画、Stable、Pro、Pro Storyboard を選びます。
2. 生成を送信
モデル ID、プロンプト、必要な参照画像、長さ、解像度、モデル固有のフィールドを指定して API リクエストを送ります。
3. ポーリングして公開
非同期タスクの完了を追跡し、生成された動画 URL をアプリ、キャンペーン、制作フローで利用します。
Sora 2 API で作れるもの
明確なクリエイティブブリーフや参照フレームから、繰り返し動画を生成したい製品に向いています。
コミュニティの Sora 2 成功事例
公開され、正常に生成された Sora 2 の出力を確認できます。各事例からプロンプト、設定、結果を詳しく見られます。
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
API ベースの動画プロダクト向け
アカウント連動の実行
ユーザーはログイン後にジョブを送信し、既存の SdanceAI 生成フローでクレジットを消費します。
参照画像サポート
被写体、スタイル、製品の一貫性が重要な場合は、画像から動画モデルを利用できます。
柔軟なモデル選択
速度、品質、シーン制御の要件に応じて、標準、Stable、Pro、Storyboard を切り替えられます。
Sora 2 API FAQ
Sora 2 API は何に向いていますか？
リアルな短尺 AI 動画生成に向いています。特にテキスト動画、画像から動画、広告、製品ビジュアル、SNS クリップ、Storyboard 型のコンセプト開発に適しています。
このページではどの Sora 2 モデルを使えますか？
Sora 2 Text to Video、Sora 2 Image to Video、Stable バリアント、Sora 2 Pro Text to Video、Sora 2 Pro Image to Video、Sora 2 Pro Storyboard を利用できます。
画像から動画を生成できますか？
はい。被写体、構図、製品ディテール、スタイルを参照画像でガイドしたい場合は、Sora 2 Image to Video または Pro Image to Video を選択してください。
統合前にどこで Sora 2 を試せますか？
このページの Playground で、プロンプト、モデルバリアント、入力フィールド、料金、API payload を確認できます。
Sora 2 と Sora 2 Pro の違いは？
Sora 2 は一般的な短尺生成と反復に向いています。Sora 2 Pro はより高品質な出力や要求の高い制作ワークフロー向けです。
Sora 2 Pro Storyboard は何に使いますか？
構造化されたシーン設計、クリエイティブなシーケンス、最終生成前のプリビズに役立ちます。
Sora 2 API は音声に対応していますか？
対応する Sora 2 バリアントでは音声関連の生成設定を利用できます。利用可否と挙動は、選択中のモデルとこのページに表示されるリクエストフィールドに依存します。
Sora 2 の動画の長さはどれくらいですか？
選択できる長さは Sora 2 のモデルタイプと料金ティアによって変わります。モデルを選択した後、料金とリクエストフィールドを確認してください。
Sora 2 API は商用プロジェクトで使えますか？
このページは商用 API ワークフロー向けに構成されています。本番利用前に、アカウントプラン、クレジット残高、モデル提供状況、適用されるコンテンツポリシーを確認してください。
Playground から API 統合へ進むには？
モデルタイプを選び、生成された request JSON とフィールド表を確認し、API ドキュメントでエンドポイント、認証、タスクポーリング、webhook の詳細を確認してください。
Sora 2 を動画ワークフローへ
まず生成画面で Sora 2 のプロンプトや参照画像を試し、結果を確認してから API ドキュメントで本番フローに接続できます。