Back to Details

sora-video

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Sora Video Generation

Sora视频生成

Generate AI videos through AceDataCloud's OpenAI Sora API.
Setup: See authentication for token setup.
通过AceDataCloud的OpenAI Sora API生成AI视频。
设置： 请查看身份验证了解令牌设置方法。

Quick Start

快速开始

bash
curl -X POST https://api.acedata.cloud/sora/videos \
  -H "Authorization: Bearer $ACEDATACLOUD_API_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"prompt": "a golden retriever running on a beach at sunset", "model": "sora-2", "callback_url": "https://api.acedata.cloud/health"}'
Async: See async task polling. Poll via 
POST /sora/tasks
with 
{"id": "..."}
.
bash
curl -X POST https://api.acedata.cloud/sora/videos \
  -H "Authorization: Bearer $ACEDATACLOUD_API_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"prompt": "a golden retriever running on a beach at sunset", "model": "sora-2", "callback_url": "https://api.acedata.cloud/health"}'
异步处理： 请查看异步任务轮询。通过
POST /sora/tasks
接口传入
{"id": "..."}
进行轮询。

Models

模型

ModelDurationQualityBest For
sora-2
10–15sStandardMost tasks (default)
sora-2-pro
10–25sHigherPremium quality, longer videos
模型时长画质适用场景
sora-2
10–15秒标准大多数任务（默认选项）
sora-2-pro
10–25秒更高高品质、长时长视频

Workflows

工作流

1. Text-to-Video

1. 文本转视频

json
POST /sora/videos
{
  "prompt": "a busy Tokyo street at night with neon signs reflecting in rain puddles",
  "model": "sora-2",
  "size": "small",
  "duration": 10,
  "orientation": "landscape"
}
json
POST /sora/videos
{
  "prompt": "a busy Tokyo street at night with neon signs reflecting in rain puddles",
  "model": "sora-2",
  "size": "small",
  "duration": 10,
  "orientation": "landscape"
}

2. Image-to-Video

2. 图像转视频

Use reference images to guide generation.
json
POST /sora/videos
{
  "prompt": "the scene gradually comes alive with gentle motion",
  "image_urls": ["https://example.com/scene.jpg"],
  "model": "sora-2",
  "orientation": "landscape"
}
使用参考图像引导视频生成。
json
POST /sora/videos
{
  "prompt": "the scene gradually comes alive with gentle motion",
  "image_urls": ["https://example.com/scene.jpg"],
  "model": "sora-2",
  "orientation": "landscape"
}

3. Character-Driven Video

3. 角色驱动视频

Extract a character from an existing video and use them in a new scene.
json
POST /sora/videos
{
  "prompt": "the character walks through a futuristic city",
  "character_url": "https://example.com/source-video.mp4",
  "character_start": 2.0,
  "character_end": 5.0,
  "model": "sora-2-pro"
}
从现有视频中提取角色，并将其应用到新场景中。
json
POST /sora/videos
{
  "prompt": "the character walks through a futuristic city",
  "character_url": "https://example.com/source-video.mp4",
  "character_start": 2.0,
  "character_end": 5.0,
  "model": "sora-2-pro"
}

Parameters

参数说明

ParameterValuesDescription
model
"sora-2"
, 
"sora-2-pro"
Model to use (required)
size
"small"
, 
"large"
Video resolution
duration
10
, 
15
, 
25
Duration in seconds (25 only with sora-2-pro)
orientation
"landscape"
(16:9), 
"portrait"
(9:16), 
"square"
(1:1)		Video orientation
version
"1.0"
API version — version 
1.0
enables duration up to 25s, orientation, character references, and image inputs
参数可选值描述
model
"sora-2"
, 
"sora-2-pro"
使用的模型（必填）
size
"small"
, 
"large"
视频分辨率
duration
10
, 
15
, 
25
视频时长（单位：秒，仅
sora-2-pro
支持25秒）
orientation
"landscape"
（16:9）, 
"portrait"
（9:16）, 
"square"
（1:1）		视频方向
version
"1.0"
API版本 — 版本
1.0
支持最长25秒时长、自定义方向、角色参考和图像输入功能

Gotchas

注意事项

  • Duration of 25 seconds is only available with 
    sora-2-pro
    model
  • size: "large"
    produces higher resolution but costs more and takes longer
  • Character-driven generation requires 
    character_start
    and 
    character_end
    timestamps (in seconds) from the source video
  • orientation
    sets the aspect ratio — use 
    "portrait"
    for mobile-first content
  • Task states use 
    "succeeded"
    (not "completed") — check for this value when polling
MCP: 
pip install mcp-sora
| Hosted: 
https://sora.mcp.acedata.cloud/mcp
| See all MCP servers
  • 25秒时长仅适用于
    sora-2-pro
    模型
  • size: "large"
    会生成更高分辨率视频，但成本更高且耗时更长
  • 角色驱动生成需要提供源视频中
    character_start
    和
    character_end
    的时间戳（单位：秒）
  • orientation
    用于设置宽高比 — 面向移动设备的内容请使用
    "portrait"
  • 任务状态使用
    "succeeded"
    （而非"completed"） — 轮询时请检查该状态值
MCP： 
pip install mcp-sora
| 托管地址：
https://sora.mcp.acedata.cloud/mcp
| 查看所有MCP服务器