Documentation Index
Fetch the complete documentation index at: https://docs.openai-nebula.com/llms.txt
Use this file to discover all available pages before exploring further.
下载视频接口用于获取已完成的视频文件数据。注意：此接口仅 Sora 2 模型支持。其他模型（Veo、阿里万相、豆包 Seedance）在任务成功后，视频URL会直接包含在查询任务接口的响应中，无需额外下载步骤。
Bearer Token，如 Bearer sk-xxxxxxxxxx
查询参数
使用示例
curl -X GET "https://llm.ai-nebula.com/v1/video/generations/download?id=video_69095b4ce0048190893a01510c0c98b0" \
-H "Authorization: Bearer sk-xxxxxxxxxx"
响应示例
{
"success": true,
"generation_id": "video_69095b4ce0048190893a01510c0c98b0",
"task_id": "video_69095b4ce0048190893a01510c0c98b0",
"format": "mp4",
"size": 15728640,
"base64": "AAAAIGZ0eXBpc29tAAACAGlzb21pc28yYXZjMW1wNDEAAAAIZnJlZQAAB...",
"data_url": "data:video/mp4;base64,AAAAIGZ0eXBpc29tAAACAGlzb21pc28yYXZjMW1wNDEAAAAIZnJlZQAAB..."
}
响应字段说明
| 字段名 | 类型 | 说明 |
|---|
success | boolean | 是否成功 |
generation_id | string | 生成ID（与 videoId 相同） |
task_id | string | 任务ID |
format | string | 视频格式（固定为 "mp4"） |
size | number | 视频文件大小（字节） |
base64 | string | Base64 编码的视频数据 |
data_url | string | Data URL 格式的视频数据，可直接用于前端 <video> 标签 |
使用说明
前端使用 data_url
data_url 字段可以直接用于 HTML <video> 标签：
<video src="data:video/mp4;base64,AAAAIGZ0eXBpc29tAAACAGlzb21pc28yYXZjMW1wNDEAAAAIZnJlZQAAB..." controls></video>
下载保存文件
使用 base64 字段可以将视频保存为文件：
JavaScript 示例
// 从响应中获取 base64 数据
const response = await fetch('https://llm.ai-nebula.com/v1/video/generations/download?id=video_xxx', {
headers: {
'Authorization': 'Bearer sk-xxxxxxxxxx'
}
});
const data = await response.json();
// 将 base64 转换为 Blob
const binaryString = atob(data.base64);
const bytes = new Uint8Array(binaryString.length);
for (let i = 0; i < binaryString.length; i++) {
bytes[i] = binaryString.charCodeAt(i);
}
const blob = new Blob([bytes], { type: 'video/mp4' });
// 创建下载链接
const url = URL.createObjectURL(blob);
const a = document.createElement('a');
a.href = url;
a.download = 'video.mp4';
a.click();
URL.revokeObjectURL(url);
Python 示例
import requests
import base64
def download_video(video_id, api_key):
"""下载视频并保存为文件"""
url = f"https://llm.ai-nebula.com/v1/video/generations/download?id={video_id}"
headers = {"Authorization": f"Bearer {api_key}"}
response = requests.get(url, headers=headers)
data = response.json()
if data.get("success"):
# 解码 base64 数据
video_data = base64.b64decode(data["base64"])
# 保存为文件
with open("video.mp4", "wb") as f:
f.write(video_data)
print(f"✅ 视频已保存: video.mp4 (大小: {data['size']} 字节)")
return True
else:
print("❌ 下载失败")
return False
完整流程示例（Sora 2）
-
提交视频生成任务
curl -X POST "https://llm.ai-nebula.com/v1/video/generations" \
-H "Authorization: Bearer sk-xxxxxxxxxx" \
-H "Content-Type: application/json" \
-d '{
"model": "sora-2",
"prompt": "一只可爱的小猫在花园里玩耍",
"seconds": "4",
"size": "720x1280"
}'
{
"task_id": "video_69095b4ce0048190893a01510c0c98b0",
"status": "submitted",
"format": "mp4"
}
-
查询任务状态（轮询直到成功）
curl -X GET "https://llm.ai-nebula.com/v1/video/generations/video_69095b4ce0048190893a01510c0c98b0" \
-H "Authorization: Bearer sk-xxxxxxxxxx"
succeeded 时，继续下一步。
-
下载视频文件
curl -X GET "https://llm.ai-nebula.com/v1/video/generations/download?id=video_69095b4ce0048190893a01510c0c98b0" \
-H "Authorization: Bearer sk-xxxxxxxxxx"
相关接口
