Agent Skills
› NeverSight/learn-skills.dev
› sora-video
sora-video
GitHub通过AceDataCloud API调用OpenAI Sora生成AI视频。支持文本转视频、图像转视频及基于现有视频的角色驱动生成，提供多种模型、分辨率和时长选项，适用于创意视频制作。
Trigger Scenarios
根据文本提示词生成视频
利用参考图片生成动态视频
从已有视频中提取角色并生成新场景视频
Install
npx skills add NeverSight/learn-skills.dev --skill sora-video -g -y
SKILL.md
Frontmatter
{
"name": "sora-video",
"license": "Apache-2.0",
"metadata": {
"author": "acedatacloud",
"version": "1.0"
},
"description": "Generate AI videos with OpenAI Sora via AceDataCloud API. Use when creating videos from text prompts, generating videos from reference images, or using character references from existing videos. Supports text-to-video, image-to-video, and character-driven generation with multiple models and resolutions.",
"compatibility": "Requires ACEDATACLOUD_API_TOKEN in .env file (see _shared\/authentication.md). Optionally pair with mcp-sora for tool-use."
}
Sora Video Generation
Generate AI videos through AceDataCloud's OpenAI Sora API.
Setup: See authentication for token setup.
Quick Start
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/taskswith{"id": "..."}.
Models
| Model | Duration | Quality | Best For |
|---|---|---|---|
sora-2 |
10–15s | Standard | Most tasks (default) |
sora-2-pro |
10–25s | Higher | Premium quality, longer videos |
Workflows
1. Text-to-Video
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
Use reference images to guide generation.
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
Extract a character from an existing video and use them in a new scene.
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
| Parameter | Values | Description |
|---|---|---|
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 |
Gotchas
- Duration of 25 seconds is only available with
sora-2-promodel size: "large"produces higher resolution but costs more and takes longer- Character-driven generation requires
character_startandcharacter_endtimestamps (in seconds) from the source video orientationsets 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
Version History
- e0220ca Current 2026-07-05 22:55
