短视频一键生成器

短视频一键生成器 v3.0。输入主题+要点，AI自动完成分镜、生图、配音、字幕、渲染，输出1080×1920竖屏MP4。

Security Scan

The skill mostly does what it says (generates images/TTS and renders video) but there are inconsistencies between declared requirements and the actual code/README (missing required env vars, third‑party endpoints), and the script performs network requests and shell execution that you should review before running with real keys.

Purpose & Capability

The skill's name/description (AI short-video generator) matches the code and SKILL.md: it plans storyboards, calls image and TTS backends, and runs ffmpeg to render. However the registry metadata lists no required environment variables/credentials while both SKILL.md and README and the script explicitly expect MINIMAX_API_KEY and optionally OPENAI_API_KEY (and other env vars). This mismatch is an incoherence (likely an author oversight) but worth flagging.

Instruction Scope

Runtime instructions and the Python script instruct the agent/user to set service API keys and then the script makes outbound HTTP requests to image/TTS APIs, downloads image data, writes files, generates audio, and invokes ffmpeg via subprocess. Those actions are expected for this purpose, but the skill transmits content (and your API keys in requests) to third-party endpoints and executes shell commands; you should verify endpoints and inspect how inputs are used when constructing shell commands.

Install Mechanism

No install spec is provided (instruction-only with an included Python script). No remote archive downloads or installers are invoked by the platform; risk is limited to running the provided Python file and its runtime network activity.

Credentials

The script uses MINIMAX_API_KEY and OPENAI_API_KEY (and other optional env vars) which are proportional to the stated functionality (image/TTS backends). But the registry metadata incorrectly lists no required env vars/configs, and the default MINIMAX_BASE is a non‑familiar domain (https://api.minimaxi.com/v1) — verify that service before providing keys. The code also allows overriding OPENAI_BASE which could redirect calls; this increases risk if you set nonstandard values or if the code is modified.

Persistence & Privilege

The skill does not request always=true or system-wide persistence. It runs as a script on demand and does not modify other skills or global agent configuration.

What to consider before installing

Before installing or running: 1) Treat this as code you should review — open video_producer.py and inspect network calls, especially requests.post and any subprocess.run usage. 2) Do not supply high‑value keys without confidence: test first with IMAGE_BACKEND=placeholder and TTS_BACKEND=edge (free/local) so no external API calls are made. 3) Verify the MiniMax endpoint (MINIMAX_BASE) — it is not a widely known provider; confirm its legitimacy before entering MINIMAX_API_KEY. 4) Run the script inside an isolated environment or container (non‑privileged user) and avoid running as root. 5) Look for shell commands constructed from untrusted input (subprocess.run with shell=True) and avoid feeding untrusted data into the script until you can confirm sanitization. 6) Ask the author to update the registry metadata to declare required env vars and to provide the .env.example file referenced in README; absence of those files/metadata is a red flag. If you want, paste the remaining truncated parts of video_producer.py and I can re-check for more specific risks (e.g., exact ffmpeg command construction or any hidden endpoints).

🎬 短视频一键生成器 v3.0 (付费版)

一句话卖点

AI自动出片，输入主题→5分钟→可直接发布的短视频

核心能力

1. AI分镜规划 — 智能生成热门短视频结构（开场→核心观点→结尾引导）
2. AI生图配画 — 根据内容语义自动匹配视觉素材（MiniMax文生图）
3. AI配音 — 高清自然语音合成，支持多场景独立配音
4. 自动字幕 — SRT硬字幕嵌入，中文字幕自动适配
5. FFmpeg渲染 — 1080×1920竖屏，短视频平台直接上传

使用方式

命令行

# 1. 设置API Key
export MINIMAX_API_KEY="你的key"

# 2. 运行
python3 /path/to/video_producer.py \
  --topic "AI会取代程序员吗？" \
  --points '[
    {"text":"AI不是取代程序员，而是成为他们的超级工具", "emoji":"🤖", "title":"认清本质"},
    {"text":"掌握AI工具的程序员薪资涨了30%", "emoji":"📈", "title":"数据说话"},
    {"text":"10年后不会AI = 今天不会用电脑", "emoji":"🎯", "title":"残酷现实"}
  ]' \
  --style tech \
  --output ./my_video

OpenClaw Skill 模式

skills:
  - name: video-producer-v3
    path: ./video-producer-v3

视觉风格

风格	适用场景	色调
tech	科技、AI、数码	蓝紫色调
warm	教育、情感、生活	暖色调
business	营销、干货、职场	商务白蓝

输出文件结构

output/
├── storyboard.json       # 分镜规划
├── materials/
│   ├── scene_0.png       # 开场图片
│   ├── scene_1.png       # 场景1图片
│   └── ...
├── audio/
│   ├── scene_0.mp3       # 开场配音
│   ├── scene_1.mp3       # 场景1配音
│   └── ...
├── output.mp4            # 无字幕版
└── final_subtitled.mp4   # 最终带字幕版

环境要求

• Python 3.8+
• FFmpeg (系统安装)
• 依赖: pip install requests pillow
• API Key: MiniMax (免费注册送额度)

定价

版本	价格	功能
免费版(Lite)	¥0	基础分镜+占位图，无水印
标准版	¥29.9	全功能：AI生图+TTS+字幕
专业版(Pro)	¥69.9	多风格+自定义Logo+批量生成

---

上架物料

卖点文案 (朋友圈/短视频)

一条短视频，从2小时变成5分钟。

❌ 不会剪？不会配？不会写脚本？ ✅ 输入主题 → AI全自动完成

🎬 分镜规划自动出 🖼️ AI配图不用找 🎙️ AI配音不卡壳 📝 字幕自动加

输出：可直接发抖音/小红书/视频号

👇 一杯奶茶钱，解放你的创作时间 💰 ¥29.9 (永久使用，后续免费更新)

适用场景

• 知识科普短视频
• 产品种草/带货
• 个人IP口播
• 行业干货分享
• 热点解读

关键词标签

短视频生成 AI视频 自媒体工具 一键出片 视频制作 抖音工具 小红书工具 智能配音 视频字幕 内容创作

用户话术 (客服/私信)

Q: 对这个视频工具感兴趣 A: 输入主题和要点，AI自动生成完整短视频，5分钟出片。¥29.9永久使用，支持抖音/小红书格式。

Q: 生成的质量怎么样？ A: 1080×1920竖屏高清，AI配音自然，自动配图和字幕。可以先用免费版体验效果。

---

更新记录

v3.0.0 (2026-04-25)

• 首次发布，标准付费版
• 自包含架构，无外部依赖
• 内置AI分镜规划
• MiniMax TTS + 文生图
• FFmpeg渲染 + SRT硬字幕