← Back to Skills Marketplace
408
Downloads
0
Stars
0
Active Installs
2
Versions
Install in OpenClaw
/install vidu-generation
Description
Vidu AI 视频/图片/音频生成。支持文生视频、图生视频、参考生视频、图片生成、TTS语音合成、声音复刻。对话式调用，自动识别意图。
Usage Guidance
This skill appears to implement a Vidu media-generation client (scripts/vidu_cli.py) and legitimately needs an API key (VIDU_API_KEY) to call api.vidu.cn or api.vidu.com. Before installing: 1) Verify the skill publisher and source (there's no homepage and source is 'unknown'). 2) Expect to provide VIDU_API_KEY — the registry metadata incorrectly claims no env vars; do not rely on the metadata. 3) Be aware the skill will read local image/audio files you supply and will upload them to the Vidu endpoints and may download generated media to disk. 4) For voice cloning, confirm you have rights to any source audio you upload and understand privacy/legal risks. 5) If you need higher assurance, ask the publisher for a homepage/repo, or review the full script contents yourself and confirm the exact API endpoints and data sent match your expectations.
Capability Analysis
Type: OpenClaw Skill
Name: vidu-generation
Version: 1.2.1
The vidu-generation skill bundle is a legitimate integration for the Vidu AI platform, providing tools for video, image, and audio generation. The core logic in scripts/vidu_cli.py uses standard Python libraries (urllib) to communicate with official Vidu API endpoints (api.vidu.cn and api.vidu.com) and includes standard functionality for base64 image encoding and file downloading. No evidence of data exfiltration, unauthorized credential access, or malicious prompt injection was found; the skill operates entirely within its stated purpose.
Capability Assessment
Purpose & Capability
The SKILL.md and scripts/vidu_cli.py implement video/image/audio generation against api.vidu.cn / api.vidu.com and require an API key (VIDU_API_KEY). That capability aligns with the stated purpose, but the registry metadata claims no required environment variables or primary credential — a clear mismatch between what the skill needs and what the metadata declares.
Instruction Scope
The runtime instructions and the CLI read local input files (images, audio, optional text files), convert local images to base64, and download generation outputs to disk. All of these actions are coherent with a media-generation skill, but they do involve reading user-provided files and writing downloaded outputs to the agent's filesystem (baseDir and usual download paths). The SKILL.md explicitly instructs use of VIDU_API_KEY and local script invocation.
Install Mechanism
There is no install spec (instruction-only install), and the code is included as a plain Python script. No remote downloads or opaque installer are specified, which is low risk from an installation mechanism perspective.
Credentials
The code and SKILL.md require a single credential: VIDU_API_KEY, which is proportionate to the described API integration. However, the registry metadata incorrectly lists no required env vars / credentials. That discrepancy is material: it could mislead users about what secrets they must supply and expose. The skill will also access local files (images/audio) — expected but worth noting for privacy.
Persistence & Privilege
The skill does not request always:true, does not modify other skills, and does not attempt to persist credentials itself. It runs as an on-demand, user-invocable skill and is not requesting elevated platform privileges.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install vidu-generation - After installation, invoke the skill by name or use
/vidu-generation - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.2.1
**Vidu Generation 1.2.1 Changelog**
- Added detailed API references and documentation files: `api_reference.md`, `template_list.md`, `voice_id_list.md`
- Introduced new CLI script: `scripts/vidu_cli.py` for easier command-line operations
- Significantly updated and streamlined the main documentation (SKILL.md) for clearer usage and model selection guidelines
- Removed legacy metadata file (`_meta.json`) to minimize redundancy
v1.0.0
Vidu Generation 1.0.0: 首次发布，集成视频、图片、音频一站式AI生成
- 支持多种视频生成：文生视频、图生视频、参考生视频、首尾帧过渡视频、场景特效模板等
- 实现图片AI生成与参考生图，适配多种模型与分辨率
- 集成语音合成TTS、声音复刻及文生音频，音色自动推荐或自定义
- 提供社交媒体内容搜索与分析（支持小红书、抖音、微博、公众号等多平台）
- 提供CLI工具，便捷调用各类生成与查询任务
- 详细参数说明、模型选项与接口用法，适用于各类内容创作者
Metadata
Frequently Asked Questions
What is Input prompts and generate images, videos, effects, speech synthesis, voice cloning, etc., using a single API key.?
Vidu AI 视频/图片/音频生成。支持文生视频、图生视频、参考生视频、图片生成、TTS语音合成、声音复刻。对话式调用，自动识别意图。 It is an AI Agent Skill for Claude Code / OpenClaw, with 408 downloads so far.
How do I install Input prompts and generate images, videos, effects, speech synthesis, voice cloning, etc., using a single API key.?
Run "/install vidu-generation" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Input prompts and generate images, videos, effects, speech synthesis, voice cloning, etc., using a single API key. free?
Yes, Input prompts and generate images, videos, effects, speech synthesis, voice cloning, etc., using a single API key. is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Input prompts and generate images, videos, effects, speech synthesis, voice cloning, etc., using a single API key. support?
Input prompts and generate images, videos, effects, speech synthesis, voice cloning, etc., using a single API key. is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Input prompts and generate images, videos, effects, speech synthesis, voice cloning, etc., using a single API key.?
It is built and maintained by Vidu AI (@x-jihua); the current version is v1.2.1.
More Skills