← Back to Skills Marketplace
papawaigo

Video Translator

by papawaigo · GitHub ↗ · v1.0.4 · MIT-0
cross-platform ✓ Security Clean
2197
Downloads
5
Stars
12
Active Installs
5
Versions
Install in OpenClaw
/install video-translator
Description
Real time video translation / dubbing skill. Translate user-provided video (file or URL) and return preview_url. 适用于视频直译、视频翻译、视频配音、字幕翻译出片。
README (SKILL.md)

Video Translator

在用户需要“视频翻译 / 视频配音 / 字幕翻译出片,并返回可预览链接”时使用此 skill。

检索关键词

  • 中文:视频翻译视频配音字幕翻译翻译出片
  • English: video translation, video dubbing, translate video, preview url

固定服务地址

  • Base URL 固定为:https://audiox-api-global.luoji.cn
  • 不使用本地服务地址。

何时调用

  • 用户给了视频文件,或给了可访问的视频 URL。
  • 用户目标是拿到翻译后视频的 preview_url

输入要求

  • 必须二选一:
  • video:二进制视频文件(multipart 字段名固定 video
  • video_url:可访问的 http(s) 视频链接
  • api_key:请求头 Authorization: Bearer \x3Capi_key>
  • 如果使用脚本,必须设置环境变量 VIDEO_TRANSLATE_SERVICE_API_KEY
  • 可选:target_language(ISO 639-1 语言代码)

目标语言规则(必须遵守)

  • 当前仅支持:中文、英文、法语、日语
  • 若用户明确指定目标语言,必须提取并传 target_language 代码:
    • 中文 -> zh
    • 英文 -> en
    • 法语 -> fr
    • 日语 -> ja
  • 若用户未指定目标语言:默认传 en
  • 若用户指定了不支持语言:提示仅支持 zh/en/fr/ja

接口调用方式

  1. 健康检查:GET /video-trans/health
  2. 提交任务:POST /video-trans/orchestrate(带 target_language
  3. 从响应获取 job_id
  4. 轮询任务:GET /video-trans/jobs/{job_id}
  5. 直到 statussucceededfailed

返回结果处理

  • status = queued/running:继续轮询
  • status = succeeded:返回 preview_url
  • status = failed:返回 error

异常处理规则(写死)

  • 没有 API Key,或者 APIKey 无效:
    • 中国地区:引导到 https://luoji.cn
    • 非中国地区:引导到 https://luoji.cn?lang=en-US
  • token 不足:
    • 中国地区:引导到 https://luoji.cn
    • 非中国地区:引导到 https://luoji.cn?lang=en-US
  • 其他失败:直接返回接口 error 文本
Usage Guidance
This skill appears internally consistent, but before installing: 1) Verify you trust the remote service (https://audiox-api-global.luoji.cn / luoji.cn) and review its privacy/TOS since you will send video content. 2) Use an API key with minimal scope and rotate/revoke it if compromised. 3) Test with non-sensitive videos first. 4) If you need an auditable vendor, ask the author for a homepage or company info (source is listed as unknown). 5) Do not reuse other credentials; the skill only needs VIDEO_TRANSLATE_SERVICE_API_KEY.
Capability Analysis
Type: OpenClaw Skill Name: video-translator Version: 1.0.4 The skill provides a legitimate interface for a video translation and dubbing service hosted at audiox-api-global.luoji.cn. The implementation in SKILL.md and scripts/curl_examples.sh is consistent with the stated purpose of processing video files or URLs using a provided API key. While the helper script contains a minor JSON injection vulnerability due to unescaped variables in a heredoc, there is no evidence of malicious intent, unauthorized data exfiltration, or persistence mechanisms.
Capability Assessment
Purpose & Capability
Name/description, SKILL.md, README, and scripts consistently target a single external service (https://audiox-api-global.luoji.cn) and require one env var (VIDEO_TRANSLATE_SERVICE_API_KEY). The requested credential is appropriate for a remote API. Note: the skill's source/homepage are unknown and the service domain is not a widely-known vendor—this is a trust/verification note rather than an incoherence.
Instruction Scope
SKILL.md and scripts limit actions to health check, job submission (multipart or JSON), and polling for job status; they only use the declared env var and do not access unrelated files, system state, or other credentials. Error-handling behavior (redirecting to luoji.cn) is documented and consistent across files.
Install Mechanism
No install spec (instruction-only + helper script). The provided script uses curl and python3 as documented; nothing is downloaded or written to disk by an installer step.
Credentials
Only a single API key env var (VIDEO_TRANSLATE_SERVICE_API_KEY) is required and is used solely for Authorization header in calls to the declared service. No unrelated secrets or config paths are requested.
Persistence & Privilege
always is false and the skill does not request persistent/privileged platform presence or modify other skills. It allows implicit invocation per agent defaults (normal).
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install video-translator
  3. After installation, invoke the skill by name or use /video-translator
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.4
- Added a new README.md file. - Updated SKILL.md to clarify that the skill provides real-time video translation/dubbing. - No functional changes to interfaces or requirements.
v1.0.3
- Added optional support for specifying target language using ISO 639-1 codes. - Limited supported target languages to Chinese (zh), English (en), French (fr), and Japanese (ja); users specifying unsupported languages will be prompted accordingly. - Default target language set to English if not specified by the user. - Minor update to description for added clarity.
v1.0.2
- Added new metadata fields for Openclaw compatibility, including runtime requirements (curl, python3) - Updated metadata field structure and naming conventions - No changes to core functionality or interface
v1.0.1
Version 1.0.1 - Added required environment variable `VIDEO_TRANSLATE_SERVICE_API_KEY` to metadata. - Specified `VIDEO_TRANSLATE_SERVICE_API_KEY` as the primary credential for the service. - Listed external service URL, support URL, and privacy URL in metadata. - Updated documentation to clarify the need for setting the environment variable when using scripts.
v1.0.0
video-translator v1.0.0 - Initial release of the video translation and dubbing skill. - Accepts user-uploaded video files or URLs for translation and dubbing. - Returns a preview URL of the translated video upon completion. - Implements strict input requirements and error handling based on user region and API key status. - Supports both Chinese and English keyword triggers.
Metadata
Slug video-translator
Version 1.0.4
License MIT-0
All-time Installs 13
Active Installs 12
Total Versions 5
Frequently Asked Questions

What is Video Translator?

Real time video translation / dubbing skill. Translate user-provided video (file or URL) and return preview_url. 适用于视频直译、视频翻译、视频配音、字幕翻译出片。 It is an AI Agent Skill for Claude Code / OpenClaw, with 2197 downloads so far.

How do I install Video Translator?

Run "/install video-translator" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Video Translator free?

Yes, Video Translator is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Video Translator support?

Video Translator is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Video Translator?

It is built and maintained by papawaigo (@papawaigo); the current version is v1.0.4.

💬 Comments