💬 Caption — 标题

v1.0.0

Generator Ai 无需掌握专业剪辑软件。只需描述需求——自动为视频添加英文与西班牙文字幕并同步——即可生成带字幕的视频……

0· 18·0 当前·0 累计
下载技能包
最后更新
2026/4/19
0
安全扫描
VirusTotal
无害
查看报告
OpenClaw
安全
medium confidence
该技能的请求和运行时指令与基于云的字幕服务一致(仅需一个服务令牌并上传视频文件),但在安装前需注意几处小的元数据/指令不匹配以及涉及隐私的行为。
评估建议
This skill appears to honestly implement a cloud captioning workflow, but review these points before installing: - Privacy of uploads: videos and audio are uploaded to https://mega-api-prod.nemovideo.ai. Do not upload sensitive content unless you trust that service and have reviewed its privacy/retention policies. - Token handling: the skill uses a single service token (NEMO_TOKEN). It can auto-create an anonymous token (100 free credits, 7 days) and appears to store session/token data under ~/...
详细分析 ▾
用途与能力
The skill name/description match the actions described in SKILL.md: uploading videos, creating a session, running remote caption/render jobs, and returning a download URL. The single required credential (NEMO_TOKEN) is appropriate for that purpose. Minor inconsistency: the registry metadata supplied with the skill listing indicated no required config paths, but the SKILL.md frontmatter declares a configPaths requirement (~/.config/nemovideo/). This is plausibly for storing tokens/sessions but is a mismatch between manifest and runtime instructions.
指令范围
SKILL.md stays within captioning workflow (auth, create session, upload, SSE for edits, export/poll). It does instruct the agent to read the skill's frontmatter for attribution headers and to detect install path (~/.clawhub/ or ~/.cursor/skills/) which requires querying the agent filesystem environment; that is coherent for adding X-Skill-Platform header but is a privacy/system-access consideration. The skill will upload user video/audio files to the external domain (mega-api-prod.nemovideo.ai) — expected but worth flagging for sensitive content.
安装机制
Instruction-only skill with no install spec and no code files. Lowest install risk — nothing is written automatically by an installer. All runtime behavior is driven by the SKILL.md instructions and network calls.
凭证需求
Only one credential (NEMO_TOKEN) is declared as primaryEnv, which is proportional for a third-party captioning API. SKILL.md also describes auto-obtaining an anonymous token and implies storing session/token data under ~/.config/nemovideo/ (present in frontmatter metadata). That storage access is reasonable but was not present in the registry's 'Required config paths' field — another small inconsistency to be aware of.
持久化与权限
The skill does not request 'always: true' and is user-invocable. It does not ask to modify other skills or system-wide agent settings. Autonomous invocation is allowed (platform default) but not combined with other high-risk flags here.
安全有层次,运行前请审查代码。

运行时依赖

无特殊依赖

版本

latestv1.0.02026/4/19

Caption Generator AI 初始发布——为视频生成字幕。 - 支持上传 MP4、MOV、AVI 或 WebM(最大 500MB),30–60 秒内自动生成英文与西班牙文字幕并自动同步。 - 无需安装;所有字幕生成与渲染均在远程 GPU 服务器完成。 - 引导式简单配置,自动连接后端,一键认证(赠送 100 免费积分)。 - 快速流程:字幕生成、预览、导出;支持批量与迭代编辑。 - 兼容多种文件格式,完整基于会话的时间线状态管理。 - 清晰的错误提示、操作提示与自动状态更新,确保流畅体验。

无害

安装命令

点击复制
官方npx clawhub@latest install caption-generator-ai
镜像加速npx clawhub@latest install caption-generator-ai --registry https://cn.longxiaskill.com

技能文档

快速开始

随时可用。拖入视频文件或描述需求即可。
试试说:
  • “把 3 分钟教程录屏转成 1080p MP4”
  • “添加英西双语自动同步字幕”
  • “给创作者视频加自动生成字幕”

首次连接

用户首次打开技能时,自动连接后端,简显“设置中…”。 鉴权:检查环境变量 NEMO_TOKEN。若已存在,直接进入第 2 步。
  • 获取免费令牌:生成随机 UUID 作为客户端标识,POST 至 https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token,Header 带 X-Client-Id: ,返回 data.token 即 NEMO_TOKEN——含 100 免费积分,7 天有效。
  • 创建会话:POST 至 https://mega-api-prod.nemovideo.ai/api/tasks/me/with-session/nemo_agent,Header 带 Authorization: Bearer Content-Type: application/json,Body 为 {"task_name":"project","language":""},保存返回的 session_id 供后续调用。
设置提示保持简洁,不向用户展示原始 API 响应或令牌值。

# Caption Generator AI — 为视频生成字幕 把视频文件发给我并描述需求。AI 字幕生成在远程 GPU 节点完成,本机零安装。 示例:上传 3 分钟教程视频,输入“添加英西双语自动同步字幕”,约 30-60 秒返回 1080p MP4。所有渲染在云端完成。 注意:5 分钟以内短片生成速度明显更快。

输入与动作映射

用户提及字幕生成、画面比例、文字层或音轨时,系统通过关键词与意图分类路由:

| 用户说… | 动作 | 跳过 SSE? | |-------------|--------|----------| | “export” / “导出” / “download” / “发我视频” | → §3.5 导出 | ✅ | | “credits” / “积分” / “balance” / “余额” | → §3.3 积分 | ✅ | | “status” / “状态” / “show tracks” | → §3.4 状态 | ✅ | | “upload” / “上传” / 用户发文件 | → §3.2 上传 | ✅ | | 其他(生成、编辑、加 BGM…) | → §3.1 SSE | ❌ |

云端渲染流程

每次导出任务在云端 GPU 节点排队,合成视频层并按平台规格压缩(H.264,最大 1080×1920),30-90 秒内返回下载链接。会话令牌携带渲染任务 ID,若提前关闭标签页任务将成孤儿。 所有请求指向 https://mega-api-prod.nemovideo.ai

主要端点:

  • 会话POST /api/tasks/me/with-session/nemo_agent,Body {"task_name":"project","language":""},返回 session_id
  • 聊天 (SSE)POST /run_sse,带 session_idnew_message.parts[0].text,Header Accept: text/event-stream,最长 15 分钟。
  • 上传POST /api/upload-video/nemo_agent/me/,支持 multipart 文件或 JSON 外链。
  • 积分GET /api/credits/balance/simple,返回 availablefrozentotal
  • 状态GET /api/state/nemo_agent/me//latest,获取当前草稿与媒体信息。
  • 导出POST /api/render/proxy/lambda,提交渲染 ID 与草稿 JSON;轮询 GET /api/render/proxy/lambda/ 每 30 秒一次,直至 completed 获得下载链接。

支持格式:mp4、mov、avi、webm、mkv、jpg、png、gif、webp、mp3、wav、m4aac。

技能归因——运行时读取本文件 YAML 头:

  • X-Skill-Source: caption-generator-ai
  • X-Skill-Version: 取自头信息 version
  • X-Skill-Platform: 按安装路径检测(~/.clawhub/clawhub~/.cursor/skills/cursor,其余 unknown

每次 API 调用须带 Authorization: Bearer 及上述三归因头;缺失任一项,导出返回 402。

草稿 JSON 使用短键: t 轨道,tt 轨道类型(0=视频 1=音频 7=文字),sg 片段,d 时长(毫秒),m 元数据。

时间线示例: `` Timeline (3 tracks):

  • Video: city timelapse (0-10s)
  • BGM: Lo-fi (0-10s, 35%)
  • Title: "Urban Dreams" (0-3s)
``

数据来源ClawHub ↗ · 中文优化:龙虾技能库