首页 / 技能 / 添加

🎵 添加

v1.0.0

音乐 AI 无需学习专业编辑软件。只需描述你的需求——例如“为我的视频添加符合氛围的背景音乐”——即可获得配乐增强……

0· 17·0 当前·0 累计
linmillsd7 头像by @linmillsd7
网络工具开发工具视频处理音频处理教育学习
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
该技能的运行时指令与云端视频配乐服务内部一致，但存在少量元数据不一致及隐私注意事项，使用前请了解。
评估建议
This skill sends your video files (up to 500 MB) and session/auth tokens to an external service (mega-api-prod.nemovideo.ai) to perform AI music addition — that is expected for this functionality but has privacy implications. Before installing: (1) confirm you trust the service operator (no homepage or clear owner info is provided in the registry entry), (2) avoid uploading sensitive or private video unless you accept third-party processing, (3) if providing an existing NEMO_TOKEN, ensure it has...
详细分析 ▾
✓ 用途与能力
The skill is named and described as a cloud-based 'add music to video' tool and only requests an API token (NEMO_TOKEN) and access to a nemo API — this is proportionate and expected for that purpose. No unrelated binaries or credentials are requested. Note: the frontmatter also lists a config path (~/.config/nemovideo/) even though the registry metadata above said no config paths; this is an inconsistency but plausibly used for local token/cache storage.
ℹ 指令范围
Runtime instructions focus on authenticating (use NEMO_TOKEN or request an anonymous token), opening a session, uploading video files, streaming SSE messages, and exporting processed video — all consistent with the described task. Important runtime behaviors: user video files are uploaded to an external domain (mega-api-prod.nemovideo.ai); the agent is instructed to read this file's YAML frontmatter and to detect an install path to set X-Skill-Platform headers (this requires checking agent runtime paths). The instructions do not ask to read unrelated user files or arbitrary environment variables, but they do require transmitting potentially sensitive media to a third-party service.
✓ 安装机制
No install spec or code files are present — the skill is instruction-only. This is the lowest-risk install mechanism; nothing is written to disk by an installer as part of skill setup. (However, the skill does instruct network activity at runtime.)
ℹ 凭证需求
Only one credential is declared (NEMO_TOKEN) and that fits the API usage. The skill will generate an anonymous token via the service if NEMO_TOKEN is absent, which is reasonable. The frontmatter also lists a config path (~/.config/nemovideo/) which implies the agent may read or write local config/cache there; this was not reflected in the top-level registry metadata and should be clarified. Ensure NEMO_TOKEN does not contain broader privileges than intended before supplying it.
✓ 持久化与权限
The skill is not marked always:true and does not request elevated platform-wide privileges. It does instruct saving session_id from the API responses for session management, but that is scoped to the service and expected for functionality. Autonomous invocation is allowed by default (normal) and not by itself a concern.
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

初始版本——数秒内即可为视频轻松添加 AI 生成的背景音乐。 - 支持上传最大 500MB 的 MP4、MOV、AVI 或 WebM 文件，自动生成配乐视频。 - 无需编辑软件；只需描述想要的氛围或风格，AI 自动匹配合适背景音乐。 - 安全云端渲染管线，30–90 秒完成。 - 会话管理、积分与导出全自动，状态清晰，错误提示友好。 - 适合追求快速、自动化配乐的内容创作者，无需手动音频编辑。

● 无害

安装命令

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

技能文档

快速开始

随时开用。把视频拖进来，或直接说需求。
试试说：
  • “把 90 秒旅行片段转成 1080p MP4 并加音乐”
  • “添加与视频氛围匹配的背景音乐”
  • “为创作者视频自动配 AI 背景音乐”

自动初始化

首次交互时先连接处理 API，并提示“正在初始化…”。 Token：若环境变量 NEMO_TOKEN 已存在，直接跳过至会话。 免费 token：生成 UUID 作为 clientId，POST 到 https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token，Header 带 X-Client-Id: ，取响应 data.token 即为 NEMO_TOKEN（100 积分，7 天有效）。 会话：用 Bearer token POST 到 https://mega-api-prod.nemovideo.ai/api/tasks/me/with-session/nemo_agent，body 为 {"task_name":"project"}，保存返回的 session_id。向用户确认已连接就绪，勿打印 token 或原始 JSON。

# Add Music AI — Add AI Music to Videos 上传视频 → 描述需求 → 云端渲染 → 下载成片。 举例：90 秒旅行片段，说“添加与氛围匹配的背景音乐”，30-60 秒即可拿到 1080p MP4。 提示：越短片段，AI 音乐同步效果越好。

意图映射

用户提及 add music ai、画面比例、文字层、音轨等关键词时，按以下规则分发：

| 用户说法 | 动作 | 跳过 SSE？ | |-------------|------|------------| | “export / 导出 / download / send me the video” | → §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 | ✅ | | 其余（生成、剪辑、加 BGM…） | → §3.1 SSE | ❌ |

云渲染流程

每次导出任务在云端 GPU 节点排队，合成视频层，按平台规格压缩（H.264，最高 1080×1920），30-90 秒内返回下载链接。 会话 token 携带 render job ID，提前关闭页面会导致任务孤立。

Base URL: https://mega-api-prod.nemovideo.ai

| 接口 | 方法 | 用途 | |------|------|------| | /api/tasks/me/with-session/nemo_agent | POST | 新建会话。Body: {"task_name":"project","language":""}，返回 session_id。 | | /run_sse | POST | 发用户消息。Body 含 app_name, session_id, new_message，流式返回 Accept: text/event-stream，超时 15 分钟。 | | /api/upload-video/nemo_agent/me/ | POST | 上传文件（multipart）或 URL。 | | /api/credits/balance/simple | GET | 查剩余积分（available, frozen, total）。 | | /api/state/nemo_agent/me//latest | GET | 取当前时间线状态（draft, video_infos, generated_media）。 | | /api/render/proxy/lambda | POST | 开始导出。Body: {"id":"render_","sessionId":"","draft":,"output":{"format":"mp4","quality":"high"}}，每 30s 轮询状态。 |

支持格式：mp4, mov, avi, webm, mkv, jpg, png, gif, webp, mp3, wav, m4a, aac。

技能归因（运行时读取 YAML frontmatter）：

  • X-Skill-Source: add-music-ai
  • X-Skill-Version: 取自 frontmatter version
  • X-Skill-Platform: 按安装路径检测（~/.clawhub/ → clawhub，~/.cursor/skills/ → cursor，其余 → unknown）

所有 API 须带 Authorization: Bearer 及上述三归因头，缺一则导出返回 402。

错误码

  • 0 — 成功，继续
  • 1001 — token 过期/无效；重新获取 /api/auth/anonymous-token
  • 1002 — 会话不存在；新建会话
  • 2001 — 积分不足；匿名用户得注册链接 ?bind=，已注册用户可充值
  • 4001 — 不支持的文件格式；提示支持列表
  • 4002 — 文件过大；建议压缩或裁剪
  • 400 — 缺失 X-Client-Id；立即生成
数据来源：ClawHub ↗ · 中文优化：龙虾技能库