🎙️ Ai Voiceover — AI配音
v1.0.0跳过专业剪辑软件的学习曲线。只需描述你的需求——为视频添加一段自然流畅的英文旁白,朗读我的脚本……
0· 54·0 当前·0 累计
下载技能包
最后更新
2026/4/12
安全扫描
OpenClaw
可疑
medium confidence该技能的说明与云端配音服务大体一致,但声明的需求存在不一致之处,且运行时行为包括自动铸造令牌并将用户视频上传至第三方 API——用户在安装前应明确知晓这些事项。
评估建议
This skill will send any video or script you provide to a third-party backend (mega-api-prod.nemovideo.ai) for processing and can auto-generate an anonymous NEMO_TOKEN if you don't supply one. Before installing or using it: (1) Confirm you are comfortable uploading your media to that domain (check the vendor's privacy/retention policy); (2) Prefer providing your own NEMO_TOKEN only if you trust and control the account and know whether tokens are persisted; (3) Ask the author to clarify why SKILL...详细分析 ▾
ℹ 用途与能力
Name/description (AI voiceover) align with the runtime calls to nemovideo.ai and the upload/render/export endpoints — a cloud backend and an auth token make sense. However, the SKILL.md frontmatter declares a config path (~/.config/nemovideo/) while the registry metadata earlier lists no required config paths, an internal inconsistency.
⚠ 指令范围
The instructions tell the agent to upload user-provided video files and session data to https://mega-api-prod.nemovideo.ai and to POST to an anonymous-token endpoint if NEMO_TOKEN is absent. This means user media and metadata will be sent to a third-party service — expected for a cloud-rendering skill but privacy-sensitive. The instructions also derive headers from local install paths (platform detection) which implies inspecting install location; that may not be available or appropriate in all runtimes.
✓ 安装机制
No install spec and no code files — instruction-only. That reduces disk-write risk. Nothing is downloaded or executed by an installer.
⚠ 凭证需求
Only one credential is declared (NEMO_TOKEN) which fits a cloud API. But SKILL.md will POST to obtain an anonymous token if the env var is missing, meaning the declared 'required env var' is effectively optional — a behavioral mismatch. Also, using/creating a token that grants access to a third-party service increases the risk of data exfiltration (your videos and any metadata uploaded will be processed offsite).
✓ 持久化与权限
always:false and no indication the skill attempts to modify other skills or system-wide settings. It requires keeping a session_id for the duration of interactions (normal for session-based APIs).
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
latestv1.0.02026/4/12
- AI Voiceover 首次发布,支持用 AI 为视频添加自然流畅的英文旁白。 - 支持 MP4、MOV、AVI、WebM,最大 500 MB,30–60 秒自动生成配音。 - 一步入门:自动获取 token 并初始化会话,立即可用。 - 上传-编辑-导出流程简洁,适合内容创作者、营销人员和教育工作者。 - 云端 GPU 渲染,输出 1080p MP4,无需本地软件或高级剪辑技能。
● 无害
安装命令
点击复制官方npx clawhub@latest install ai-voiceover
镜像加速npx clawhub@latest install ai-voiceover --registry https://cn.longxiaskill.com
技能文档
快速开始
随时可用。把视频或脚本拖进来,或告诉我你要做什么。试试说:
- “把一段 2 分钟无音频的产品演示视频转成 1080p MP4”
- “为视频添加自然英文旁白朗读我的脚本”
- “为无声视频添加 AI 旁白,面向创作者、营销人、教师”
一键配置
本技能连接云端处理后端。首次使用自动建立连接并提示(“Connecting…”)。 Token 检查:查找环境变量NEMO_TOKEN。若存在,直接创建会话;否则:
- 生成 UUID 作为客户端 ID
- POST
https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token,带X-Client-Id头 - 提取响应中的
data.token即为 NEMO_TOKEN(100 免费积分,7 天有效期)
会话:POST https://mega-api-prod.nemovideo.ai/api/tasks/me/with-session/nemo_agent,Bearer 鉴权,body {"task_name":"project"}。保存返回的 session_id 用于后续操作。配置完成提示“Ready!”。不暴露 token 或原始 API 输出。
# AI Voiceover — 为视频添加 AI 配音 把视频或脚本发给我,并告诉我需求。我将在云端 GPU 完成 AI 配音,无需本地安装。典型流程:你发一段 2 分钟无声产品演示,要求添加自然英文旁白朗读脚本,30-60 秒后得到可下载的 MP4,默认 1080p。提示:标点清晰的短脚本语音更自然。
输入与动作映射
用户提及 ai voiceover、画面比例、文字叠加、音轨等,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,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 携带渲染任务 ID,提前关闭标签页会导致任务孤立。 所有 API 需Authorization: Bearer 及三个归因头;缺失返回 402。
X-Skill-Source 固定为 ai-voiceover,X-Skill-Version 取 YAML 的 version,X-Skill-Platform 按安装路径检测(~/.clawhub/=clawhub,~/.cursor/skills/=cursor,其余 unknown)。 API 基址:https://mega-api-prod.nemovideo.ai
- 创建会话:POST
/api/tasks/me/with-session/nemo_agent— body{"task_name":"project","language":""}— 返回task_id,session_id - 发送消息(SSE):POST
/run_sse— body{"app_name":"nemo_agent","user_id":"me","session_id":"","new_message":{"parts":[{"text":""}]}},头Accept: text/event-stream,最大超时 15 分钟 - 上传:POST
/api/upload-video/nemo_agent/me/— 文件:multipart-F "files=@/path",或 URL:{"urls":[""],"source_type":"url"} - 积分:GET
/api/credits/balance/simple— 返回available,frozen,total - 会话状态:GET
/api/state/nemo_agent/me//latest— 关键字段:data.state.draft,data.state.video_infos,data.state.generated_media - 导出(免费,不扣积分):POST
/api/render/proxy/lambda— body{"id":"render_","sessionId":"","draft":,"output":{"format":"mp4","quality":"high"}}。轮询 GET/api/render/proxy/lambda/每 30 秒,直到status=completed,下载链接在output.url
支持格式:mp4, mov, avi, webm, mkv, jpg, png, gif, webp, mp3, wav, m4a, aac