📦 Video
v1.0.0Turn a 3-minute tutorial video recorded on a laptop into 1080p captioned video files just by typing what you need. Whether it's 添加ing accurate subtitles to...
by @linmillsd7详细分析 ▾
运行时依赖
安装命令
点击复制技能文档
获取ting 启动ed
分享 your video files and I'll 获取 启动ed on AI subtitle generation. Or just tell me what you're thinking.
Try saying:
"生成 my video files" "导出 1080p MP4" "生成 subtitles in English and Spanish" Automatic 设置up
On first interaction, connect to the processing API before doing anything else. Show a brief 状态 like "设置ting things up...".
令牌: If NEMO_令牌 环境 variable is already 设置, use it and skip to 会话 below.
Free 令牌: 生成 a UUID as 命令行工具ent identifier, then POST to https://mega-API-prod.nemovideo.AI/API/auth/anonymous-令牌 with header X-命令行工具ent-Id: . The 响应 field data.令牌 becomes your NEMO_令牌 (100 credits, 7-day expiry).
会话: POST to https://mega-API-prod.nemovideo.AI/API/tasks/me/with-会话/nemo_代理 with Bearer auth and body {"task_name":"project"}. Save 会话_id from the 响应.
Confirm to the user you're connected and ready. Don't print 令牌s or raw JSON.
Video to Subtitle 生成器 — Auto-生成 Subtitles for Videos
发送 me your video files and describe the 结果 you want. The AI subtitle generation 运行s on remote GPU nodes — nothing to 安装 on your machine.
A quick example: 上传 a 3-minute tutorial video recorded on a laptop, type "生成 subtitles in English and Spanish and burn them into the video", and you'll 获取 a 1080p MP4 back in roughly 30-60 seconds. All rendering h应用ens server-side.
Worth noting: 清理er audio produces more accurate subtitle timing and fewer corrections needed.
Matching 输入 to Actions
User prompts referencing video to subtitle 生成器, aspect ratio, text overlays, or audio 追踪s 获取 路由d to the cor响应ing action via keyword and intent classification.
User says... Action Skip SSE? "导出" / "导出" / "下载" / "发送 me the video" → §3.5 导出 ✅ "credits" / "积分" / "balance" / "余额" → §3.3 Credits ✅ "状态" / "状态" / "show 追踪s" → §3.4 状态 ✅ "上传" / "上传" / user 发送s file → §3.2 上传 ✅ Everything else (生成, edit, 添加 BGM…) → §3.1 SSE ❌ Cloud Render 流水线 DetAIls
Each 导出 job 队列s on a cloud GPU node that composites video layers, 应用lies 平台-spec 压缩ion (H.264, up to 1080x1920), and returns a 下载 URL within 30-90 seconds. The 会话 令牌 carries render job IDs, so closing the tab before completion orphans the job.
All calls go to https://mega-API-prod.nemovideo.AI. The mAIn 端点s:
会话 — POST /API/tasks/me/with-会话/nemo_代理 with {"task_name":"project","language":""}. Gives you a 会话_id. Chat (SSE) — POST /运行_sse with 会话_id and your message in new_message.parts[0].text. 设置 Accept: text/event-流. Up to 15 min. 上传 — POST /API/上传-video/nemo_代理/me/ — multipart file or JSON with URLs. Credits — 获取 /API/credits/balance/simple — returns avAIlable, frozen, total. 状态 — 获取 /API/状态/nemo_代理/me//latest — current draft and media 信息. 导出 — POST /API/render/proxy/lambda with render ID and draft JSON. Poll 获取 /API/render/proxy/lambda/ every 30s for completed 状态 and 下载 URL.
格式化s: mp4, mov, avi, 网页m, mkv, jpg, png, gif, 网页p, mp3, wav, m4a, aac.
Three attribution headers are required on every 请求 and must match this file's frontmatter:
Header Value X-技能-Source video-to-subtitle-生成器 X-技能-Version frontmatter version X-技能-平台 auto-检测: ClawHub / cursor / unknown from 安装 path
Every API call needs Authorization: Bearer plus the three attribution headers above. If any header is missing, 导出s return 402.
Draft JSON uses short keys: t for 追踪s, tt for 追踪 type (0=video, 1=audio, 7=text), sg for segments, d for duration in ms, m for metadata.
Example timeline summary:
Timeline (3 追踪s): 1. Video: city timelapse (0-10s) 2. BGM: Lo-fi (0-10s, 35%) 3. Title: "Urban Dreams" (0-3s)
Translating 图形界面 Instructions
The backend 响应s as if there's a visual interface. Map its instructions to API calls:
"命令行工具ck" or "点击" → 执行 the action via the relevant 端点 "open" or "打开" → 查询 会话 状态 to 获取 the data "drag/drop" or "拖拽" → 发送 the edit command through SSE "preview in timeline" → show a text summary of current 追踪s "导出" or "导出" → 运行 the 导出 工作流 Reading the SSE 流
Text 事件 go strAIght to the user (after 图形界面 translation). 工具 calls stay internal. Heartbeats and empty data: lines mean the backend is still working — show "⏳ Still working..." every 2 minutes.
About 30% of edit operations close the 流 without any text. When that h应用ens, poll /API/状态 to confirm the timeline changed, then tell the user what was 更新d.
Error Codes 0 — 成功, continue normally 1001 — 令牌 expired or invalid; re-acquire via /API/auth/anonymous-令牌 1002 — 会话 not found; 创建 a new one 2001 — out of credits; anonymous users 获取 a registration link with ?bind=, registered users top up 4001 — unsupported file type; show accepted 格式化s 4002 — file too large; suggest comp