Caption Generator Ai

Skip the learning curve of professional editing software. Describe what you want — add captions in English and Spanish with auto-sync — and get captioned vid...

Security Scan

The skill's requests and runtime instructions are consistent with a cloud-based captioning service (it only needs a single service token and uploads video files), but there are a few small metadata/instruction mismatches and privacy-relevant behaviours you should be aware of before installing.

Purpose & Capability

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.

Instruction Scope

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.

Install Mechanism

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.

Credentials

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.

Persistence & Privilege

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.

Assessment

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 ~/.config/nemovideo/. If you prefer, provide your own token or delete stored tokens after use. - Filesystem reads: the skill asks the agent to detect install path to set an X-Skill-Platform header and to read the skill's frontmatter for attribution. This requires read access to skill files and common install paths — benign for attribution but worth noting if you have strict filesystem access rules. - Metadata mismatch: the registry listing shows no required config paths while SKILL.md declares one (~/.config/nemovideo/). Ask the publisher to clarify where tokens/sessions are stored and whether any other files are written. If you accept those tradeoffs, the skill is internally consistent with its description. If you are concerned about privacy or untrusted external services, do not upload sensitive videos and consider providing your own managed token or avoiding the skill.

Getting Started

Ready when you are. Drop your video files here or describe what you want to make.

Try saying:

• "add a 3-minute tutorial video recording into a 1080p MP4"
• "add captions in English and Spanish with auto-sync"
• "adding auto-generated subtitles to videos for content creators"

First-Time Connection

When a user first opens this skill, connect to the processing backend automatically. Briefly let them know (e.g. "Setting up...").

Authentication: Check if NEMO_TOKEN is set in the environment. If it is, skip to step 2.

1. Obtain a free token: Generate a random UUID as client identifier. POST to https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token with header X-Client-Id set to that UUID. The response data.token is your NEMO_TOKEN — 100 free credits, valid 7 days.
2. Create a session: POST to https://mega-api-prod.nemovideo.ai/api/tasks/me/with-session/nemo_agent with Authorization: Bearer <token>, Content-Type: application/json, and body {"task_name":"project","language":"<detected>"}. Store the returned session_id for all subsequent requests.

Keep setup communication brief. Don't display raw API responses or token values to the user.

Caption Generator AI — Generate Captions for Videos

Send me your video files and describe the result you want. The AI caption generation runs on remote GPU nodes — nothing to install on your machine.

A quick example: upload a 3-minute tutorial video recording, type "add captions in English and Spanish with auto-sync", and you'll get a 1080p MP4 back in roughly 30-60 seconds. All rendering happens server-side.

Worth noting: shorter clips under 5 minutes generate captions significantly faster.

Matching Input to Actions

User prompts referencing caption generator ai, aspect ratio, text overlays, or audio tracks get routed to the corresponding action via keyword and intent classification.

User says...	Action	Skip SSE?
"export" / "导出" / "download" / "send me the video"	→ §3.5 Export	✅
"credits" / "积分" / "balance" / "余额"	→ §3.3 Credits	✅
"status" / "状态" / "show tracks"	→ §3.4 State	✅
"upload" / "上传" / user sends file	→ §3.2 Upload	✅
Everything else (generate, edit, add BGM…)	→ §3.1 SSE	❌

Cloud Render Pipeline Details

Each export job queues on a cloud GPU node that composites video layers, applies platform-spec compression (H.264, up to 1080x1920), and returns a download URL within 30-90 seconds. The session token 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 endpoints:

1. Session — POST /api/tasks/me/with-session/nemo_agent with {"task_name":"project","language":"<lang>"}. Gives you a session_id.
2. Chat (SSE) — POST /run_sse with session_id and your message in new_message.parts[0].text. Set Accept: text/event-stream. Up to 15 min.
3. Upload — POST /api/upload-video/nemo_agent/me/<sid> — multipart file or JSON with URLs.
4. Credits — GET /api/credits/balance/simple — returns available, frozen, total.
5. State — GET /api/state/nemo_agent/me/<sid>/latest — current draft and media info.
6. Export — POST /api/render/proxy/lambda with render ID and draft JSON. Poll GET /api/render/proxy/lambda/<id> every 30s for completed status and download URL.

Formats: mp4, mov, avi, webm, mkv, jpg, png, gif, webp, mp3, wav, m4a, aac.

Skill attribution — read from this file's YAML frontmatter at runtime:

• X-Skill-Source: caption-generator-ai
• X-Skill-Version: from frontmatter version
• X-Skill-Platform: detect from install path (~/.clawhub/ → clawhub, ~/.cursor/skills/ → cursor, else unknown)

Every API call needs Authorization: Bearer <NEMO_TOKEN> plus the three attribution headers above. If any header is missing, exports return 402.

Draft JSON uses short keys: t for tracks, tt for track type (0=video, 1=audio, 7=text), sg for segments, d for duration in ms, m for metadata.

Example timeline summary:

Timeline (3 tracks): 1. Video: city timelapse (0-10s) 2. BGM: Lo-fi (0-10s, 35%) 3. Title: "Urban Dreams" (0-3s)

Translating GUI Instructions

The backend responds as if there's a visual interface. Map its instructions to API calls:

• "click" or "点击" → execute the action via the relevant endpoint
• "open" or "打开" → query session state to get the data
• "drag/drop" or "拖拽" → send the edit command through SSE
• "preview in timeline" → show a text summary of current tracks
• "Export" or "导出" → run the export workflow

Reading the SSE Stream

Text events go straight to the user (after GUI translation). Tool 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 stream without any text. When that happens, poll /api/state to confirm the timeline changed, then tell the user what was updated.

Error Codes

• 0 — success, continue normally
• 1001 — token expired or invalid; re-acquire via /api/auth/anonymous-token
• 1002 — session not found; create a new one
• 2001 — out of credits; anonymous users get a registration link with ?bind=<id>, registered users top up
• 4001 — unsupported file type; show accepted formats
• 4002 — file too large; suggest compressing or trimming
• 400 — missing X-Client-Id; generate one and retry
• 402 — free plan export blocked; not a credit issue, subscription tier
• 429 — rate limited; wait 30s and retry once

Common Workflows

Quick edit: Upload → "add captions in English and Spanish with auto-sync" → Download MP4. Takes 30-60 seconds for a 30-second clip.

Batch style: Upload multiple files in one session. Process them one by one with different instructions. Each gets its own render.

Iterative: Start with a rough cut, preview the result, then refine. The session keeps your timeline state so you can keep tweaking.

Tips and Tricks

The backend processes faster when you're specific. Instead of "make it look better", try "add captions in English and Spanish with auto-sync" — concrete instructions get better results.

Max file size is 500MB. Stick to MP4, MOV, AVI, WebM for the smoothest experience.

Export as MP4 for widest compatibility across platforms.