Subtitle Generator Hinglish

generate video files into Hinglish captioned videos with this skill. Works with MP4, MOV, AVI, WebM files up to 500MB. Indian content creators use it for add...

Security Scan

The skill's declared inputs and runtime instructions generally match a cloud subtitle service, but small inconsistencies and a lack of provenance (no homepage/source) plus automatic token acquisition and an unexplained frontmatter config path deserve caution before install.

Purpose & Capability

Name/description match the runtime instructions: the skill uploads videos to a nemo video backend and returns captioned MP4s. Requesting a NEMO_TOKEN is appropriate for that purpose. However, the frontmatter metadata includes a configPaths entry (~/.config/nemovideo/) that the registry summary did not list — this mismatch is unexplained and could indicate stale metadata or an instruction to access a local config directory that the registry didn't surface.

Instruction Scope

SKILL.md instructs the agent to look for NEMO_TOKEN, and if missing to automatically POST to https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token to obtain one, then create sessions, upload files, read SSE streams, and poll render endpoints. Those actions align with the described feature set (upload, render, download), but the auto-token acquisition and session management mean the agent will contact an external service and upload user video content. The instructions do not reference reading unrelated local files or creds, but they do require constructing attribution headers (X-Skill-Platform auto-detection via install path), which could cause the agent to examine its environment/install path.

Install Mechanism

Instruction-only skill with no install steps or code files; nothing is downloaded or written to disk by an installer. This is the lowest-risk install mechanism.

Credentials

Only a single credential (NEMO_TOKEN) is declared and used, which is proportionate to a cloud API. However, the skill's ability to obtain an anonymous NEMO_TOKEN on behalf of the user (without a prior explicit credential) means the agent will call an external auth endpoint and receive a token that grants 100 free credits — the user should be aware this creates short-lived credentials and external backend access. The metadata/configPaths mismatch (frontmatter lists ~/.config/nemovideo/) is unexplained and suggests the skill may expect a local config file in some deployments.

Persistence & Privilege

always is false and the skill does not request permanent platform-wide presence. It instructs the agent to keep session_id for the session lifecycle (normal). Autonomous invocation is allowed (platform default) but not an extra privilege here.

What to consider before installing

This skill appears to be a thin wrapper around a nemo-video cloud API and will upload user videos to https://mega-api-prod.nemovideo.ai and require/use a NEMO_TOKEN. Before installing, consider: 1) provenance — the skill has no homepage or known source; verify the provider and read its privacy/data-retention policy; 2) sensitive content — uploaded videos will be sent to an external service, so avoid private/secret material unless you trust the operator; 3) token behavior — the skill will auto-request an anonymous token if you don't provide one (100 free credits, short expiry) which means it will make outbound network calls immediately; 4) metadata mismatch — the frontmatter references a local config path (~/.config/nemovideo/) even though the registry didn't list it — ask the author why and whether local config files will be read; 5) headers/platform detection — the agent may inspect its install path to set X-Skill-Platform. If you proceed, prefer supplying your own NEMO_TOKEN from a trusted account (so you control the credentials) and monitor outgoing requests during first use. If you need higher assurance, ask the publisher for a homepage, privacy policy, and source code before using with sensitive content.

Getting Started

Share your video files and I'll get started on Hinglish subtitle generation. Or just tell me what you're thinking.

Try saying:

• "generate my video files"
• "export 1080p MP4"
• "generate subtitles in Hinglish for my"

Quick Start Setup

This skill connects to a cloud processing backend. On first use, set up the connection automatically and let the user know ("Connecting...").

Token check: Look for NEMO_TOKEN in the environment. If found, skip to session creation. Otherwise:

• Generate a UUID as client identifier
• POST https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token with X-Client-Id header
• Extract data.token from the response — this is your NEMO_TOKEN (100 free credits, 7-day expiry)

Session: POST https://mega-api-prod.nemovideo.ai/api/tasks/me/with-session/nemo_agent with Bearer auth and body {"task_name":"project"}. Keep the returned session_id for all operations.

Let the user know with a brief "Ready!" when setup is complete. Don't expose tokens or raw API output.

Subtitle Generator Hinglish — Generate Hinglish Captions for Videos

This tool takes your video files and runs Hinglish subtitle generation through a cloud rendering pipeline. You upload, describe what you want, and download the result.

Say you have a 3-minute Hindi vlog recorded on a phone and want to generate subtitles in Hinglish for my YouTube video — the backend processes it in about 30-60 seconds and hands you a 1080p MP4.

Tip: shorter clips under 5 minutes process faster and produce more accurate Hinglish captions.

Matching Input to Actions

User prompts referencing subtitle generator hinglish, 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 requests must include: Authorization: Bearer <NEMO_TOKEN>, X-Skill-Source, X-Skill-Version, X-Skill-Platform. Missing attribution headers will cause export to fail with 402.

Three attribution headers are required on every request and must match this file's frontmatter:

Header	Value
X-Skill-Source	subtitle-generator-hinglish
X-Skill-Version	frontmatter version
X-Skill-Platform	auto-detect: clawhub / cursor / unknown from install path

API base: https://mega-api-prod.nemovideo.ai

Create session: POST /api/tasks/me/with-session/nemo_agent — body {"task_name":"project","language":"<lang>"} — returns task_id, session_id.

Send message (SSE): POST /run_sse — body {"app_name":"nemo_agent","user_id":"me","session_id":"<sid>","new_message":{"parts":[{"text":"<msg>"}]}} with Accept: text/event-stream. Max timeout: 15 minutes.

Upload: POST /api/upload-video/nemo_agent/me/<sid> — file: multipart -F "files=@/path", or URL: {"urls":["<url>"],"source_type":"url"}

Credits: GET /api/credits/balance/simple — returns available, frozen, total

Session state: GET /api/state/nemo_agent/me/<sid>/latest — key fields: data.state.draft, data.state.video_infos, data.state.generated_media

Export (free, no credits): POST /api/render/proxy/lambda — body {"id":"render_<ts>","sessionId":"<sid>","draft":<json>,"output":{"format":"mp4","quality":"high"}}. Poll GET /api/render/proxy/lambda/<id> every 30s until status = completed. Download URL at output.url.

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

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

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.

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)

Tips and Tricks

The backend processes faster when you're specific. Instead of "make it look better", try "generate subtitles in Hinglish for my YouTube video" — 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 YouTube, Instagram, and WhatsApp.

Common Workflows

Quick edit: Upload → "generate subtitles in Hinglish for my YouTube video" → 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.