Ai Unified Video Lyrics

Skip the learning curve of professional editing software. Describe what you want — sync song lyrics as animated captions to the beat of the video — and get l...

Security Scan

The skill's declared purpose (remote lyrics-sync rendering) matches its runtime instructions, but there are modest incoherencies and privacy/behavior concerns (automatic phone-home, metadata mismatch about config paths, and opaque token handling) you should understand before installing.

Purpose & Capability

The skill claims to perform remote video lyric-syncing and all API endpoints and request patterns in SKILL.md align with that purpose. Requiring a NEMO_TOKEN is reasonable for a hosted rendering service. Minor inconsistency: the registry metadata reported no required config paths, but the skill's frontmatter includes configPaths ("~/.config/nemovideo/"). Also the skill declares NEMO_TOKEN required yet provides an anonymous-token auto-provision flow, which is functionally fine but could be misleading.

Instruction Scope

The SKILL.md instructs the agent to automatically connect to the remote backend on first open (POST to an external endpoint) and to auto-generate/store tokens and session IDs. That means the skill will 'phone home' and obtain credentials without an explicit user action beyond opening the skill. It also instructs reading install paths to set X-Skill-Platform headers (inspects ~/.clawhub/ and ~/.cursor/skills/), which requires inspecting local paths. The file-upload and render/export workflows send user media to an external domain (mega-api-prod.nemovideo.ai) — expected for the stated purpose but important to surface as a privacy risk.

Install Mechanism

Instruction-only skill with no install spec and no code files — nothing is written to disk by an installer. This is the lowest install risk.

Credentials

Only one credential (NEMO_TOKEN) is declared as required and as primaryEnv, which is proportionate for a cloud rendering service. However, the skill's runtime will auto-provision an anonymous NEMO_TOKEN if none is present, so requiring the env var is partly informational. The frontmatter's configPaths entry is out-of-band relative to registry metadata and suggests it may access a local config directory; that should be justified to the user.

Persistence & Privilege

always:false and no install or persistent modification of other skills are present. The skill stores a session_id for its own requests (expected). It does not request elevated or always-on privileges.

What to consider before installing

This skill appears to do what it claims (upload a video to a Nemo backend and return a rendered, lyrics-synced file), but you should weigh privacy and transparency before installing: - The skill will automatically connect to https://mega-api-prod.nemovideo.ai on first use and may auto-generate an anonymous token without an explicit consent step — expect network activity as soon as you open the skill. - Uploaded media and any associated text/instructions are sent to the remote service; do not upload content you cannot share. Confirm the service's privacy policy and retention rules (homepage is missing in the registry). - The skill will inspect local paths to set X-Skill-Platform headers (it infers install path); if you prefer no local path probing, ask the publisher to remove or explain this behavior. - There is a minor metadata mismatch (configPaths present in the frontmatter but not in registry metadata) — ask the author to clarify what local files or directories the skill will access and why. If you want to proceed, prefer supplying a token you control (NEMO_TOKEN) after verifying the provider, or request the publisher add an explicit opt-in step before any network calls. If any of these behaviors are unacceptable, do not install and ask for a version that requires explicit user consent before connecting or uploading files.

Getting Started

Got video with audio to work with? Send it over and tell me what you need — I'll take care of the AI lyrics sync.

Try saying:

• "add a 3-minute music video file into a 1080p MP4"
• "sync song lyrics as animated captions to the beat of the video"
• "adding synced lyric captions to music videos for musicians and 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.

AI Unified Video Lyrics — Sync Lyrics to Music Videos

Send me your video with audio and describe the result you want. The AI lyrics sync runs on remote GPU nodes — nothing to install on your machine.

A quick example: upload a 3-minute music video file, type "sync song lyrics as animated captions to the beat of the video", and you'll get a 1080p MP4 back in roughly 1-2 minutes. All rendering happens server-side.

Worth noting: cleaner audio tracks produce more accurate lyric sync results.

Matching Input to Actions

User prompts referencing ai unified video lyrics, 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: ai-unified-video-lyrics
• X-Skill-Version: from frontmatter version
• X-Skill-Platform: detect from install path (~/.clawhub/ → clawhub, ~/.cursor/skills/ → cursor, else unknown)

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.

Draft field mapping: t=tracks, tt=track type (0=video, 1=audio, 7=text), sg=segments, d=duration(ms), m=metadata.

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

Backend Response Translation

The backend assumes a GUI exists. Translate these into API actions:

Backend says	You do
"click [button]" / "点击"	Execute via API
"open [panel]" / "打开"	Query session state
"drag/drop" / "拖拽"	Send edit via SSE
"preview in timeline"	Show track summary
"Export button" / "导出"	Execute 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 Handling

Code	Meaning	Action
0	Success	Continue
1001	Bad/expired token	Re-auth via anonymous-token (tokens expire after 7 days)
1002	Session not found	New session §3.0
2001	No credits	Anonymous: show registration URL with ?bind=<id> (get <id> from create-session or state response when needed). Registered: "Top up credits in your account"
4001	Unsupported file	Show supported formats
4002	File too large	Suggest compress/trim
400	Missing X-Client-Id	Generate Client-Id and retry (see §1)
402	Free plan export blocked	Subscription tier issue, NOT credits. "Register or upgrade your plan to unlock export."
429	Rate limit (1 token/client/7 days)	Retry in 30s once

Tips and Tricks

The backend processes faster when you're specific. Instead of "make it look better", try "sync song lyrics as animated captions to the beat of the 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 streaming and social platforms.

Common Workflows

Quick edit: Upload → "sync song lyrics as animated captions to the beat of the video" → Download MP4. Takes 1-2 minutes 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.