Best Unified Video Lyrics

add video with audio into lyrics-synced videos with this skill. Works with MP4, MOV, AVI, WebM files up to 500MB. musicians and content creators use it for a...

Security Scan

The skill's stated purpose (syncing lyrics onto videos) aligns with its API calls, but there are inconsistent declarations and some runtime instructions that ask the agent to generate/store credentials and probe local install/config paths — these mismatches and minor scope creep merit caution.

Purpose & Capability

Name/description match the endpoints and actions described (upload, render, SSE, export). However the registry lists NEMO_TOKEN as a required env var while the SKILL.md instructs the agent to obtain an anonymous token automatically if none is set; the SKILL.md frontmatter also lists a config path (~/.config/nemovideo/) although the registry metadata reported no required config paths. This inconsistency between declared requirements and runtime behavior should be clarified.

Instruction Scope

Instructions include network calls to a third-party API (expected), uploading user files (expected), and persistent session/token management (expected). They also instruct the agent to detect an install path to set X-Skill-Platform headers (reading local install location), and to read the SKILL.md frontmatter for attribution. Asking the agent to probe filesystem locations and to 'store' tokens/session IDs expands scope beyond pure video processing and could lead to unintended access or persistent credentials if implemented without safeguards.

Install Mechanism

No install spec and no code files — instruction-only. Lowest install risk (nothing is written/executed by a packaged installer).

Credentials

Only one credential is declared (NEMO_TOKEN), which is proportional to a cloud-rendering API. However the skill both declares the token as required and provides an anonymous-token acquisition flow; it also references a specific config directory in its frontmatter. The token acquisition and storage behavior (generate UUID, POST to anonymous-token, 'store' token) should be understood before use because it implies persisting credentials beyond a single call.

Persistence & Privilege

always:false (no forced presence). The skill instructs storing session_id and token for subsequent requests (normal for session-based APIs), and notes orphaned jobs if sessions close. This is expected but means the skill will create and persist short-lived credentials and session state — users should know where these are stored and for how long.

What to consider before installing

This skill appears to do what it says (upload video, run cloud lyric-sync, return MP4), but there are a few things to consider before installing or invoking it: 1) Credential handling: the registry lists NEMO_TOKEN as required, yet the instructions will auto-request an anonymous token if one is not set and tell the agent to 'store' it — ask where tokens and session IDs are stored and how long they persist. 2) Local probing: the runtime asks the agent to detect install paths and read the SKILL.md frontmatter to set attribution headers — confirm whether that involves reading arbitrary files or only its own skill file. 3) External endpoint: the skill sends video and audio to mega-api-prod.nemovideo.ai — only proceed if you trust that service and its privacy/retention policy. 4) Ask the publisher to reconcile the mismatched metadata (required config paths vs registry) and to document exactly what is persisted and where; if you cannot verify these, treat it with caution or use a sandboxed environment.

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 recording into a 1080p MP4"
• "sync song lyrics as on-screen text timed to the vocals"
• "adding synchronized lyrics overlays 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.

Best Unified Video Lyrics — Sync Lyrics to Video Automatically

This tool takes your video with audio and runs AI lyrics sync through a cloud rendering pipeline. You upload, describe what you want, and download the result.

Say you have a 3-minute music video recording and want to sync song lyrics as on-screen text timed to the vocals — the backend processes it in about 1-2 minutes and hands you a 1080p MP4.

Tip: cleaner audio tracks produce more accurate lyric sync timing.

Matching Input to Actions

User prompts referencing best 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.

Base URL: https://mega-api-prod.nemovideo.ai

Endpoint	Method	Purpose
/api/tasks/me/with-session/nemo_agent	POST	Start a new editing session. Body: {"task_name":"project","language":"<lang>"}. Returns session_id.
/run_sse	POST	Send a user message. Body includes app_name, session_id, new_message. Stream response with Accept: text/event-stream. Timeout: 15 min.
/api/upload-video/nemo_agent/me/<sid>	POST	Upload a file (multipart) or URL.
/api/credits/balance/simple	GET	Check remaining credits (available, frozen, total).
/api/state/nemo_agent/me/<sid>/latest	GET	Fetch current timeline state (draft, video_infos, generated_media).
/api/render/proxy/lambda	POST	Start export. Body: {"id":"render_<ts>","sessionId":"<sid>","draft":<json>,"output":{"format":"mp4","quality":"high"}}. Poll status every 30s.

Accepted file types: 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: best-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.

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

SSE Event Handling

Event	Action
Text response	Apply GUI translation (§4), present to user
Tool call/result	Process internally, don't forward
heartbeat / empty data:	Keep waiting. Every 2 min: "⏳ Still working..."
Stream closes	Process final response

~30% of editing operations return no text in the SSE stream. When this happens: poll session state to verify the edit was applied, then summarize changes to the user.

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

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)

Common Workflows

Quick edit: Upload → "sync song lyrics as on-screen text timed to the vocals" → 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.

Tips and Tricks

The backend processes faster when you're specific. Instead of "make it look better", try "sync song lyrics as on-screen text timed to the vocals" — 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.