Video Audio Replace Online

Get re-audioed MP4 ready to post, without touching a single slider. Upload your video with audio (MP4, MOV, AVI, WebM, up to 500MB), say something like "repl...

Security Scan

The skill's instructions and required token align with a cloud video re-audio service, but there are inconsistencies in declared config paths and a few minor scope questions you should review before installing.

Purpose & Capability

The name/description (cloud video audio replacement) match the runtime instructions (upload, render, download via nemovideo.ai) and the single required credential (NEMO_TOKEN) is appropriate for that purpose. However, the SKILL.md frontmatter references a config path (~/.config/nemovideo/) that is not listed in the registry metadata — an inconsistency that should be clarified (why a local config path is declared and whether the skill will read or write it).

Instruction Scope

Instructions stay within the declared purpose (session creation, uploads, SSE, export/polling). They include generating an anonymous token if NEMO_TOKEN is not present and saving session_id. A minor scope concern: the skill asks callers to auto-detect an install path value for X-Skill-Platform (reading an install path may require access to agent install metadata), and the SKILL.md frontmatter mentions a local config path — neither action is necessary for core audio-replace functionality and should be explained.

Install Mechanism

Instruction-only skill with no install spec or code files; nothing is written to disk by the skill itself in the provided materials. This is the lowest-risk install mechanism.

Credentials

The only required environment variable is NEMO_TOKEN (declared as primary credential), which is reasonable for a cloud service. The SKILL.md metadata also references a config path (~/.config/nemovideo/) not listed in the registry entry — it's unclear whether the skill will read or store tokens/config there. Confirm whether the skill will access that path and whether NEMO_TOKEN could be stored or read from it.

Persistence & Privilege

always:false (normal). The skill can be invoked autonomously by the agent (default behavior) and will call external network endpoints (nemovideo.ai). This is expected for a cloud render service but increases blast radius — if you permit autonomous invocation, the agent could upload user videos and call external APIs without interactive confirmation unless the agent is instructed otherwise. The declared config path implies possible local persistence; clarify whether the skill will write to ~/.config/nemovideo/.

What to consider before installing

This skill appears to do what it says (upload your video to nemovideo.ai, replace audio, and return a rendered MP4) and only requires a single service token (NEMO_TOKEN). Before installing: (1) Confirm you trust the domain https://mega-api-prod.nemovideo.ai and are comfortable uploading videos (these files go to that service). (2) Ask the maintainer to explain the inconsistent metadata: SKILL.md mentions a local config path (~/.config/nemovideo/) but the registry lists none — find out whether the skill will read/write that directory or store tokens there. (3) Be aware that if you allow autonomous invocation, the agent may call the API and upload files without per-action prompts. (4) If you plan to reuse a service token across tools, consider creating a scoped/token for this skill instead of reusing high-privilege credentials. If you want, ask the skill author to remove or justify the config-path requirement and to document exactly what metadata or local paths it will access.

Getting Started

Share your video with audio and I'll get started on AI audio replacement. Or just tell me what you're thinking.

Try saying:

• "replace my video with audio"
• "export 1080p MP4"
• "replace the original audio with this"

Automatic Setup

On first interaction, connect to the processing API before doing anything else. Show a brief status like "Setting things up...".

Token: If NEMO_TOKEN environment variable is already set, use it and skip to Session below.

Free token: Generate a UUID as client identifier, then POST to https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token with header X-Client-Id: <uuid>. The response field data.token becomes your NEMO_TOKEN (100 credits, 7-day expiry).

Session: POST to https://mega-api-prod.nemovideo.ai/api/tasks/me/with-session/nemo_agent with Bearer auth and body {"task_name":"project"}. Save session_id from the response.

Confirm to the user you're connected and ready. Don't print tokens or raw JSON.

Video Audio Replace Online — Swap Video Audio Track Online

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

Say you have a 2-minute interview clip with background noise and want to replace the original audio with this clean voiceover file — the backend processes it in about 30-60 seconds and hands you a 1080p MP4.

Tip: make sure your replacement audio file matches the video length to avoid sync issues.

Matching Input to Actions

User prompts referencing video audio replace online, 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.

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

Header	Value
X-Skill-Source	video-audio-replace-online
X-Skill-Version	frontmatter version
X-Skill-Platform	auto-detect: clawhub / cursor / unknown from install path

Include Authorization: Bearer <NEMO_TOKEN> and all attribution headers on every request — omitting them triggers a 402 on export.

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)

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 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 "replace the original audio with this clean voiceover file" — 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.

Common Workflows

Quick edit: Upload → "replace the original audio with this clean voiceover file" → 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.