Audio Replace Online

replace video with audio into re-audioned video files with this skill. Works with MP4, MOV, AVI, WebM files up to 500MB. content creators, YouTubers, podcast...

Security Scan

The skill's behavior (uploading user videos to an unfamiliar third‑party API and auto‑creating tokens) broadly matches its stated purpose, but there are inconsistencies (metadata vs. registry), no homepage/privacy info, and the instructions imply reading runtime/install paths — the privacy/credential handling merits caution.

Purpose & Capability

The skill claims to perform cloud-based audio replacement and only requests a single backend credential (NEMO_TOKEN), which is appropriate for a hosted service. However, the SKILL.md frontmatter lists a config path (~/.config/nemovideo/) that the registry metadata did not, creating an inconsistency about whether it will access local config files. The required headers and endpoints all point to the same nemovideo.ai backend, which is coherent with the stated purpose.

Instruction Scope

The runtime instructions direct the agent to upload user video/audio to https://mega-api-prod.nemovideo.ai, create sessions, poll SSE streams, and automatically obtain an anonymous token if none is present. The skill also instructs auto-detecting install/platform information (reading install path) and references a local config path in the frontmatter — both imply filesystem access beyond just reading the NEMO_TOKEN env var. There is no privacy/retention policy or clear guidance about how uploaded media are used or stored. The guidance to 'don't expose tokens' is good, but the skill still handles sensitive data (user media and auth tokens) and will transmit them to a third party.

Install Mechanism

This is an instruction-only skill with no install spec and no code files, so nothing will be written to disk or installed by default. That reduces supply‑chain risk compared with download/install mechanics.

Credentials

Only NEMO_TOKEN is declared as required (primary credential), which is proportional to calling a hosted video-processing API. The SKILL.md also instructs creating an anonymous token when none is supplied, so a user-supplied token is optional. The frontmatter's reference to a config path (~/.config/nemovideo/) and the platform auto-detection mean the skill may attempt to read local paths or metadata — this is not justified by the description and should be clarified before use.

Persistence & Privilege

always:false and no install/deamonization are appropriate. The skill keeps an in-memory session_id for jobs, which is normal. The only durability question is the frontmatter config path (suggesting possible local config read/write), but no explicit persistent writes or system-wide config changes are described.

What to consider before installing

This skill will upload your videos and any replacement audio to a third‑party service (mega-api-prod.nemovideo.ai) and use a NEMO_TOKEN (or create an anonymous one) to authenticate. Before installing or invoking: 1) Verify the backend/service owner and read its privacy/retention policy (none provided in the registry). 2) Do not provide high‑value or unrelated secrets as NEMO_TOKEN; prefer letting the skill obtain an anonymous token if you want minimal linkage. 3) Ask the publisher whether the skill will read ~/.config or other local paths and whether tokens or session IDs are persisted. 4) Test with non‑sensitive sample media first to confirm behavior. 5) If you need stronger guarantees about data handling, ask for a provenance page or avoid using the skill until the maintainer/publisher is known.

Getting Started

Send me your video with audio and I'll handle the AI audio replacement. Or just describe what you're after.

Try saying:

• "replace a 2-minute interview clip with background noise into a 1080p MP4"
• "replace the original audio track with a clean voiceover file"
• "swapping out bad audio tracks with clean recordings for content creators, YouTubers, podcasters"

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.

Audio Replace Online — Swap Audio Tracks in Videos

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

A quick example: upload a 2-minute interview clip with background noise, type "replace the original audio track with a clean voiceover file", and you'll get a 1080p MP4 back in roughly 30-60 seconds. All rendering happens server-side.

Worth noting: sync your replacement audio to match the video length before uploading to get the cleanest result.

Matching Input to Actions

User prompts referencing 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.

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.

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

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

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

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.

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

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)

Common Workflows

Quick edit: Upload → "replace the original audio track with a 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.

Tips and Tricks

The backend processes faster when you're specific. Instead of "make it look better", try "replace the original audio track with a 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 across platforms and devices.