Video To Mp3

Get extracted MP3 audio ready to post, without touching a single slider. Upload your video files (MP4, MOV, AVI, WebM, up to 500MB), say something like "extr...

Security Scan

The skill's behavior mostly matches a cloud-based video→MP3 extractor, but there are small inconsistencies and file-system/credential behaviors you should understand before sending video files to an unknown backend.

Purpose & Capability

The skill's stated purpose (upload a video, extract MP3 via a cloud backend) aligns with the single required credential (NEMO_TOKEN) and the API endpoints in SKILL.md. However, registry metadata lists no config paths while the SKILL.md frontmatter and runtime instructions reference a config path (~/.config/nemovideo/) and require reading the SKILL.md frontmatter — an inconsistency between declared registry requirements and the runtime instructions.

Instruction Scope

Instructions tell the agent to upload user video files (up to 500MB) to https://mega-api-prod.nemovideo.ai, create sessions, poll SSE endpoints, and include attribution headers. They also instruct the agent to read this skill's YAML frontmatter and detect install paths (~/.clawhub/, ~/.cursor/skills/) to set X-Skill-Platform. Those file-system reads are not declared in the registry and expand the scope beyond just 'send this file to an API.'

Install Mechanism

No install spec and no code files — instruction-only. This is the lowest install risk because nothing is written to disk by an installer.

Credentials

Only one required environment variable is declared (NEMO_TOKEN), which is proportionate to a cloud service. However SKILL.md also describes obtaining an anonymous token by POSTing to an auth endpoint if NEMO_TOKEN is missing (it will mint a short-lived anonymous token). The registry declares NEMO_TOKEN as required but the instructions will generate one if absent — this mismatch should be noted. There are no other unrelated credentials requested.

Persistence & Privilege

The skill does not request always:true, does not modify other skills, and does not require persistent system-level privileges. It creates and uses ephemeral sessions on the backend, which is consistent with its purpose.

What to consider before installing

This skill will upload your video files to an external service (mega-api-prod.nemovideo.ai) and requires/provides a bearer token (NEMO_TOKEN). Before installing or invoking: 1) Verify you trust the remote domain/operator and find a privacy/retention policy — there's no homepage provided here. 2) Understand that the skill will read its own frontmatter and probe common install paths in your home directory to set an attribution header — if you don't want local path metadata exposed, don't install. 3) If you don't already have a NEMO_TOKEN, the skill will request an anonymous token from the backend automatically (100 free credits, 7-day expiry) — consider whether you want an unknown service to mint and manage tokens for you. 4) Avoid uploading sensitive or confidential video content until you confirm the service's storage/retention practices. 5) The registry metadata inconsistently omits the config path that SKILL.md references; ask the publisher for clarification (or a homepage) before use. If you are uncomfortable, do not install or use the skill and consider running a network/traffic inspection or using a sandbox to test its behavior first.

Getting Started

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

Try saying:

• "convert my video files"
• "export audio only MP3"
• "extract the audio from this video"

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.

Video to MP3 — Extract Audio from Any Video

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

Say you have a 4-minute YouTube video download and want to extract the audio from this video as an MP3 file — the backend processes it in about 20-40 seconds and hands you a audio only MP3.

Tip: shorter videos extract faster — trim your video first if you only need a specific segment.

Matching Input to Actions

User prompts referencing video to mp3, 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: video-to-mp3
• 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 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)

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

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.

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 "extract the audio from this video as an MP3 file" — concrete instructions get better results.

Max file size is 500MB. Stick to MP4, MOV, AVI, WebM for the smoothest experience.

MP3 at 192kbps gives a good balance of file size and audio quality for most uses.

Common Workflows

Quick edit: Upload → "extract the audio from this video as an MP3 file" → Download MP3. Takes 20-40 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.