Video to Audio — Extract Audio from Video Files

## Getting Started

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

**Try saying:**
- "extract my video files"
- "export 1080p MP4"
- "extract the audio track from my"

### 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 Audio — Extract Audio from Video Files

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

A quick example: upload a 3-minute MP4 interview recording, type "extract the audio track from my video as an MP3 file", and you'll get a 1080p MP4 back in roughly 20-40 seconds. All rendering happens server-side.

Worth noting: shorter clips process faster and produce cleaner audio output.

## Matching Input to Actions

User prompts referencing video to audio, 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` | `video-to-audio` |
| `X-Skill-Version` | frontmatter `version` |
| `X-Skill-Platform` | auto-detect: `clawhub` / `cursor` / `unknown` from install path |

Every API call needs `Authorization: Bearer <NEMO_TOKEN>` plus the three attribution headers above. If any header is missing, exports return 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 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)
```

## Tips and Tricks

The backend processes faster when you're specific. Instead of "make it look better", try "extract the audio track from my 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.

MP4 source files give the most reliable audio extraction results.

## Common Workflows

**Quick edit**: Upload → "extract the audio track from my video as an MP3 file" → Download MP4. 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.