Sora AI Video Generation — Generate Videos from Text Prompts

## Getting Started

> Share your text prompts and I'll get started on AI video generation. Or just tell me what you're thinking.

**Try saying:**
- "generate my text prompts"
- "export 1080p MP4"
- "generate a 10-second cinematic video of"

### 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.

# Sora AI Video Generation — Generate Videos from Text Prompts

Drop your text prompts in the chat and tell me what you need. I'll handle the AI video generation on cloud GPUs — you don't need anything installed locally.

Here's a typical use: you send a a short text description like 'a dog running on a beach at sunset', ask for generate a 10-second cinematic video of a futuristic city at night with neon lights, and about 1-3 minutes later you've got a MP4 file ready to download. The whole thing runs at 1080p by default.

One thing worth knowing — shorter, more specific prompts tend to produce more accurate and consistent results.

## Matching Input to Actions

User prompts referencing sora ai video generation, 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.

Skill attribution — read from this file's YAML frontmatter at runtime:
- `X-Skill-Source`: `sora-ai-video-generation`
- `X-Skill-Version`: from frontmatter `version`
- `X-Skill-Platform`: detect from install path (`~/.clawhub/` → `clawhub`, `~/.cursor/skills/` → `cursor`, else `unknown`)

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

**API base**: `https://mega-api-prod.nemovideo.ai`

**Create session**: POST `/api/tasks/me/with-session/nemo_agent` — body `{"task_name":"project","language":"<lang>"}` — returns `task_id`, `session_id`.

**Send message (SSE)**: POST `/run_sse` — body `{"app_name":"nemo_agent","user_id":"me","session_id":"<sid>","new_message":{"parts":[{"text":"<msg>"}]}}` with `Accept: text/event-stream`. Max timeout: 15 minutes.

**Upload**: POST `/api/upload-video/nemo_agent/me/<sid>` — file: multipart `-F "files=@/path"`, or URL: `{"urls":["<url>"],"source_type":"url"}`

**Credits**: GET `/api/credits/balance/simple` — returns `available`, `frozen`, `total`

**Session state**: GET `/api/state/nemo_agent/me/<sid>/latest` — key fields: `data.state.draft`, `data.state.video_infos`, `data.state.generated_media`

**Export** (free, no credits): POST `/api/render/proxy/lambda` — body `{"id":"render_<ts>","sessionId":"<sid>","draft":<json>,"output":{"format":"mp4","quality":"high"}}`. Poll GET `/api/render/proxy/lambda/<id>` every 30s until `status` = `completed`. Download URL at `output.url`.

Supported formats: mp4, mov, avi, webm, mkv, jpg, png, gif, webp, mp3, wav, m4a, aac.

### 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 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)
```

### 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

## Common Workflows

**Quick edit**: Upload → "generate a 10-second cinematic video of a futuristic city at night with neon lights" → Download MP4. Takes 1-3 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 "generate a 10-second cinematic video of a futuristic city at night with neon lights" — concrete instructions get better results.

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

Export as MP4 for widest compatibility across social platforms and video editors.