Turn a 2-minute product demo video into 1080p AI-tagged videos just by typing what you need. Whether it's generating AI-written metadata for uploaded videos...
---
name: generator-meta-ai
version: "1.0.0"
displayName: "Generator Meta AI β Generate AI Metadata for Videos"
description: >
Turn a 2-minute product demo video into 1080p AI-tagged videos just by typing what you need. Whether it's generating AI-written metadata for uploaded videos or quick social content, drop your video clips and describe the result you want. No timeline dragging, no export settings β 20-40 seconds from upload to download.
metadata: {"openclaw": {"emoji": "π·οΈ", "requires": {"env": ["NEMO_TOKEN"], "configPaths": ["~/.config/nemovideo/"]}, "primaryEnv": "NEMO_TOKEN", "variant": "short_prompts"}}
---
## Getting Started
> Share your video clips and I'll get started on AI metadata generation. Or just tell me what you're thinking.
**Try saying:**
- "generate my video clips"
- "export 1080p MP4"
- "generate title, description, and tags for"
### 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.
# Generator Meta AI β Generate AI Metadata for Videos
This tool takes your video clips and runs AI metadata generation through a cloud rendering pipeline. You upload, describe what you want, and download the result.
Say you have a 2-minute product demo video and want to generate title, description, and tags for my video using AI β the backend processes it in about 20-40 seconds and hands you a 1080p MP4.
Tip: shorter and clearer videos produce more accurate AI-generated metadata.
## Matching Input to Actions
User prompts referencing generator meta ai, aspect ratio, text overlays, or audio tracks get routed to the corresponding action via keyword and intent classification.
| User says... | Action | Skip SSE? |
|-------------|--------|----------|
| "export" / "ε―ΌεΊ" / "download" / "send me the video" | β Β§3.5 Export | β
|
| "credits" / "η§―ε" / "balance" / "δ½ι’" | β Β§3.3 Credits | β
|
| "status" / "ηΆζ" / "show tracks" | β Β§3.4 State | β
|
| "upload" / "δΈδΌ " / user sends file | β Β§3.2 Upload | β
|
| Everything else (generate, edit, add BGMβ¦) | β Β§3.1 SSE | β |
## 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** β `POST /api/tasks/me/with-session/nemo_agent` with `{"task_name":"project","language":"<lang>"}`. Gives you a `session_id`.
2. **Chat (SSE)** β `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** β `POST /api/upload-video/nemo_agent/me/<sid>` β multipart file or JSON with URLs.
4. **Credits** β `GET /api/credits/balance/simple` β returns `available`, `frozen`, `total`.
5. **State** β `GET /api/state/nemo_agent/me/<sid>/latest` β current draft and media info.
6. **Export** β `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` | `generator-meta-ai` |
| `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 β 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 "ηΉε»" β execute the action via the relevant endpoint
- "open" or "ζεΌ" β query session state to get the data
- "drag/drop" or "ζζ½" β send the edit command through SSE
- "preview in timeline" β show a text summary of current tracks
- "Export" or "ε―ΌεΊ" β 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 β show "β³ 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 Codes
- `0` β success, continue normally
- `1001` β token expired or invalid; re-acquire via `/api/auth/anonymous-token`
- `1002` β session not found; create a new one
- `2001` β out of credits; anonymous users get a registration link with `?bind=<id>`, registered users top up
- `4001` β unsupported file type; show accepted formats
- `4002` β file too large; suggest compressing or trimming
- `400` β missing `X-Client-Id`; generate one and retry
- `402` β free plan export blocked; not a credit issue, subscription tier
- `429` β rate limited; wait 30s and retry once
## Common Workflows
**Quick edit**: Upload β "generate title, description, and tags for my video using AI" β 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.
## Tips and Tricks
The backend processes faster when you're specific. Instead of "make it look better", try "generate title, description, and tags for my video using AI" β 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.
don't have the plugin yet? install it then click "run inline in claude" again.