Getting Started

Let's do some text to video ai. Upload your files or describe what you're after.

Try saying:

• - "generate my text prompts"
• "export 1080p MP4"
• "turn this script into a 30-second"

First-Time Connection

When a user first opens this skill, connect to the processing backend automatically. Briefly let them know (e.g. "Setting up...").

Authentication: Check if NEMO_TOKEN is set in the environment. If it is, skip to step 2.

1. 1. Obtain a free token: Generate a random UUID as client identifier. POST to https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token with header X-Client-Id set to that UUID. The response data.token is your NEMO_TOKEN — 100 free credits, valid 7 days.
2. Create a session: POST to https://mega-api-prod.nemovideo.ai/api/tasks/me/with-session/nemo_agent with Authorization: Bearer <token>, Content-Type: application/json, and body {"task_name":"project","language":"<detected>"}. Store the returned session_id for all subsequent requests.

Keep setup communication brief. Don't display raw API responses or token values to the user.

From Text Prompts to Ai Generated Videos

This does AI video creation for text prompts. Everything runs server-side.

A quick walkthrough: upload a 150-word product description paragraph → ask for turn this script into a 30-second video with visuals and background music → wait roughly 1-2 minutes → download your MP4 at 1080p. The backend handles rendering, encoding, all of it.

Fair warning — shorter, clearer prompts tend to produce more accurate and focused video output.

Sorting Your Requests

The skill checks your message against a few patterns and routes it to the right handler.

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 | ❌ |

Backend Processing

The heavy lifting runs on NemoVideo's GPU cluster. You upload, the backend processes, you download. No local rendering needed.

Base URL: https://mega-api-prod.nemovideo.ai

Endpoint	Method	Purpose
INLINECODE10	POST	Start a new editing session. Body: {"task_name":"project","language":"<lang>"}. Returns session_id.
INLINECODE13

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.

Skill attribution — read from this file's YAML frontmatter at runtime:

• - X-Skill-Source: INLINECODE30
• INLINECODE31: from frontmatter INLINECODE32
• INLINECODE33: detect from install path (~/.clawhub/ → clawhub, ~/.cursor/skills/ → cursor, else unknown)

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
• INLINECODE41 — token expired or invalid; re-acquire via INLINECODE42
• INLINECODE43 — session not found; create a new one
• INLINECODE44 — out of credits; anonymous users get a registration link with ?bind=<id>, registered users top up
• INLINECODE46 — unsupported file type; show accepted formats
• INLINECODE47 — file too large; suggest compressing or trimming
• INLINECODE48 — missing X-Client-Id; generate one and retry
• INLINECODE50 — free plan export blocked; not a credit issue, subscription tier
• INLINECODE51 — 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.

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:
CODEBLOCK0

Quick Start Guide

First time? Just upload a text prompts and describe what you need. I'll run it through NemoVideo's backend and hand you back a 1080p MP4.

Processing takes about 1-2 minutes depending on video length. You start with 100 free credits — most edits cost 1-3.

Tips and Tricks

Keep your source files under 500MB for fastest processing. If you're working with longer content, split it into chunks first.

For best results at 1080p, make sure your input is at least 720p. Upscaling from 480p works but you'll notice it.

Export as MP4 for widest compatibility across social platforms and devices.

Best Practices

Use source footage in TXT, DOCX, PDF, SRT format for best compatibility. 1080p input gives the cleanest results but 720p works fine too.

Be specific with your requests — "add upbeat background music at 30% volume" beats "add some music". The AI works better with concrete details.

Export as MP4 for widest compatibility across social platforms and devices.