Ai To Video

Get generated video clips ready to post, without touching a single slider. Upload your text or prompts (TXT, DOCX, PDF, URL, up to 50MB), say something like...

Security Scan

The skill's declared purpose (convert text to video) aligns with its network calls and single credential request, but there are inconsistencies and privacy-relevant behaviors (filesystem detection for attribution headers, mismatched metadata, and an anonymous-token flow) that merit caution before installing.

Purpose & Capability

The skill's name/description map to the API endpoints it calls (session, upload, render). Requesting a single service token (NEMO_TOKEN) is proportionate. However, the SKILL.md metadata lists a required config path (~/.config/nemovideo/) while the registry metadata earlier reported no required config paths — this mismatch is inconsistent and should be clarified by the author.

Instruction Scope

The runtime instructions instruct the agent to call external APIs, upload files, store session_id and tokens, and to derive attribution headers by reading this file's YAML frontmatter and detecting install paths (e.g., ~/.clawhub, ~/.cursor/skills). Detecting install paths and reading frontmatter require accessing local filesystem state and could leak local environment details in outbound requests (X-Skill-Platform header). The skill also instructs generating an anonymous token via a remote endpoint when NEMO_TOKEN is absent — a network call that creates credentials automatically. These filesystem reads and automated token generation are outside pure ‘video generation’ logic and raise privacy considerations.

Install Mechanism

Instruction-only skill with no install spec and no code files present — nothing is downloaded or written by an installer. This is the lowest install risk.

Credentials

Only one env var (NEMO_TOKEN) is declared as required and is directly relevant to calling the remote video API. However, the SKILL.md both treats NEMO_TOKEN as required and supplies an anonymous-token acquisition flow if it's missing — that dual approach is inconsistent (declared required but automatically obtained), and the anonymous-token flow creates credentials server-side that the agent will store and use. That behavior should be documented and consented to explicitly.

Persistence & Privilege

The skill does not request always:true and does not ask to modify other skills. It instructs saving a session_id and token for the session (normal for an API client). No elevated platform privileges are requested.

What to consider before installing

Before installing, consider that: (1) the skill will call mega-api-prod.nemovideo.ai and may upload files and metadata — verify you trust that service and its privacy terms; (2) it asks for or will create a NEMO_TOKEN (you can avoid using a personal long-lived token by using an ephemeral anonymous token, but the skill will request that token from the remote API and store it for the session); (3) the runtime steps include detecting install paths and reading this skill's frontmatter to populate attribution headers — that exposes local path/installation information to the remote service; (4) registry metadata and the SKILL.md disagree about required config paths, which is a sign the package may be sloppy or incompletely specified. If you plan to use it, prefer: using ephemeral/limited tokens, testing in a sandboxed environment, reviewing the network endpoints manually (mega-api-prod.nemovideo.ai), and asking the skill author to clarify the configPath/metadata inconsistencies and the exact storage/retention behavior for generated tokens and session IDs.

Getting Started

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

Try saying:

• "convert my text or prompts"
• "export 1080p MP4"
• "turn this blog post intro into"

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.

AI to Video — Convert Text Into Video

Send me your text or prompts and describe the result you want. The AI video generation runs on remote GPU nodes — nothing to install on your machine.

A quick example: upload a 200-word product description, type "turn this blog post intro into a 30-second explainer video", and you'll get a 1080p MP4 back in roughly 1-2 minutes. All rendering happens server-side.

Worth noting: shorter, focused prompts produce more accurate video results than long vague ones.

Matching Input to Actions

User prompts referencing ai to video, 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: ai-to-video
• X-Skill-Version: from frontmatter version
• X-Skill-Platform: 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.

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)

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

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.

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

Tips and Tricks

The backend processes faster when you're specific. Instead of "make it look better", try "turn this blog post intro into a 30-second explainer video" — concrete instructions get better results.

Max file size is 50MB. Stick to TXT, DOCX, PDF, URL for the smoothest experience.

Export as MP4 for widest compatibility.

Common Workflows

Quick edit: Upload → "turn this blog post intro into a 30-second explainer video" → Download MP4. Takes 1-2 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.