Text To Video Long

Get long-form videos ready to post, without touching a single slider. Upload your text script (TXT, DOCX, PDF, MD, up to 500MB), say something like "turn thi...

Security Scan

The skill's stated purpose (convert long text to video) matches most of its instructions, but there are a few inconsistencies and hidden behaviors (token generation, filesystem attribution checks, and mismatched metadata) that you should understand before installing.

Purpose & Capability

Name/description (text→long-form video) aligns with endpoints and actions in SKILL.md: upload script, create session, submit render jobs, poll export status. Requesting a service token (NEMO_TOKEN) is appropriate for a cloud-rendering integration.

Instruction Scope

Instructions tell the agent to call external API endpoints, upload user files, stream SSE responses, and include attribution headers derived from local install paths/YAML frontmatter. Reading the skill file's frontmatter and probing common install paths (~/.clawhub/, ~/.cursor/skills/) is outside pure video-processing logic and increases local-file access scope; this is plausible for attribution but should be explicit. The SKILL.md also instructs automatic anonymous-token creation if NEMO_TOKEN is not present, which contradicts the manifest's 'required env var' implication.

Install Mechanism

This is an instruction-only skill with no install spec and no code files — low install-risk. All runtime actions are network calls; nothing is written to disk by an installer.

Credentials

Only one credential (NEMO_TOKEN) is declared, which is reasonable. However, the SKILL.md will autonomously POST to an external auth endpoint to obtain an anonymous NEMO_TOKEN if none is set — meaning the 'required' env var is effectively optional. The SKILL.md also references a config path (~/.config/nemovideo/) in its frontmatter, but the registry metadata reported earlier did not list required config paths; this mismatch should be clarified.

Persistence & Privilege

The skill is not always-enabled and is user-invocable. It asks to store session_id and use tokens for subsequent requests, which is expected for session-based cloud APIs. It does not request system-wide privileges or to modify other skills' configs.

What to consider before installing

Things to consider before installing: - The skill will call external endpoints at mega-api-prod.nemovideo.ai and needs a bearer token (NEMO_TOKEN). If you don't provide one, it will request an anonymous token for you — decide whether you trust that domain to handle your uploads and metadata. - The SKILL.md asks the agent to read the skill file's YAML frontmatter and probe common install paths to set attribution headers; ask the developer to confirm exactly what local paths/files will be read and why. If you prefer, run the skill in an isolated/sandboxed environment. - There is a minor metadata inconsistency: the SKILL.md mentions a config path (~/.config/nemovideo/) while the registry metadata did not list required config paths. Request clarification from the publisher about whether the skill will access that directory. - If you plan to provide a persistent NEMO_TOKEN tied to an account, be aware the skill will include it in every request; confirm how tokens and session_ids are stored and for how long. - If you want greater assurance, ask the maintainer for a privacy/security statement (what files/uploads are retained, where are files stored, data retention, who can access rendered outputs) and for a signed domain or official homepage. Without those, treat the skill as functional but exercise caution with sensitive content. Additional data that would increase confidence: explicit confirmation of config-path usage, a homepage/source repo, and clarity on where tokens/session IDs are stored and how long the vendor retains uploaded media.

Getting Started

Got text script to work with? Send it over and tell me what you need — I'll take care of the long video creation.

Try saying:

• "generate a 1500-word blog post or article script into a 1080p MP4"
• "turn this 10-minute script into a full narrated video with visuals"
• "generating long-form videos from written scripts or articles for YouTubers, educators, content marketers"

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. 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.

Text to Video Long — Generate Long-Form Videos from Text

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

Here's a typical use: you send a a 1500-word blog post or article script, ask for turn this 10-minute script into a full narrated video with visuals, and about 3-6 minutes later you've got a MP4 file ready to download. The whole thing runs at 1080p by default.

One thing worth knowing — breaking your script into clear sections or chapters helps the AI structure scenes more accurately.

Matching Input to Actions

User prompts referencing text to video long, 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.

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

• X-Skill-Source: text-to-video-long
• 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.

Error Handling

Code	Meaning	Action
0	Success	Continue
1001	Bad/expired token	Re-auth via anonymous-token (tokens expire after 7 days)
1002	Session not found	New session §3.0
2001	No credits	Anonymous: show registration URL with ?bind=<id> (get <id> from create-session or state response when needed). Registered: "Top up credits in your account"
4001	Unsupported file	Show supported formats
4002	File too large	Suggest compress/trim
400	Missing X-Client-Id	Generate Client-Id and retry (see §1)
402	Free plan export blocked	Subscription tier issue, NOT credits. "Register or upgrade your plan to unlock export."
429	Rate limit (1 token/client/7 days)	Retry in 30s 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 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)

Common Workflows

Quick edit: Upload → "turn this 10-minute script into a full narrated video with visuals" → Download MP4. Takes 3-6 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 "turn this 10-minute script into a full narrated video with visuals" — concrete instructions get better results.

Max file size is 500MB. Stick to TXT, DOCX, PDF, MD for the smoothest experience.

Export as MP4 for widest compatibility across YouTube, Vimeo, and social platforms.