Text To Video Json

Skip the learning curve of professional editing software. Describe what you want — convert this text into a 30-second video with visuals and voiceover — and...

Security Scan

The skill's requests and runtime instructions mostly match a text→video service, but there are inconsistencies and behaviors (automatic token generation/storage and arbitrary-file upload instructions) that warrant caution before installing.

Purpose & Capability

Name/description map to a cloud text→video service and the single required credential (NEMO_TOKEN) is appropriate for that purpose. However, the SKILL.md frontmatter declares a config path (~/.config/nemovideo/) while registry metadata lists no required config paths — an internal inconsistency. The skill also elects to auto-provision an anonymous token if NEMO_TOKEN is absent, which is explainable for usability but differs from a model that requires only user-supplied credentials.

Instruction Scope

Runtime instructions direct the agent to: contact an external API to create an anonymous token, store a session_id for subsequent requests, and upload files (multipart form with file paths or URL-based uploads). Uploading user-specified files is expected, but the instructions allow sending file paths (e.g., '-F "files=@/path"'), which — if misused — could exfiltrate arbitrary local files. The guidance to 'Don't display raw API responses or token values' indicates secrets are handled, but where/how session/token are persisted is unspecified. Overall, the instruction set grants the agent discretion to create tokens, persist them, and read local files — all normal for this skill but high-impact if abused.

Install Mechanism

No install steps or code are included (instruction-only), so nothing is written to disk by an installer and there is no package download risk.

Credentials

Only NEMO_TOKEN is declared as required and is relevant to the stated service. The skill's ability to auto-request an anonymous token means it can operate without a pre-provisioned secret. The metadata's mention of a config path suggests the skill may persist tokens or session data on disk (proportional for convenience but a privacy consideration). There are no unrelated credentials requested.

Persistence & Privilege

always:false and autonomous invocation are normal. The SKILL.md instructs storing session_id (and possibly token) for subsequent calls and the frontmatter references ~/.config/nemovideo/, implying it may persist state to disk. That persistence is plausible for a long-running cloud render session, but the registry metadata vs SKILL.md mismatch is ambiguous and should be clarified.

What to consider before installing

This skill appears to implement a cloud text→video workflow and only asks for a single service token (NEMO_TOKEN), which is reasonable — but take these precautions before installing: - Verify the backend domain (mega-api-prod.nemovideo.ai) and the service's reputation before sending any sensitive content. Uploaded files are sent to that external service. - Understand token handling: the skill will accept a user-provided NEMO_TOKEN or create an anonymous token by calling the API itself. Either token/session may be persisted (SKILL.md frontmatter references ~/.config/nemovideo/). Ask where tokens/session_ids are stored and how to revoke/delete them. - Avoid uploading sensitive or private files unless you trust the service and its privacy policy. The instructions explicitly allow multipart uploads from local paths; ensure the agent only uploads files you intentionally provide. - If you must test, prefer ephemeral or least-privilege tokens and delete any stored session/token after use. - Clarify the metadata inconsistency: registry metadata lists no config paths while the SKILL.md frontmatter references a config directory. Ask the publisher to confirm exactly what (if anything) will be written to disk. If you cannot confirm these points or don't trust the external service, do not install or use the skill with sensitive data.

Getting Started

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

Try saying:

• "convert my text prompts"
• "export 1080p MP4"
• "convert this text 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. 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 JSON — Convert Text Scripts to Video

This tool takes your text prompts and runs AI video creation through a cloud rendering pipeline. You upload, describe what you want, and download the result.

Say you have a 150-word product description paragraph and want to convert this text into a 30-second video with visuals and voiceover — the backend processes it in about 1-2 minutes and hands you a 1080p MP4.

Tip: well-structured JSON with clear scene keys produces more accurate video segmentation.

Matching Input to Actions

User prompts referencing text to video json, 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.

Headers are derived from this file's YAML frontmatter. X-Skill-Source is text-to-video-json, X-Skill-Version comes from the version field, and X-Skill-Platform is detected from the install path (~/.clawhub/ = clawhub, ~/.cursor/skills/ = cursor, otherwise unknown).

All requests must include: Authorization: Bearer <NEMO_TOKEN>, X-Skill-Source, X-Skill-Version, X-Skill-Platform. Missing attribution headers will cause export to fail with 402.

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.

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)

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

Tips and Tricks

The backend processes faster when you're specific. Instead of "make it look better", try "convert this text into a 30-second video with visuals and voiceover" — concrete instructions get better results.

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

Export as MP4 for widest compatibility across platforms and devices.

Common Workflows

Quick edit: Upload → "convert this text into a 30-second video with visuals and voiceover" → 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.