Text To Video Open Source

Skip the learning curve of professional editing software. Describe what you want — generate a 15-second video clip from this scene description: a fox running...

Security Scan

The skill's requirements and runtime instructions are consistent with a text→video cloud service: it needs a NEMO_TOKEN, calls nemovideo endpoints, and uploads user-provided files — nothing obviously disproportionate or covert was found.

Purpose & Capability

Name/description promise (generate short videos from text) matches the declared requirement (NEMO_TOKEN) and the SKILL.md lists API endpoints for session creation, SSE chat, upload, and export which are all appropriate for a cloud render/video service.

Instruction Scope

Instructions direct the agent to create sessions, use SSE for generation, upload user files up to 500MB, and poll export endpoints — all expected. The SKILL.md also instructs creating an anonymous token (POST to the nemovideo anonymous-token endpoint) when NEMO_TOKEN is absent; this is a legitimate fallback but means the skill will call an external API autonomously if no token is provided. The doc also uses install-path detection to set attribution headers, which requires access to the agent's install path.

Install Mechanism

No install spec or code files are provided (instruction-only), so there is no package download or arbitrary code install risk from this skill itself.

Credentials

The single required env var (NEMO_TOKEN) is appropriate for an API-backed video service. Minor inconsistency: requires.env lists NEMO_TOKEN but the runtime instructions include an explicit fallback that fetches an anonymous token if NEMO_TOKEN is missing. Metadata also declares a config path (~/.config/nemovideo/) which may be used to store session/token data — plausible but worth noting.

Persistence & Privilege

The skill does not request always:true, does not modify other skills, and does not require elevated system privileges. It may store or read its own config (implied) but nothing in the manifest indicates system-wide changes.

Assessment

This skill appears to be what it claims: it will send your text and any uploaded files (up to 500MB) to the nemovideo API and needs a NEMO_TOKEN to authenticate. Before installing, consider: 1) any files you upload will be transmitted to an external service — do not upload sensitive/private data unless you trust the provider; 2) if you don't set NEMO_TOKEN, the skill will request an anonymous token from the nemovideo endpoint automatically (i.e., it will make outbound network calls); 3) the skill may store session/token data under ~/.config/nemovideo/ per its metadata — review or clear that directory if you later uninstall; and 4) prefer providing your own NEMO_TOKEN (and verify the nemo domain) rather than relying on anonymous tokens. If you need higher assurance, ask the skill author for a privacy/data-retention policy or test with non-sensitive content first.

Getting Started

Send me your text prompts and I'll handle the AI video generation. Or just describe what you're after.

Try saying:

• "generate a two-sentence description of a sunset over a mountain lake into a 1080p MP4"
• "generate a 15-second video clip from this scene description: a fox running through a snowy forest at dusk"
• "generating video clips from written text descriptions for developers and indie creators"

Getting Connected

Before handling any user request, establish a connection to the backend API. Show a brief status like "Connecting...".

If NEMO_TOKEN is in the environment, use it directly and create a session. Otherwise, acquire a free starter token:

• Generate a UUID as client identifier
• POST to https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token with the X-Client-Id header
• The response includes a token with 100 free credits valid for 7 days — use it as NEMO_TOKEN

Then create a session by POSTing to https://mega-api-prod.nemovideo.ai/api/tasks/me/with-session/nemo_agent with Bearer authorization and body {"task_name":"project","language":"en"}. The session_id in the response is needed for all following requests.

Tell the user you're ready. Keep the technical details out of the chat.

Text to Video Open Source — Generate Videos from Text

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

Here's a typical use: you send a a two-sentence description of a sunset over a mountain lake, ask for generate a 15-second video clip from this scene description: a fox running through a snowy forest at dusk, and about 1-3 minutes later you've got a MP4 file ready to download. The whole thing runs at 1080p by default.

One thing worth knowing — shorter and more specific prompts produce more consistent and accurate video output.

Matching Input to Actions

User prompts referencing text to video open source, 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.

Headers are derived from this file's YAML frontmatter. X-Skill-Source is text-to-video-open-source, 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).

Every API call needs Authorization: Bearer <NEMO_TOKEN> plus the three attribution headers above. If any header is missing, exports return 402.

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 "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 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

Common Workflows

Quick edit: Upload → "generate a 15-second video clip from this scene description: a fox running through a snowy forest at dusk" → Download MP4. Takes 1-3 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 "generate a 15-second video clip from this scene description: a fox running through a snowy forest at dusk" — concrete instructions get better results.

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

Export as MP4 with H.264 encoding for the widest playback compatibility.