Text To Video I

Get AI-generated videos ready to post, without touching a single slider. Upload your text prompts (TXT, DOCX, PDF, SRT, up to 200MB), say something like "tur...

Security Scan

The skill's requirements and runtime instructions largely match a cloud text→video service (it needs a NEMO_TOKEN and talks to nemovideo.ai), but there are small inconsistencies and privacy considerations you should review before installing.

Purpose & Capability

Name/description (text→video) match the API endpoints and flows described in SKILL.md and the single required env var (NEMO_TOKEN). Minor inconsistency: the registry metadata listed no config paths but the SKILL.md frontmatter declares a config path (~/.config/nemovideo/). That mismatch should be clarified (skill may look for local config).

Instruction Scope

Instructions stay within the stated purpose: create sessions, send messages via SSE, upload files, check credits, and request renders from mega-api-prod.nemovideo.ai. Important operational behavior: the skill will upload user-provided files to a third-party cloud service and will POST files via multipart or by URL. It also describes deriving headers from the skill frontmatter and detecting the agent install path to set X-Skill-Platform (this requires inspecting the agent runtime/install path). No instructions request unrelated system files, but the skill may probe an install/config path.

Install Mechanism

No install spec and no code files — instruction-only. That reduces installation risk because nothing is downloaded or written by the skill itself.

Credentials

Only NEMO_TOKEN is declared as required and is appropriate for a remote video service. Caveat: SKILL.md frontmatter also lists a config path (~/.config/nemovideo/), which is not reflected in the top-level metadata; if the skill reads that path it could access local config. The NEMO_TOKEN (if provided) will be used for all API calls — treating it as a secret with account-level access and credits is appropriate.

Persistence & Privilege

always:false and no install actions — the skill does not request forced permanent inclusion or system-level modifications. It uses remote sessions on the provider side (jobs may remain running on the provider if you close the client), which is normal for rendering services.

Assessment

This skill is consistent with a cloud text→video service, but consider these points before installing: (1) The skill will upload any files you give it to https://mega-api-prod.nemovideo.ai — do not send proprietary or PII-containing files unless you accept that third-party processing and storage. (2) If you provide a NEMO_TOKEN, it will be used as an account credential for all requests and can represent account/credits access—only supply a token you trust. (3) SKILL.md mentions a local config path (~/.config/nemovideo/) and detecting the agent install path to set a header; confirm whether the skill will read that path and whether any sensitive local config could be exposed. (4) The skill creates remote render jobs that may persist on the provider; check the provider's terms/retention/privacy if that matters. If you need higher assurance, ask the publisher for explicit documentation about what local paths (if any) the skill reads and how long uploaded artifacts and anonymous tokens are retained.

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"
• "turn this text into a 30-second"

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 — Convert Text Into Generated Videos

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

Here's a typical use: you send a a 150-word product description, ask for turn this text into a 30-second explainer video with voiceover and visuals, and about 1-2 minutes later you've got a MP4 file ready to download. The whole thing runs at 1080p by default.

One thing worth knowing — shorter, clearer sentences produce more accurate scene generation.

Matching Input to Actions

User prompts referencing text to video i, 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.

Include Authorization: Bearer <NEMO_TOKEN> and all attribution headers on every request — omitting them triggers a 402 on export.

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

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.

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

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

SSE Event Handling

Event	Action
Text response	Apply GUI translation (§4), present to user
Tool call/result	Process internally, don't forward
heartbeat / empty data:	Keep waiting. Every 2 min: "⏳ Still working..."
Stream closes	Process final response

~30% of editing operations return no text in the SSE stream. When this happens: poll session state to verify the edit was applied, then summarize changes to the user.

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)

Common Workflows

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

Tips and Tricks

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

Max file size is 200MB. Stick to TXT, DOCX, PDF, SRT for the smoothest experience.

Export as MP4 for widest compatibility.