Voiceover Ai Maker

Turn a 2-minute silent product demo video into 1080p voiced-over videos just by typing what you need. Whether it's adding AI-generated voiceovers to silent o...

Security Scan

The skill's declared purpose (cloud voiceover for videos) matches its runtime instructions, but there are mismatches in metadata and some behaviors (automatic anonymous token creation, hidden tokens, and uploading user media to an unknown backend) that warrant caution before installing or using it with sensitive content.

Purpose & Capability

The skill claims to generate AI voiceovers and all visible instructions map to that behavior (uploading media, creating sessions, rendering/export endpoints). Requesting a token named NEMO_TOKEN is coherent with a third‑party API token. However, the SKILL.md frontmatter includes a configPaths entry (~/.config/nemovideo/) while the registry metadata reported no required config paths — this inconsistency is unexplained and worth checking with the author.

Instruction Scope

Instructions explicitly direct the agent to: auto-connect to the backend on first open, generate or use NEMO_TOKEN, POST uploads of user media, and poll for exports. Automatically generating and storing an anonymous token and connecting without an explicit user confirmation expands scope beyond a simple 'on demand' action. The skill also instructs the agent to hide raw API responses and token values, which is reasonable for secrets but also reduces transparency about what is sent/received. Uploading user videos/audio to an external service creates a clear data-exfiltration/privacy surface — this is expected for the feature but should be flagged to users.

Install Mechanism

There is no install spec and no code files (instruction-only), so nothing is being downloaded or written during install. This minimizes install-time risk.

Credentials

Only NEMO_TOKEN is declared as required (primaryEnv), which is proportionate for a cloud API. However, the SKILL.md metadata also lists a config path (~/.config/nemovideo/) that the registry summary did not declare — mismatch between declared requirements. The skill also instructs the agent to create and persist an anonymous token if none is present (so a user-supplied credential is optional). Requiring a single token is reasonable, but automatically creating/storing credentials and hiding API responses increases the chance the agent will hold credentials or session state without explicit user controls.

Persistence & Privilege

always:false (default) and autonomous invocation is allowed (platform default). The skill instructs storing session_id for subsequent requests, but doesn't specify storage location or lifetime. No evidence it requests system-wide privileges or modifies other skills, so persistence/privilege is not excessive — but the combination of automatic backend connection + opaque token storage increases blast radius if the backend were malicious or compromised.

What to consider before installing

This skill appears to be a straightforward cloud-based voiceover service, but it will upload whatever video/audio you provide to an external domain (mega-api-prod.nemovideo.ai). Before installing or using it: (1) Do not upload sensitive or confidential videos. (2) Ask the author to explain the configPaths discrepancy and where session tokens are stored and for how long. (3) Prefer a workflow that prompts you before the first automatic connection or anonymous token creation. (4) If you must try it, monitor network activity and avoid giving permanent credentials; consider running it in an isolated account or environment. If you need higher assurance, request the service's privacy/security policy or source code for review.

Getting Started

Got video or audio files to work with? Send it over and tell me what you need — I'll take care of the AI voiceover generation.

Try saying:

• "generate a 2-minute silent product demo video into a 1080p MP4"
• "generate a natural-sounding voiceover in English for this product walkthrough"
• "adding AI-generated voiceovers to silent or muted videos for content creators, marketers, educators"

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.

Voiceover AI Maker — Generate AI Voiceovers for Videos

This tool takes your video or audio files and runs AI voiceover generation through a cloud rendering pipeline. You upload, describe what you want, and download the result.

Say you have a 2-minute silent product demo video and want to generate a natural-sounding voiceover in English for this product walkthrough — the backend processes it in about 30-60 seconds and hands you a 1080p MP4.

Tip: shorter clips under 60 seconds produce the most natural-sounding voiceover output.

Matching Input to Actions

User prompts referencing voiceover ai maker, 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 voiceover-ai-maker, 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 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)

Backend Response Translation

The backend assumes a GUI exists. Translate these into API actions:

Backend says	You do
"click [button]" / "点击"	Execute via API
"open [panel]" / "打开"	Query session state
"drag/drop" / "拖拽"	Send edit via SSE
"preview in timeline"	Show track summary
"Export button" / "导出"	Execute 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.

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 natural-sounding voiceover in English for this product walkthrough" → Download MP4. Takes 30-60 seconds 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 natural-sounding voiceover in English for this product walkthrough" — concrete instructions get better results.

Max file size is 500MB. Stick to MP4, MOV, AVI, WebM for the smoothest experience.

Export as MP4 for widest compatibility across platforms and devices.