Ai Voiceover Tool

add video or script into voiced-over videos with this skill. Works with MP4, MOV, AVI, WebM files up to 500MB. content creators and marketers use it for addi...

Security Scan

The skill generally matches a cloud voiceover tool but contains inconsistencies about required config/credentials and instructs the agent to generate/use tokens and probe install paths — this behavior is plausible but unclear and worth caution.

Purpose & Capability

Name/description (AI voiceover for uploaded videos) aligns with the network calls and upload/export flows in SKILL.md. Requesting a NEMO_TOKEN is reasonable for a cloud API. However the skill metadata/frontmatter references a config path (~/.config/nemovideo/) while the registry listing said no config paths — an internal inconsistency that isn't justified by the description.

Instruction Scope

Instructions require uploading user media and calling third-party endpoints (mega-api-prod.nemovideo.ai) which is expected. But the runtime instructions also tell the agent to: generate anonymous tokens by POSTing to the auth endpoint if no NEMO_TOKEN present, read the skill's YAML frontmatter at runtime, and detect install paths (e.g., ~/.clawhub/, ~/.cursor/skills/) to set X-Skill-Platform — reading those install paths exposes information about the agent environment and other installed tools. The instructions do not explicitly state whether tokens or session IDs are persisted to disk (the metadata suggests a config path), creating ambiguity about persistence and data exposure.

Install Mechanism

Instruction-only skill with no install spec or code files — nothing is downloaded or written by an installer. This is the lowest install risk.

Credentials

Only NEMO_TOKEN is declared as required which fits the service. But the SKILL.md instructs obtaining an anonymous token automatically when NEMO_TOKEN is absent, meaning the token is optional in practice — the declared requirement may be misleading. The metadata also lists a config path (~/.config/nemovideo/) that the registry said was not required, introducing an unexplained request for access to a user config location. Reading install paths to detect platform is additional environment/file access that is not strictly necessary for voiceover functionality.

Persistence & Privilege

always:false and no install means the skill is not force-included and has no explicit elevated privileges. However ambiguity remains about whether the skill will store the anonymous token or session state under ~/.config/nemovideo/ (the frontmatter references it) — if it writes credentials or job metadata to the user home, that increases persistence. The SKILL.md does not clearly state whether any files are written.

What to consider before installing

This skill behaves like a standard cloud voiceover service but has a few red flags: it will upload your media to mega-api-prod.nemovideo.ai and can automatically create an anonymous bearer token if NEMO_TOKEN isn't provided. Before installing or invoking it, consider: (1) Do you trust the unknown source/owner? (2) Avoid sending sensitive videos or transcripts unless you confirm the service's privacy/retention policy. (3) Ask whether the skill will write tokens or job data under ~/.config/nemovideo/ or elsewhere — the metadata is inconsistent. (4) If you prefer tighter control, provide your own NEMO_TOKEN (from a trusted provider) and avoid allowing the agent to auto-generate/store credentials. (5) Be cautious because the skill probes install paths (it may read your home dir layout), which can leak info about your environment. If you need higher assurance, request code or a vendor homepage, or run the skill in an isolated environment.

Getting Started

Share your video or script and I'll get started on AI voiceover generation. Or just tell me what you're thinking.

Try saying:

• "add my video or script"
• "export 1080p MP4"
• "add a natural-sounding English voiceover to"

Quick Start Setup

This skill connects to a cloud processing backend. On first use, set up the connection automatically and let the user know ("Connecting...").

Token check: Look for NEMO_TOKEN in the environment. If found, skip to session creation. Otherwise:

• Generate a UUID as client identifier
• POST https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token with X-Client-Id header
• Extract data.token from the response — this is your NEMO_TOKEN (100 free credits, 7-day expiry)

Session: POST https://mega-api-prod.nemovideo.ai/api/tasks/me/with-session/nemo_agent with Bearer auth and body {"task_name":"project"}. Keep the returned session_id for all operations.

Let the user know with a brief "Ready!" when setup is complete. Don't expose tokens or raw API output.

AI Voiceover Tool — Add Voice Narration to Videos

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

Here's a typical use: you send a a 2-minute product demo video, ask for add a natural-sounding English voiceover to my silent screen recording, and about 30-60 seconds later you've got a MP4 file ready to download. The whole thing runs at 1080p by default.

One thing worth knowing — shorter scripts generate more accurate voiceovers — break long narrations into segments.

Matching Input to Actions

User prompts referencing ai voiceover tool, 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.

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

• X-Skill-Source: ai-voiceover-tool
• X-Skill-Version: from frontmatter version
• X-Skill-Platform: detect from install path (~/.clawhub/ → clawhub, ~/.cursor/skills/ → cursor, else 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.

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

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 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

Common Workflows

Quick edit: Upload → "add a natural-sounding English voiceover to my silent screen recording" → 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 "add a natural-sounding English voiceover to my silent screen recording" — 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.