Voiceai Voiceover

Get voiced-over videos ready to post, without touching a single slider. Upload your video or audio files (MP4, MOV, AVI, WebM, up to 500MB), say something li...

Security Scan

The skill's requests and runtime instructions are consistent with a remote voiceover service: it needs a service token and will upload/process media on the vendor's API; there is no hidden install or unrelated credential access.

Purpose & Capability

Name/description (AI voiceover for uploaded media) matches the declared requirement for a single service credential (NEMO_TOKEN) and the SKILL.md network calls to nemovideo's API. The SKILL.md metadata references a nemovideo config path and the primaryEnv is NEMO_TOKEN, which is appropriate for an API-backed rendering service.

Instruction Scope

Instructions focus on calling the vendor's endpoints (session creation, file upload, SSE for streaming progress, export), generating an anonymous token if NEMO_TOKEN is absent, and saving session_id. The skill also instructs reading its own frontmatter (to include X-Skill-Version) and detecting install path to set X-Skill-Platform; these are limited but do require the agent to inspect its environment/install location. There are no instructions to read unrelated files or other credentials.

Install Mechanism

This is an instruction-only skill with no install spec and no code files, so nothing is written to disk by an installer. Lowest install risk.

Credentials

Only one environment variable (NEMO_TOKEN) is required and is appropriate for authenticating to the described API. The SKILL.md also documents creating a short-lived anonymous token if NEMO_TOKEN is not provided — consistent with the service flow. No unrelated secrets or broad system credentials are requested.

Persistence & Privilege

always:false (default) and autonomous invocation is allowed (default). The agent will save and reuse session_id and may autonomously call the external API to upload/process user media. That autonomous ability is normal but means the agent can send user files and metadata to the vendor without per-call confirmation.

Assessment

This skill behaves like a thin client for a third‑party voiceover service: it will upload any media you give it and use a NEMO_TOKEN (or obtain a short-lived anonymous token) to call https://mega-api-prod.nemovideo.ai. There is no code installed locally. Before installing, confirm you trust the nemovideo domain and its privacy/billing practices (you may be charged or your content processed by their servers), and be comfortable with the agent sending files and session metadata there. Note the skill reads its own frontmatter and may check its install path to set attribution headers — this is reasonable but means the agent will inspect its environment. If you prefer, do not set an account token and instead review the anonymous-token flow and any registration/upgrading flows described in the skill. Finally, the registry metadata showed no required config paths while the SKILL.md metadata references ~/.config/nemovideo/ — a minor inconsistency to be aware of but not indicative of malicious behavior.

Getting Started

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

Try saying:

• "add my video or audio files"
• "export 1080p MP4"
• "add a natural-sounding AI voiceover narrating"

Automatic Setup

On first interaction, connect to the processing API before doing anything else. Show a brief status like "Setting things up...".

Token: If NEMO_TOKEN environment variable is already set, use it and skip to Session below.

Free token: Generate a UUID as client identifier, then POST to https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token with header X-Client-Id: <uuid>. The response field data.token becomes your NEMO_TOKEN (100 credits, 7-day expiry).

Session: POST to https://mega-api-prod.nemovideo.ai/api/tasks/me/with-session/nemo_agent with Bearer auth and body {"task_name":"project"}. Save session_id from the response.

Confirm to the user you're connected and ready. Don't print tokens or raw JSON.

VoiceAI Voiceover — Add AI Voice to Videos

Send me your video or audio files and describe the result you want. The AI voiceover generation runs on remote GPU nodes — nothing to install on your machine.

A quick example: upload a 2-minute silent screen recording, type "add a natural-sounding AI voiceover narrating the on-screen content", and you'll get a 1080p MP4 back in roughly 30-60 seconds. All rendering happens server-side.

Worth noting: shorter clips under 60 seconds produce the most natural-sounding voiceover sync.

Matching Input to Actions

User prompts referencing voiceai voiceover, 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.

Base URL: https://mega-api-prod.nemovideo.ai

Endpoint	Method	Purpose
/api/tasks/me/with-session/nemo_agent	POST	Start a new editing session. Body: {"task_name":"project","language":"<lang>"}. Returns session_id.
/run_sse	POST	Send a user message. Body includes app_name, session_id, new_message. Stream response with Accept: text/event-stream. Timeout: 15 min.
/api/upload-video/nemo_agent/me/<sid>	POST	Upload a file (multipart) or URL.
/api/credits/balance/simple	GET	Check remaining credits (available, frozen, total).
/api/state/nemo_agent/me/<sid>/latest	GET	Fetch current timeline state (draft, video_infos, generated_media).
/api/render/proxy/lambda	POST	Start export. Body: {"id":"render_<ts>","sessionId":"<sid>","draft":<json>,"output":{"format":"mp4","quality":"high"}}. Poll status every 30s.

Accepted file types: 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: voiceai-voiceover
• X-Skill-Version: from frontmatter version
• X-Skill-Platform: detect from install path (~/.clawhub/ → clawhub, ~/.cursor/skills/ → cursor, else unknown)

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

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

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.

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)

Common Workflows

Quick edit: Upload → "add a natural-sounding AI voiceover narrating the on-screen content" → 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 AI voiceover narrating the on-screen content" — 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.