Ai Voice Over Capcut

add video clips into narrated MP4 videos with this skill. Works with MP4, MOV, AVI, WebM files up to 500MB. TikTok creators use it for adding AI-generated vo...

Security Scan

The skill's declared requirements and runtime instructions are consistent with an AI video-voiceover service that calls a remote API, but it sends user media to an external endpoint and has a small metadata/instruction mismatch you should be aware of.

Purpose & Capability

Name and description match the actual runtime instructions: the skill calls a remote 'nemovideo' API to upload videos, create a session, run SSE-style generation, and export MP4s. The single required environment variable (NEMO_TOKEN) is appropriate for a remote service API credential.

Instruction Scope

Instructions are narrowly focused on connecting to the external API, creating sessions, streaming SSE, uploading files (multipart or via URL), checking credits/state, and exporting. They instruct uploading user video files to the remote service and to include attribution headers. One minor scope ambiguity: header 'X-Skill-Platform' is described as 'auto-detect: from install path', which implies the agent may inspect its install path or environment to set the header; the SKILL.md does not explicitly describe how or where to read that path. Otherwise, instructions do not request unrelated environment variables or system credentials.

Install Mechanism

This is instruction-only with no install spec and no code files. That minimizes local install risk.

Credentials

The skill only requires NEMO_TOKEN (declared as primaryEnv) which is proportionate. The frontmatter metadata also lists a config path (~/.config/nemovideo/), but SKILL.md contains no explicit steps to read that path — a small mismatch worth noting. No unrelated secrets or system credentials are requested.

Persistence & Privilege

always is false and the skill does not request elevated persistence or system-wide changes. It instructs saving a session_id in runtime state but gives no instructions to modify other skills or system-wide configuration.

Assessment

This skill works by uploading your video files and metadata to an external service (https://mega-api-prod.nemovideo.ai) and returning generated videos. Before installing or using it: 1) Be comfortable with sending any media you upload to that remote domain (avoid sensitive or private footage). 2) Verify the service/provider if you need a trust or retention guarantee (privacy, retention, deletion policy). 3) Consider setting a dedicated NEMO_TOKEN with limited scope if available; the skill can also generate an anonymous token but that still posts your files to the remote service. 4) Note the small metadata mismatch: the manifest lists a config path (~/.config/nemovideo/) not referenced in the instructions, and the skill asks you to auto-detect install path for X-Skill-Platform — this may require the agent to inspect its environment/install path. 5) If you need higher assurance, test with non-sensitive sample videos and review network activity or request provider documentation about data handling before sending real content.

Getting Started

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

Try saying:

• "add a 60-second silent screen recording into a 1080p MP4"
• "add a natural AI voiceover narrating my tutorial video"
• "adding AI-generated voiceovers to videos without recording audio for TikTok creators"

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.

AI Voice Over CapCut — Add AI Voiceover to Videos

Drop your video clips 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 60-second silent screen recording, ask for add a natural AI voiceover narrating my tutorial video, 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 clips under 2 minutes produce the most natural-sounding voiceover sync.

Matching Input to Actions

User prompts referencing ai voice over capcut, 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 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.

Three attribution headers are required on every request and must match this file's frontmatter:

Header	Value
X-Skill-Source	ai-voice-over-capcut
X-Skill-Version	frontmatter version
X-Skill-Platform	auto-detect: clawhub / cursor / unknown from install path

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

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.

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 → "add a natural AI voiceover narrating my tutorial video" → 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 AI voiceover narrating my tutorial video" — 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 TikTok, YouTube, and Instagram.