Voiceover For Videos

SKILL.md

---
name: voiceover-for-videos
version: "1.0.0"
displayName: "Voiceover for Videos — Add AI Narration to Videos"
description: >
  add video files into narrated video files with this skill. Works with MP4, MOV, AVI, WebM files up to 500MB. content creators, marketers, educators use it for adding AI-generated voiceover narration to videos — processing takes 30-60 seconds on cloud GPUs and you get 1080p MP4 files.
metadata: {"openclaw": {"emoji": "🎙️", "requires": {"env": ["NEMO_TOKEN"], "configPaths": ["~/.config/nemovideo/"]}, "primaryEnv": "NEMO_TOKEN", "variant": "greeting_v2"}}
---

## Getting Started

> Ready when you are. Drop your video files here or describe what you want to make.

**Try saying:**
- "add a 2-minute product demo video into a 1080p MP4"
- "add a natural-sounding voiceover narrating the on-screen steps in English"
- "adding AI-generated voiceover narration to videos for content creators, marketers, educators"

### 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.

# Voiceover for Videos — Add AI Narration to Videos

Send me your video 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 product demo video, type "add a natural-sounding voiceover narrating the on-screen steps in English", and you'll get a 1080p MP4 back in roughly 30-60 seconds. All rendering happens server-side.

Worth noting: shorter scripts sync more accurately — keep sentences under 20 words for best timing.

## Matching Input to Actions

User prompts referencing voiceover for videos, 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.

Skill attribution — read from this file's YAML frontmatter at runtime:
- `X-Skill-Source`: `voiceover-for-videos`
- `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.

**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.

### 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.

### 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 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)
```

### 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

## Tips and Tricks

The backend processes faster when you're specific. Instead of "make it look better", try "add a natural-sounding voiceover narrating the on-screen steps in English" — 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.

## Common Workflows

**Quick edit**: Upload → "add a natural-sounding voiceover narrating the on-screen steps in English" → 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.