# ipollowork-video-voiceover

ipollowork-video-voiceover adds or revises scene-bound narration and speech-linked captions in the iPolloWork video you are editing, using the voice settings already enabled.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf (Devin Desktop), Claude.ai · ★ 7523 repo stars
- Author: Devin-AXIS
- License: LicenseRef-Proprietary · policy=link-only · description only; the file stays with the author
- Source: https://github.com/Devin-AXIS/iPolloWork/tree/HEAD/.agents/skills/ipollowork-video-voiceover/SKILL.md
- Updated: 2026-10-29
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/ipollowork-video-voiceover

## What it does

Adds narration or captions to the scenes of the iPolloWork video you have open, and revises them when they are already there. Synthesis runs through the built-in batch contract: the audio and captions that come back get mounted, and the measured timing shift is applied once.

It starts from the shared session boundaries and the voiceover reference, then reads the current `voiceover.json`, storyboard and scene anchors. Authorization and any saved disabled state stay as they are, and pinned or per-frame voices keep their assignment. Earlier speech holds until a take succeeds. Music and SFX are left in place. Captions-only jobs reuse the saved alignment, so nothing is synthesized twice.

The skill does not choose a provider or a voice for you: it works from whatever the voice settings already have enabled. Timings are not invented, and the TTS service is not swapped out. What got mounted is checked with the existing media tools, and the actual files are what you get back. Any required speech still unfinished is reported.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add Devin-AXIS/iPolloWork --skill ipollowork-video-voiceover -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/ipollowork-video-voiceover/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/ipollowork-video-voiceover/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add Devin-AXIS/iPolloWork --skill ipollowork-video-voiceover -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/ipollowork-video-voiceover/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add Devin-AXIS/iPolloWork --skill ipollowork-video-voiceover -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/ipollowork-video-voiceover/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install Devin-AXIS/iPolloWork .agents/skills/ipollowork-video-voiceover
```

2. **Manually: put the files in place**
- File: `.github/skills/ipollowork-video-voiceover/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add Devin-AXIS/iPolloWork --skill ipollowork-video-voiceover -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/Devin-AXIS/iPolloWork --path .agents/skills/ipollowork-video-voiceover
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/ipollowork-video-voiceover/SKILL.md` — The legacy .windsurf/skills/ path still works

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/Devin-AXIS/iPolloWork/tree/HEAD/.agents/skills/ipollowork-video-voiceover/SKILL.md

## When to use it
- add narration to scenes that already have picture
- redo one scene's voice without touching the rest
- attach captions to audio synthesized earlier
- correct timing once the audio is measured
- keep the music bed while swapping speech

## Example prompts
- Add narration to scene 2 and wire the captions to the audio that's already there.
- Redo the voice lines in `scene-04`, leave the music alone.
- Refresh captions from the saved alignment, skip synthesis.

## Similar
- [CantoneseTTS.com: Hong Kong Cantonese Voiceover & SRT MCP](https://affpapa.org/en/nevibecode/mcp/cantonesettscom-hong-kong-cantonese-voiceover-srt-mcp.md) — MCP server
- [ai-voiceover](https://affpapa.org/en/nevibecode/skills/ai-voiceover.md) — skill · 1300 installs
- [StudioMeyer Video](https://affpapa.org/en/nevibecode/mcp/studiomeyer-video.md) — MCP server · ★ 5 repo stars
- [media-use](https://affpapa.org/en/nevibecode/skills/media-use.md) — skill · 1500000 installs
- [MakeAIVideo](https://affpapa.org/en/nevibecode/mcp/makeaivideo.md) — MCP server
- [explainer-video-guide](https://affpapa.org/en/nevibecode/skills/explainer-video-guide.md) — skill · 249 installs

From the same set: [devin-axis/ipollowork](https://affpapa.org/en/nevibecode/by/devin-axis/ipollowork.md) — 42 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
