# Youtube Voiceover

> Prepare or generate YouTube voiceover assets. Use when Codex needs narration cleanup, voice direction, pronunciation notes, segment timing, TTS prompts, or audio generation planning from a YouTube script.

- Skill: `lynn2023hahaha/youtube-voiceover` (Agent Skill, multi-file: 2 files)
- Install (CLI): `npx skillmds@latest add lynn2023hahaha/youtube-voiceover`
- Raw SKILL.md: https://api.skillmd.com/api/skills/lynn2023hahaha/youtube-voiceover/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Productivity
- Author: Lynn2023hahaha (https://skillmd.com/u/lynn2023hahaha)
- Updated: 2026-09-22
- Page: https://skillmd.com/skills/lynn2023hahaha/youtube-voiceover

---


# YouTube Voiceover

## Inputs

Use `script.md`, target language, preferred voice, speed, emotion, and any tool-specific TTS requirements.

## Process

1. Extract narration only from the script.
2. Clean text for speech: remove table syntax, visual notes, and unsupported symbols.
3. Add pronunciation notes for names, acronyms, numbers, and uncommon terms.
4. Split narration into timed segments.
5. Generate audio if a TTS tool is available; otherwise create a TTS-ready plan.
6. Record file names and durations.

## Output Format

Create `voiceover-plan.md`:

```markdown
# Voiceover Plan

## Voice Direction

## Clean Narration

## Pronunciation Notes

## Segments
| Segment | Text | Target Duration | Audio File |
|---|---|---:|---|

## Audio Settings

## Checks
```

## Quality Check

- The narration must be speakable without markup.
- Segment durations should support the target video length.
- Voice direction should match the audience and topic.
- Any generated audio should be checked for clipping, truncation, and mispronunciation.