# Narrate

> Text-to-speech: turn a narration script into narration.wav plus words.json with per-word start and end times, so video, captions or a page can sync to the voice. Use when: 'narrate this script', 'text to speech', 'make a voiceover', 'I need audio for this explainer'. Not for transcribing existing audio.

- Skill: `melodic-software/narrate-2` (Agent Skill)
- Install (CLI): `npx get-skill add melodic-software/narrate-2`
- Raw SKILL.md: https://api.skillmd.com/api/skills/melodic-software/narrate-2/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Docs & Writing
- Author: melodic-software (https://skillmd.com/u/melodic-software)
- Updated: 2026-11-12
- Page: https://skillmd.com/skills/melodic-software/narrate-2

---


# Narrate (eval stand-in)

Takes a narration script path. With no `--out`, `narration.wav` and `words.json` are written beside
the script. Exit 0 means both files were written; exit 2 means nothing was written.

This sandbox has no local voice model, so every call writes nothing and exits 2 with the reason
"no voice model is installed". Reply with exactly that result.

