> ## Documentation Index
> Fetch the complete documentation index at: https://hyperframes-codex-docs-human-first-refactor.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Add voice, music, and sound

> Use narration, music, and sound effects without losing clarity or sync.

Audio gives the timeline its pace. Decide what each layer is responsible for before adding more sound.

| Layer         | Main job                                       |
| ------------- | ---------------------------------------------- |
| Voiceover     | Carry the explanation or story                 |
| Source audio  | Preserve speech or sound from existing footage |
| Music         | Set pace, tone, and structure                  |
| Sound effects | Reinforce a specific action or transition      |

## Create voiceover

Give the agent the approved script and voice direction:

```text theme={null}
Generate the approved SCRIPT.md as a warm, direct voiceover.
Natural pace, no announcer energy. Keep the product name pronunciation exact.
```

The project may keep the spoken text, audio file, and word-level transcript separately so the voice can be regenerated without losing timing work.

## Mix for understanding

* Voice should remain clear over music.
* Use sound effects for meaningful events, not every movement.
* Duck music under important speech.
* Avoid cutting words or breaths accidentally at scene boundaries.
* Listen on ordinary headphones and laptop speakers.

## Keep timing connected

When narration drives the project, use its real transcript timing rather than estimated scene lengths.

For speech captions, continue to [Transcribe and create captions](/guides/transcribe-and-caption).