Script Direction Guide

Direction markers tell your AI voice how to perform a line — pace, emphasis, emotion, pauses and breath. Drop them inline anywhere in your directed script. They never count toward billable characters.

Pitch

[RISE] Pitch rises on the next phrase

Lifts pitch on the next phrase — adds curiosity, openness or a question feel.

[FALL] Pitch falls on the next phrase

Drops pitch on the next phrase — adds finality, weight or resolve.

Pace

[EXTEND] Stretch the next word

Stretches the next word — adds drama or scale.

[SLOW] Slow down

Reduces pace for the wrapped phrase.

[FAST] Speed up

Increases pace — momentum, urgency, energy.

Pause

[PAUSE] Natural pause (~500 ms)

Inserts a natural ~500 ms beat between thoughts.

[PAUSE:1.5] Pause of X seconds

Custom-length pause in seconds. Use for deliberate breathing room.

[PAUSE:BEAT] Dramatic beat (~800 ms)

Stronger ~800 ms dramatic beat — use sparingly for impact.

Emphasis

[EMPHASIS] Stress the next word

Stresses the next word — pulls listener focus.

[EMPHASIS:STRONG] Maximum stress

Maximum stress with a small volume lift.

[EMPHASIS:SUBTLE] Light stress

Soft, unobtrusive lift — good for keywords mid-sentence.

Volume

[WHISPER] Quiet, intimate delivery

Quiet, intimate, slow delivery.

[SOFT] Quieter delivery

Quieter delivery without slowing down.

[LOUD] Louder delivery

Louder delivery without speeding up.

[SHOUT] Shouting delivery (v3 audio tag)

Shouting delivery (v3 audio tag)

Breath

[BREATH] Insert a natural breath

Inserts an audible inhale — humanises long passages.

[GASP] Sharp inhale (v3)

Sharp inhale (v3)

Emotion

[DRAMATIC] Heightened emotion

Pitch up + slow + louder — heightened emotion.

[WARM] Warmer, friendlier tone

Gentle slowdown + slight pitch drop — friendly and reassuring.

[AUTHORITATIVE] Firmer, commanding tone

Slower, lower, firmer — commanding tone.

[EXCITED] Energetic, upbeat delivery

Faster, higher, brighter — upbeat energy.

[LAUGH] Insert a laugh (v3)

Insert a laugh (v3)

[SIGH] Insert a sigh (v3)

Insert a sigh (v3)

[SNIFF] A sniff (v3)

A sniff (v3)

[CRY] Tearful delivery (v3)

Tearful delivery (v3)

[ANGRY] Angry delivery (v3)

Angry delivery (v3)

[SAD] Sad delivery (v3)

Sad delivery (v3)

[SARCASTIC] Sarcastic tone (v3)

Sarcastic tone (v3)

[NERVOUS] Nervous delivery (v3)

Nervous delivery (v3)

[CONFIDENT] Confident delivery (v3)

Confident delivery (v3)

Combining markers

Markers apply to the phrase that follows them, until the next marker or pause. Stack carefully — one tone marker plus an emphasis is usually enough.

Above: warm tone for the greeting → dramatic beat → emphasis on "waiting".

  • Tone markers (WARM, AUTHORITATIVE, DRAMATIC, EXCITED, WHISPER) cover whole phrases — don't combine two on the same phrase.
  • EMPHASIS works on a single word — place it directly before that word.
  • PAUSE always lives between sentences, never inside a clause.
  • BREATH is best after long sentences or before an emotional shift.

    • Optimal marker density

    Aim for roughly one marker per 8–15 spoken words. More than one marker per four words makes delivery sound robotic — the editor will warn you when you cross that threshold.

  • Sparse (1 per ~20 words): natural reads, audiobook, conversational.
  • Balanced (1 per ~10 words): corporate, IVR, social — recommended default.
  • Dense (1 per ~5 words): trailers, animation, high-energy radio — only short bursts.

    • Recommended markers by script type

  • Ivr: [PAUSE] [WARM] [EMPHASIS] [AUTHORITATIVE]
  • Corporate: [PAUSE] [WARM] [EMPHASIS] [AUTHORITATIVE]
  • Radio: [FAST] [EXCITED] [EMPHASIS:STRONG] [DRAMATIC]
  • Social: [FAST] [RISE] [EMPHASIS] [EXCITED]
  • Luxury: [SLOW] [PAUSE:BEAT] [FALL] [SOFT] [WARM]
  • Animation: Use the full range freely.