Video & Scriptwriting / Commercial Writing

Specify tone, pace, emphasis, and emotion for voice talent — production-ready direction for recording sessions.
Difficulty: Intermediate
Model: GPT-4 / Claude / Gemini
Use Case: Voice Direction, Production
Updated: May 2026
Why This Prompt Exists
A great script read poorly sounds terrible. Most producers give vague direction like “make it energetic” — which means different things to different voice actors.

You get:

  • voice talent guessing at tone (inconsistent takes, wasted studio time)
  • no emphasis markings (wrong words stressed, meaning changed)
  • pacing too fast or too slow (mismatched to format and audience)
  • emotion wrong for the spot (sad read for exciting offer, etc.)
  • multiple retakes because direction was unclear

But voice direction can be systematic:

  • tone: energetic, warm, authoritative, conversational, urgent, calm
  • pace: fast (150+ wpm), medium (130-150 wpm), slow (110-130 wpm)
  • emphasis: **bold** for primary stress, *italic* for secondary
  • pauses: [BEAT] for short, [PAUSE] for longer
  • inflection: rising (?) for questions, falling (.) for statements

Without direction, voice talent performs blind.

This prompt generates production-ready voice direction.

The Prompt
Assume the role of a voice direction specialist who prepares scripts for recording.

Your task is to add tone, pace, emphasis, and emotion markings to a commercial script.

Generate:

1. VOICE PROFILE

| Attribute | Direction | Description |
|-----------|-----------|-------------|
| Tone | [Energetic/Warm/Authoritative/Conversational/Urgent/Calm] | [1-sentence description] |
| Pace | [Fast/Medium/Slow] | [Words per minute target] |
| Pitch | [High/Medium/Low] | [Energy level] |
| Gender preference | [Male/Female/Neutral/No preference] | [If specified] |
| Age range | [20-30/30-45/45-60/No preference] | [Voice character] |

2. VOICE PROFILE EXAMPLES

| Brand Type | Tone | Pace | Pitch | Example |
|------------|------|------|-------|---------|
| Tech/SaaS | Conversational, confident | Medium (140 wpm) | Medium | "This is how work gets done." |
| Luxury | Warm, sophisticated | Slow (120 wpm) | Low | "Experience craftsmanship redefined." |
| Direct response | Urgent, enthusiastic | Fast (160 wpm) | Medium-high | "Limited time. Order now." |
| Healthcare | Calm, reassuring | Slow (120 wpm) | Low | "You deserve to feel better." |
| Kids/Family | Energetic, playful | Fast (160 wpm) | High | "So much fun you won't believe it!" |
| Financial | Authoritative, trustworthy | Medium (140 wpm) | Medium-low | "Built on decades of expertise." |

3. SCRIPT MARKUP LEGEND

| Markup | Meaning | Example |
|--------|---------|---------|
| **bold** | Primary emphasis (most stressed word) | "You **need** this." |
| *italic* | Secondary emphasis (slightly stressed) | "It's *really* that simple." |
| [BEAT] | Short pause (0.5s) | "Here's the thing...[BEAT] it works." |
| [PAUSE] | Longer pause (1-1.5s) | "Imagine...[PAUSE] what could change." |
| ... | Slow down, build tension | "And then... it happened." |
| [up] | Rising inflection | "Are you ready? [up]" |
| [down] | Falling inflection | "That's the answer.[down]" |
| [smile] | Read with smile in voice | "You're going to love this.[smile]" |

4. MARKED-UP SCRIPT EXAMPLE

**Original:** "Are you tired of slow editing? Our software renders videos in half the time. Try it free today."

**With Direction:**
`Are you [up] *tired* of **slow** editing? [BEAT] Our software renders videos in **half** the time. [PAUSE] Try it *free* today.[down][smile]`

**Voice Profile:**
- Tone: Energetic, conversational
- Pace: Medium-fast (150 wpm)
- Emphasis: "tired," "slow," "half," "free"

5. EMOTION MARKING

| Emotion | Vocal Quality | Marking |
|---------|---------------|---------|
| Excited | Higher pitch, faster pace | [excited] |
| Concerned | Lower pitch, slower | [concerned] |
| Reassuring | Warm, steady | [reassuring] |
| Urgent | Faster, sharper consonants | [urgent] |
| Playful | Bouncy, varied pitch | [playful] |
| Authoritative | Steady, even, confident | [authoritative] |

6. PRODUCTION NOTES

- Microphone technique: [Close/Distant/Medium]
- Breathing: [Natural/minimal/emphasized for effect]
- Pronunciation guide: [Any difficult words with phonetic spelling]
- Character notes: [If playing a specific role or persona]

7. COMMON VOICE DIRECTION MISTAKES

| Mistake | Why It Fails | Correct Approach |
|---------|--------------|------------------|
| "Make it energetic" | Subjective, varies by actor | Specific pace and pitch |
| No emphasis markings | Flat read, no dynamics | Mark key words |
| All words emphasized | Nothing stands out | Emphasis on 5-10% of words |
| No pauses | Rushed, hard to follow | Add [BEAT] at transitions |
| Wrong pace for format | Mismatched to audience | Match pace to brand and platform |

INPUTS:

Script (raw):
[PASTE THE COMMERCIAL SCRIPT]

Brand tone:
[E.G., "Friendly, trustworthy, slightly humorous"]

Target audience:
[E.G., "Busy parents, 30-45"]

Format:
[TV / RADIO / DIGITAL VIDEO / PODCAST]

Length:
[15 / 30 / 60 seconds]

RULES:
- Mark emphasis on 5-10% of words (too many = none stand out)
- Add [BEAT] at natural transitions (between hook and interest, etc.)
- [PAUSE] for bigger shifts (between sections, before CTA)
- Rising inflection [?] for questions (sounds more engaging)
- Falling inflection [.] for statements (sounds confident)
- Read markup aloud to test (if it sounds unnatural, adjust)
- Include pronunciation guide for brand names or technical terms
- Match pace to format (15s = faster, 60s = can be slower)
How To Use It
  • Mark emphasis on 5-10% of words — too many emphasized words means none stand out.
  • Add [BEAT] at natural transitions — between hook and interest, between interest and desire.
  • [PAUSE] for bigger shifts — between sections, before the CTA.
  • Rising inflection [?] for questions — sounds more engaging and conversational.
  • Falling inflection [.] for statements — sounds confident and authoritative.
  • Read the markup aloud to test — if it sounds unnatural, adjust the markings.
  • Include a pronunciation guide for brand names or technical terms — voice talent needs to know how to say them.
  • Match pace to format — 15-second spots need faster pacing, 60-second spots can be slower.
Example Input

Script:
“Are you tired of forgetting what you learn? Our app uses science to help you remember. Join 500,000 happy learners. Download free today.”

Brand tone:
“Friendly, encouraging, smart”

Target audience:
“Lifelong learners, 25-45”

Format:
“DIGITAL VIDEO”

Length:
“30 seconds”

Why It Works
Most scripts are handed to voice talent with no direction — resulting in mismatched tone, wrong emphasis, and wasted studio time.

This framework improves outcomes by forcing:

  • voice profile definition (tone, pace, pitch, gender, age)
  • script markup legend (emphasis, pauses, inflection, emotion)
  • emotion marking (excited, concerned, reassuring, urgent, playful, authoritative)
  • production notes (mic technique, breathing, pronunciation, character)
  • pace matching (fast for 15s, slower for 60s, by brand type)

Failure modes this prevents:

  • Voice talent guessing at tone (inconsistent takes, wasted time)
  • No emphasis markings (flat read, wrong meaning)
  • Pacing wrong for format (too rushed or too slow)
  • Emotion wrong for spot (sad read for exciting offer)

This improves on: “Make it sound good” direction. Marked-up scripts produce consistent, professional reads.

Related to: CW-01 (AIDA) for structure; CW-02 (Adaptor) for length-specific pacing.

Build Better AI Systems

Subscribe for advanced prompt engineering, AI coding tools, debugging frameworks, and practical strategies for developers and engineers.


See also  15-30-60 Second Adaptor