Writing Prompts for Voice Emotions

Several techniques can be used to control the emotional tone of voice scripts for talking animations, such as using expressive interjections or adding emotional cues to the prompt or the speech text.

Voice Emotion Prompting

Add emotional cues in the Prompt field to describe the character's emotional state and mindset while speaking.

Prompt	Reference Image / Video
The boy sat on a fallen log, his legs dangling and swinging in the air. Fireflies danced around him, and the boy looked up at them with delight, his movements and expressions animated. He looked left and right, gesturing wildly as he talked to the fireflies.
Speech Text	AI Output
Hey, you’re late! I thought you guys weren’t coming!
Prompt	Reference Image / Video
A man in an interrogation room, staring firmly straight ahead with intense anger and absolute confidence in his eyes. His eyebrows are sharply furrowed, creating a deep frown that shows vivid, angry micro-expressions. A slightly clenched jaw and subtle twitch in the facial muscles exude a powerful aura, as if he has completely seen through the conspiracy. He delivers a commanding and passionate movie dialogue line with rich, lively facial performance filled with authority. Cinematic modern neo-noir film style, sharp focus on realistic skin textures and raw emotions.
Speech Text	AI Output
Every single alibi you gave me is a complete lie... You have two choices right now: you either look me in the eye and talk, or you go down for all of it. Huh?
Prompt	Reference Image / Video
He speaks with furious anger, staring straight ahead with a highly expressive, comedic angry face—especially with intense, animated eyebrow movements. His mouth shapes must also be highly exaggerated as he talks.
Speech Text	AI Output
Look at this mess you made... You screwed up the whole thing!

Expressive Interjections

Expressive interjections can make dialogue more vivid. Common examples and emotional contexts are as follows:

Expressive Interjection	Emotional Context
Wow!, Oh!, Aha!	Surprise / Amazement
Ouch!, Ow!	Pain
Ew!, Yuck!	Disgust
Yay!, Hooray!, Woohoo!	Joy / Excitement
Oops!, Whoops!	Mistake / Regret
Hmm...	Thoughtfulness / Hesitation

Single Actor

Scenario	Speech Text	Text to Voice
Playful Nostalgia	Haha! Sometimes I still catch the scent of rain on the pavement and, for a second, I’m ten years old again, standing right here with you. Hehehe~
Frustration + Nostalgia	Damn it! Listen to me! Sometimes I still catch the scent of rain on the pavement and, for a second, I’m ten years old again, standing right here with you.

Multiple Actors

Scenario	Speech Text	Text to Voice
Speaker A has a realization; Speaker B is amazed by how the place has changed.	A: Aha! I haven't been here in a long time. B: Wow! It's good to see this place again.
Speaker A dislikes the place; Speaker B realizes the comment came out awkwardly.	A: Ew... I haven't been here in a long time. B: Whoops... It's good to see this place again.
Both speakers A and B are excited.	A: Yay! We finally made it! B: Woohoo! I was waiting for you!
Speaker A realizes something; Speaker B responds with slight awkwardness.	A: Aha! We finally made it. B: Whoops... I was waiting for you.

Emotional Prefixes

Try using the following emotional prefix formulas in the Speech Text field:
[Pitch], [Speed], [Tone / Resonance], [Emotion]

Scenario	Speech Text	Text to Voice
Playful teasing	[Amused, Bouncy, Bright, Warm] Sometimes I still catch the scent of rain on the pavement and, for a second, I’m ten years old again, standing right here with you.
Whispered secret	[Breathy, Soft, Slow pace, Low pitch] Sometimes I still catch the scent of rain on the pavement and, for a second, I’m ten years old again, standing right here with you.
Angry confrontation	[Aggressive, Sharp, Fast pace, Strained] Sometimes I still catch the scent of rain on the pavement and, for a second, I’m ten years old again, standing right here with you.
Cold villain dialogue	[Cold, Low pitch, Deliberate, Raspy] Sometimes I still catch the scent of rain on the pavement and, for a second, I’m ten years old again, standing right here with you.

Back to Product Home

Emotional Prefix	Effect Description	Emotional Context
Low pitch	Lowered vocal pitch, creating a steady or suppressed tone.	Sadness, coldness, threats, exhaustion.
High pitch	Raised vocal pitch, sounding sharp or bright.	Excitement, surprise, panic, playful affection.
Monotone	Minimal pitch variation, delivering lines in a flat robotic manner.	Reading scripts, emotionless delivery, narration, AI voice.
Dynamic pitch	Wide pitch variation with strong dramatic expression.	Storytelling, speeches, intense emotions.

Emotional Prefix	Effect Description	Emotional Context
Slow pace	Slower speaking speed with extended spacing between words.	Nostalgia, deep affection, weakness, serious warnings.
Fast pace	Faster speaking speed with tighter articulation.	Tension, anxiety, excitement, heated arguments.
Rushed	Sense of haste; sentence endings may cut off quickly.	Running away, being in a hurry, panic.
Deliberate	Intentional and clearly articulated delivery with noticeable pauses.	Lecturing, issuing ultimatums, declaring rules.

Emotional Prefix	Effect Description	Emotional Context
Breathy	Airy vocal delivery with reduced solidity and noticeable breathiness.	Weakness, sorrow, extreme gentleness, whispering.
Raspy	Hoarse and rough voice texture with noticeable graininess.	Just waking up, post-yelling exhaustion, villain characters.
Soft	Smooth and gentle resonance with minimal aggressiveness.	Comforting, reminiscing, talking to small animals.
Sharp	Voice has a sharp edge with strong penetration.	Sarcasm, harsh scolding, giving commands.
Strained	Tense voice, as if the throat is constricted or overexerted.	Suppressed anger, pain, extreme impatience.
Bright	Clear, crisp, and glossy voice quality that sounds energetic.	Cheerful morning greetings, hopeful speeches.
Crisp	Clean and precise articulation with confidence and briskness.	Solving a puzzle successfully, confident declarations.
Bouncy	Elastic and lively vocal rhythm with a playful cadence.	Discovering amusing little things, joking with friends.

Emotional Prefix	Effect Description	Emotional Context
Cold	Detached from all emotional warmth; indifferent.	Refusal, stating harsh facts, ignoring.
Warm	Slightly smiling resonance; friendly tone.	Slightly smiling resonance; friendly tone.
Sad / Melancholic	Slightly lowered tone, lacking vitality.	Heartbreak, mourning, recalling sad memories.
Aggressive	Strong aggression; every word carries attacking energy.	Provocation, anger, pre-battle moments.
Calm	Stable emotion with no obvious fluctuations.	Daily conversation, explanation, rational analysis.
Joyful / Happy	Basic sense of pleasure; naturally light and upbeat tone.	Sharing good news, simple positive moods.
Cheerful	Bright and energetic; strong positive energy.	Motivating teammates, enthusiastic greetings, low-stress situations.
Excited / Thrilled	Very high energy; emotionally intense and hard to control.	Rare achievements, major exciting events.
Excited / Thrilled	Very high energy; emotionally intense and hard to control.	Rare achievements, major exciting events.
Amused	Feeling entertained; tone carries subtle laughter.	Funny scenes, light humorous teasing.