Voice Metrics & Classifications
A comprehensive glossary of how our AI Analysis Engine scores and categorizes voices across archetypes, textures, emotions, and physical metrics.
Archetypes
Archetypes define the core "character role" of a voice. They answer the question: "Who is speaking?"
Authority & Leadership
The Trusted Mentor
Wise, experienced, and authoritative.
A voice that commands respect through wisdom rather than volume. It inspires confidence without being overbearing, perfect for educational content, corporate leadership, and high-level advisory messaging.
If you want the audience to feel...
"I am learning from a wise master."
Best For
Self-help, life coaching, philosophy.
The Corporate Professional
Polished, efficient, and board-room ready.
Sophisticated and direct, this voice implies competence and reliability. Designed for B2B communications, industrial presentations, and scenarios where credibility is the only metric that matters.
If you want the audience to feel...
"I am doing serious business."
Best For
B2B sales, board presentations, formal announcements.
The News Anchor
Objective, articulate, and trustworthy.
Prompt, neutral delivery with flawless articulation. Perfect for breaking news, financial reports, and fact-based reporting where clarity and impartiality are paramount.
If you want the audience to feel...
"I need to know this right now."
Best For
Breaking news, urgent updates, finance reports.
The Radio God
Deep, resonant, and larger-than-life.
The classic 'Big Voice' with immense physical presence and timber. It commands immediate attention for promos, stadium announcements, and high-impact movie trailers.
If you want the audience to feel...
"I am listening to the ultimate truth."
Best For
Manifestos, vintage broadcasting, profound statements.
The Drill Sergeant
Strict, powerful, and uncompromising.
High-volume, authoritative command that demands action. Best for military characters, intense fitness coaching, and discipline-focused motivational content.
If you want the audience to feel...
"I need to get my act together NOW."
Best For
Motivational speeches, gym content, 'hard truths.'
Relatability & Trust
The Girl/Guy Next Door
Relatable, approachable, and effortlessly authentic.
A conversational tone that feels like a trusted friend. It avoids artificial polish in favor of genuine human connection, making it the gold standard for community-focused brands and modern, grounded narration.
If you want the audience to feel...
"I am chatting with a friend."
Best For
Daily vlogs, casual reviews, relatable stories.
The Caring Guide
Nurturing, supportive, and empathetic.
Warm, soft-edged delivery designed to comfort and assist. Its restorative quality makes it the primary choice for healthcare, wellness apps, and therapeutic experiences.
If you want the audience to feel...
"I am safe and understood."
Best For
Therapy, mental health awareness, non-profits.
The Spunky Sidekick
Witty, dynamic, and full of character.
Fast-paced and energetic with a focus on personality quirks. Best for animated characters, tech gadget demos, and energetic, youthful marketing.
If you want the audience to feel...
"I am going on a fun adventure."
Best For
Travel vlogs, gaming, energetic unboxings.
The Cool Parent
Modern, steady, and approachable.
Balances parental authority with contemporary relevance. It feels experienced and safe but remains open and relatable to a modern audience.
If you want the audience to feel...
"I am being guided, not bossed around."
Best For
Parenting advice, DIY tutorials, constructive criticism.
The Nervous Rookie
Uncertain, eager, and high-pitched.
Featuring slightly unstable delivery and rapid pitch shifts. Perfect for underdog characters, comedic storytelling, and relatable 'first-day-on-the-job' scenarios.
If you want the audience to feel...
"I am trying my best (just like you)."
Best For
'Fail' compilations, learning a new skill from scratch.
Edge, Grit & Intrigue
The Rebel / Antihero
Edgy, unconventional, and cool.
A gritty, slightly detached voice that lives outside the mainstream. Ideal for streetwear brands, contemporary gaming characters, and storytelling that challenges the status quo.
If you want the audience to feel...
"I am breaking the rules."
Best For
Counter-culture brands, skateboarding, disruption.
The Wicked Villain
Sinister, calculating, and dramatic.
Cold, deliberate, and often dripping with malice. Designed specifically for antagonist roles, dark fantasy settings, and projects requiring a touch of sophisticated menace.
If you want the audience to feel...
"I am in danger (or intrigued by evil)."
Best For
Horror narration, cautionary tales, dramatic storytelling.
The Noir Detective
World-weary, gravelly, and atmospheric.
A smoky voice that sounds like it has seen too much. Perfect for mysteries, crime dramas, and narratives that require a gritty, cinematic edge.
If you want the audience to feel...
"I am hearing a dark secret."
Best For
True crime, historical mysteries, deep dives.
The Streetwise Insider
Authentic, grounded, and real.
A voice with a distinct urban pulse that feels rooted in lived experience. It avoids commercial polish in favor of raw, street-level credibility.
If you want the audience to feel...
"I am getting the raw, unfiltered truth."
Best For
Alex Hormozi style, crypto, sales tactics, 'anti-guru' content.
Atmosphere & Vibe
The Luxury Spokesperson
Elegant, prestigious, and meticulously refined.
A voice of exclusivity, characterized by deliberate pacing and rich texture. It represents high-end fashion, automotive, and premium lifestyle brands with effortless sophistication.
If you want the audience to feel...
"I am buying something exclusive."
Best For
Perfume, high-end cars, architectural tours.
The Ethereal Spirit
Mystical, spacious, and otherworldly.
Breathy, weightless delivery that feels detached from the physical realm. Ideal for fantasy roles, sleep stories, and high-concept creative projects.
If you want the audience to feel...
"I am transcending reality."
Best For
Spiritual content, astrology, artistic showcases.
The Gentle Giant
Deep, resonant, and inherently kind.
Physically imposing timber softened by a gentle delivery. Perfect for reassuring characters, stable brands, and protective, fatherly figures.
If you want the audience to feel...
"I am being soothed and grounded."
Best For
Meditation, deep sleep stories, nature documentaries.
The Sleep Narrator
Hypnotic, soothing, and sedative.
Extremely low-energy delivery with high breathiness. Designed specifically to lower heart rates and guide listeners into deep, restorative relaxation.
If you want the audience to feel...
"I am drifting off to sleep."
Best For
Bedtime stories, hypnosis, white noise intros.
Modern & Niche
The Confident Narrator
Clear, commanding, and engaging.
A steady, professional anchor that keeps the audience focused. It balances objectivity with narrative interest, essential for documentaries, audiobooks, and long-form storytelling.
If you want the audience to feel...
"I am learning the objective facts."
Best For
Roman Army style, video essays, documentaries.
The Hype Man
High-octane, infectious, and adrenaline-fueled.
Fast-paced delivery designed to build excitement and momentum. It is the definitive choice for product launches, event promotions, and high-energy gaming or sports content.
If you want the audience to feel...
"I am pumped up and ready to party."
Best For
Event promos, sneaker drops, high-energy intros.
The Tech Bro
Visionary, fast-paced, and confident.
A futuristic tone characterized by speed and confidence. Ideal for startup pitches, crypto projects, and software technical demos that need to sound 'next-gen'.
If you want the audience to feel...
"I am optimizing my systems."
Best For
Toyota/Prius style, SaaS demos, productivity hacks, AI tools.
The Digital Assistant
Efficient, polite, and hyper-clear.
The quintessential AI companion. Characterized by helpful, neutral delivery and a focus on high-frequency utility tasks and smart-home integration.
If you want the audience to feel...
"I am being helped by a machine."
Best For
App tutorials, futuristic concepts, faceless channels.
The Tired Slacker
Indifferent, casual, and low-effort.
A voice that sounds borderline bored or deliberately unpolished. Perfect for comedic character roles, situational irony, and anti-establishment brand vibes.
If you want the audience to feel...
"I don't care (and neither should you)."
Best For
Gen Z irony, meme commentary, 'deadpan' humor.
Textures
Texture describes the "physical quality" or timber of the sound. It answers the question: "What does the voice feel like?"
Luxury & Comfort (Soft)
Velvet / Smooth
Liquid-like, luxurious, and seamless.
A voice with a consistent, flowing quality and zero audible friction. It feels high-end and effortless, gliding between words with rich, honeyed tones.
If you want the audience to feel...
"I am being wrapped in a blanket."
Best For
Luxury brands (Mercedes, Rolex), bedtime stories, premium intros.
Liquid / Warm
Resonant, comforting, and full-bodied.
Saturated with low-mid frequencies that provide an acoustic ‘embrace.’ This texture feels inherently human, stable, and deeply trustworthy.
If you want the audience to feel...
"I am being poured a drink."
Best For
Heartfelt charity appeals, therapy apps, welcoming tutorials.
Smoke / Husky
Textured, raspy, and alluring.
A sophisticated, breathy quality that suggests maturity and depth. It adds a natural weight and intimacy to every word, often implying experience.
If you want the audience to feel...
"I am sharing a secret in the dark."
Best For
Earl Nightingale style, noir storytelling, seductive ads, jazz radio.
Airy / Breathy
Light, spacious, and intimate.
Significant audible breath support that adds a sense of close-up intimacy or an ethereal, weightless presence to the delivery.
If you want the audience to feel...
"I am floating on a cloud."
Best For
ASMR, meditation guides, spiritual content, fashion/perfume ads.
Grit & Experience (Rough)
Gravel / Gritty
Rough, lived-in, and raw.
Deeply textured with prominent vocal fry or rasp. It feels authentic and unpolished, as if the voice has weathered many storms.
If you want the audience to feel...
"I am driving off-road."
Best For
Alex Hormozi style, truck commercials, 'hustle' motivation, action movie trailers.
Sandpaper / Dry
Matte, unpolished, and direct.
A flat texture with minimal resonance. It feels honest and grounded, stripping away the ‘commercial’ sheen in favor of a raw, matter-of-fact vibe.
If you want the audience to feel...
"I am touching raw earth."
Best For
Roman Army style, cynical comedy, deadpan humor, historical facts.
Steel / Cutting
Cold, precise, and powerful.
Featuring a sharp, metallic edge that implies dominance and a lack of emotional bias. It is the sound of command, control, and efficiency.
If you want the audience to feel...
"I am being cut by the truth."
Best For
Military commands, breaking news, urgent warnings, 'hard truths.'
Clarity & Modernity (Clean)
Glass / Clean
Transparent, sharp, and hyper-clear.
Focuses on extreme legibility and a bright top end. It remains perfectly clear even in noisy environments, ideal for critical information delivery.
If you want the audience to feel...
"I am looking through a clean window."
Best For
Toyota/Prius style, tech reviews, corporate manifestos, high-end documentaries.
Crystal / Piercing
Thin, brilliant, and cutting.
A high-frequency focus that cuts through background audio with laser precision. Designed to be impossible to ignore or misunderstand.
If you want the audience to feel...
"I am hearing a high-frequency signal."
Best For
Urgent notifications, announcements that must be heard over music.
Plastic / Sharp
Bright, artificial, and hyper-modern.
A synthesized, pop-focused clarity with extremely sharp edges. It fits perfectly within futuristic aesthetics or hyper-digital marketing contexts.
If you want the audience to feel...
"I am interacting with a perfect product."
Best For
Commercial radio, high-energy YouTubers, pop culture news, toys/candy ads.
Synthetic & Stylized (Unnatural)
Metal / Robotic
Synthesized, mechanical, and resonant.
Characterized by harmonic distortion or steady pitch modulation that feels explicitly machine-made. Ideal for sci-fi and industrial utility roles.
If you want the audience to feel...
"I am talking to a machine."
Best For
AI assistants, sci-fi narrators, futuristic concepts.
Rubber / Bouncy
Dynamic, elastic, and playful.
High pitch variance and rhythmic modulation. It feels like the voice is constantly in motion, moving elastically between notes and energies.
If you want the audience to feel...
"I am bouncing around with energy."
Best For
Cartoons, comedy skits, high-energy gaming content.
Emotions
Emotion defines the psychological intent or vibe of the delivery. It answers the question: "How is the speaker feeling?"
Confident / Assured
Stable, certain, and positive.
Defined by steady breath support and a lack of hesitation. This is the voice of someone who knows their value and the truth of what they are saying.
Friendly / Warm
Kind, approachable, and smiling.
A 'smiling' tone that uses soft inflections to build immediate rapport. It lowers the listener's guard and creates a welcoming atmosphere.
Sympathetic / Reassuring
Soft-edged, supportive, and kind.
An empathy-first delivery aimed at de-escalation or comfort. It prioritizes the listener's emotional well-being over the information itself.
Stoic / Calm
Unshaken, steady, and reliable.
Minimal emotional modulation. This voice projects a sense of peace and steady logic, remaining reliable even in high-stress descriptions.
Neutral / Clinical
Objective, dry, and fact-focused.
Purely informational delivery without emotional bias. Ideal for documentation, technical instructions, and safety protocols.
Apathetic / Bored
Uninterested, flat, and detached.
Deliberately low engagement used to communicate indifference. Most effective for specific character work, dry humor, or irony.
Eager
Enthusiastic, ready, and helpful.
A forward-leaning energy that suggests the speaker is excited to help or provide information. It radiates positive, active engagement.
Hype / Excited
Loud, motivated, and electrifying.
Peak emotional exertion designed to motivate an audience. It uses high volume and extreme pitch range to create a sense of manic energy.
Inspirational / Uplifting
Hopeful, grand, and encouraging.
Broad dynamics and a rising cadence. It makes the listener feel part of a larger purpose and encourages them to look toward a better future.
Whimsical / Playful
Fun, lighthearted, and mischievous.
A voice full of unexpected inflections and rhythmic shifts. It suggests a sense of play and avoids taking itself or the subject too seriously.
Sarcastic / Dry
Witty, biting, and ironic.
Uses subtext and 'eye-rolling' inflections to mock the subject matter. It is a voice of intelligence and skepticism.
Melancholic
Sad, reflective, and weighted.
Lower pitch and slower tempo, carrying the acoustic weight of loss, nostalgia, or deep, solitary thought.
Anxious / Scared
Unsteady, worried, and tight.
Characterized by high instability, shallow breathing patterns, and sharp, defensive inflections. It communicates immediate stress or fear.
Urgent / Stressed
Pressured, fast, and high-stakes.
Rapid delivery with sharp, clipping articulation. It suggests a situation that requires immediate attention and has no time for pauses.
Aggressive / Angry
Hostile, intense, and forceful.
Forceful projection often paired with harsh textures. It is used to express dominance, frustration, or outright rage.
Condescending / Strict
Judgmental, cold, and superior.
A voice that speaks from a position of perceived superiority. It uses precise, cold articulation to reprimand or diminish the listener.
Seductive / Intimate
Close, alluring, and magnetic.
Low-volume, high-texture delivery intended for magnetism and close-quarter focus. It suggests a private conversation and deep attraction.
Voice Metrics (1-10 Scale)
Voice Metrics are quantified measurements of a voice's characteristic qualities. Most are measured on a 1-10 scale by our AI Analysis Engine.
Expressiveness
Measures the personality and pitch modulation range of the voice.
Robotic, extremely stoic, or repressed. Minimal pitch variation.
Polite, conversational, and professional. Typical for assistants and news.
High character acting, sing-songy, and highly modulated pitch.
Roughness
Measures the signal noise, including grit, breath, and vocal fry.
Synthetic perfection or high-end commercial polish. No audible grit.
Human warmth with slight breathiness or light rasp.
Distinct vocal fry, heavy rasp, or a 'smoker' quality.
Aggressive growl, vocal damage, or extreme noise.
Projection
Measures the perceived distance the voice is 'throwing' its sound.
Whisper, close-proximity, 'pillow talk' or ASMR style.
Speaking naturally to a person 3 feet away.
Public speaking, stage acting, or 'Hard Sell' commercials.
Screaming, survival instinct, or extreme urgency.
Tempo
Measures the perceived urgency and speed of delivery.
Dragging words, hypnotic pacing, or pauses longer than words.
Natural conversation or deliberate explanation.
Rushing, removing pauses, high urgency or excitement.
Brightness
Measures the EQ balance (Treble vs. Bass) of the voice.
Muffled, chest-heavy, or deeply resonant.
Natural balance between highs and lows.
Nasal, piercing, cutting, or 'tinny' quality.
Instability
Measures the level of vocal control, wobble, or emotional tremor.
Confident, solid breath support, and unwavering pitch.
Natural human emotion with slight, realistic tremors.
Crying, terrified, laughing, or shivering.
Articulation
Measures the clarity and enunciation of consonants.
Mumbling, swallowing consonants, or 'Mumblecore' style.
Standard conversational clarity.
Broadcaster crispness with clear T's and K's.
Pedagogical, robotic precision, or over-enunciated.
Accent Strength
Measures the intensity of the speaker's regional accent.
'Global English' or General American. Barely detectable region.
Clear regional marker (e.g., Standard British).
Heavy dialect, stylized character accent, harder for non-natives.
Perceived Age
Measures the biological age quality of the voice.
Pre-pubescent voice.
Adolescent tone.
Approx. 18-35 years old.
Established adult, approx. 35-55 years old.
Authority figure, approx. 55-65 years old.
Elderly, 65+ years old.
Naturalness
Measures how human-like and natural the voice sounds (MOS scale).
Clearly artificial, metallic, or glitched.
Choppy transitions, unusual rhythm, or digital artifacts.
Occasionally expressive but still identifiable as synthetic.
Highly realistic with natural prosody and emotional nuances.
Indistinguishable from a high-quality human recording.
Physical Analysis
Pitch (Hz)
The fundamental frequency of the voice. Lower values (80-150Hz) sound deeper/masculine, while higher values (200Hz+) sound higher/feminine or youthful.
Unit: Hz
Words Per Minute (WPM)
The speed of speech. Average conversation is ~140-160 WPM. Values above 190 WPM are considered fast/energetic, while below 120 WPM are slow/deliberate.
Unit: WPM
Vocal Fry
A measurement of the creaky, low-register vibration in the voice. Often perceived as relaxed, trendy, or tired. High values indicate prominent fry.
Unit: Ratio (0-1)