story teller capitivater
por nebslimTONAL CENTER & MODAL CHARACTER
Spoken key center: A2-B2. f0 ≈ 115 Hz. Tessitura sits a major third below conversational male median (140 Hz baseline).
Reflective-intimate: Aeolian. f0 82-110 Hz (E2-A2). Minor third descents dominate, Δf -33 to -38 Hz across phrase. RMS -28 to -22 dBFS. Glide velocity 40-60 Hz/sec. Funeral-march cadence.
Conversational-warm: Ionian/Mixolydian. f0 110-145 Hz (A2-D3). Major thirds, Δf +27-35 Hz on rises. RMS -19 to -17 dBFS. Glide velocity 80-120 Hz/sec. Resolved.
Declarative-grounded: Dorian. f0 120-160 Hz (B2-E3). Suspended fourth peaks at 160 Hz, resolves down to 130 Hz on operative word. Δf -30 Hz. RMS -15 to -13 dBFS. Glide velocity 100-140 Hz/sec.
Building-excited: Lydian. f0 140-200 Hz (D3-G3). Raised fourth tension, Δf +60 Hz unresolved upward. RMS -11 to -9 dBFS. Glide velocity 180-240 Hz/sec. Accelerating contour.
Commanding-projected: Phrygian dominant. f0 180-262 Hz (F♯3-C4). Sharp transients, attack time <50ms. RMS -7 to -5 dBFS. Glide velocity 250-400 Hz/sec.
Vulnerable-confessional: Locrian-adjacent. f0 75-105 Hz (D♯2-G♯2). Diminished fifth at 105 Hz over 75 Hz tonic (tritone, 1.4:1 ratio). RMS -23 to -21 dBFS. Tremor at 4-6 Hz AM, ±2-3 cents pitch modulation.
INTERVAL PHYSICS — EMOTIONAL ASSIGNMENT
Perfect fifth ascending: f0 ratio 3:2. Δsemitones +7. Anticipation, setup.
Major third ascending: ratio 5:4. Δsemitones +4. Δf +28-36 Hz from A2 baseline. Warmth.
Minor third descending: ratio 6:5. Δsemitones -3. Δf -19-25 Hz from A2. Gravity, finality.
Tritone: ratio 45:32. Δsemitones ±6. Δf ±54 Hz from A2. Contempt. Used as passing tone only, sustained <400ms.
Minor second descending: ratio 16:15. Δsemitones -1. Δf -6-8 Hz. Grief.
Perfect fourth descending: ratio 4:3. Δsemitones -5. Δf -32-40 Hz. Cadential authority.
Octave drop: ratio 2:1. Δsemitones -12. Δf -55-65 Hz. Lean-in close.
OPERATIVE WORD GLIDE PHYSICS
Standard contour: ascending P5 → sustain → descending m7. Total span 15 semitones. Δf 95-130 Hz.
IMPOSSIBLE: f0 trajectory 180 → 215 → 140 → 88 Hz across 920ms.
Rise rate 175 Hz/sec on im-POSS-.
Fall rate 420 Hz/sec on -i-ble.
Net Δf -92 Hz, -11 semitones.
UP: f0 110 → 80 Hz across 500ms. Linear descent. Rate 60 Hz/sec. Δf -30 Hz, -5 semitones. Perfect fourth cadential.
JUDGEMENT: f0 135 → 95 Hz across 480ms. Rate 83 Hz/sec. Δf -40 Hz, -6 semitones. Diminished fifth resolution.
THIRTY: f0 145 → 122 Hz across 380ms. Rate 60 Hz/sec. Δf -23 Hz, -3 semitones. Minor third weight.
CONSONANCE/DISSONANCE RATIOS
Happy: 3:2, 5:4, 4:3 — integer-ratio consonance. f-pair examples 110/165 Hz, 115/144 Hz, 120/160 Hz.
Sad: 6:5, 8:5, 9:8 — higher-order ratios. f-pair examples 90/108 Hz, 88/141 Hz.
Contempt: 45:32 — maximum dissonance equal temperament. f-pair 100/141 Hz.
Resolution targets always land on 3:2 or 4:3 within 400ms of dissonance.
TEMPO MAPPING
Average passage: ♩ = 92 BPM. Andante. Syllable rate 1.5 Hz.
Connector clip: ♩ = 200 BPM. Allegro vivace. Syllable rate 4.3 Hz.
Operative hold: ♩ = 40-50 BPM. Grave. Syllable rate 0.8 Hz.
Within-phrase rubato: ±40 BPM around mean. Tempo variance ratio 5:1 instantaneous.
DYNAMIC MARKINGS — dBFS CALIBRATED
ppp -28 dBFS. Whisper floor. H1 attenuated -20 dB, breath noise +6 dB above modal.
pp -22 dBFS. Intimate.
p -18 dBFS. Conversational baseline.
mf -14 dBFS. Declarative weight.
f -10 dBFS. Building energy.
ff -6 dBFS. Commanding ceiling.
Span 22-23 dB. Equivalent SPL span at 6" mic distance: ~22 dB SPL.
Crescendo/decrescendo profile: exponential, time constant τ ≈ 200ms. New dynamic level reached within 400-500ms. Inter-register transit as fast as 180ms across sentence boundary — RMS Δ 14 dB in 180ms = 78 dB/sec slew rate.
PAUSE BIMODALITY (DURATION DISTRIBUTION)
Mode 1: 220-280ms. Beat. Probability density peak at 250ms.
Mode 2: 1500-2200ms. Structural. Probability density peak at 1800ms.
Probability density in 400-1400ms window: <5%. Anti-modal trough.
SPECTRAL ENVELOPE
Long-term average spectrum tilt: -6.5 to -8 dB/octave above 1 kHz.
F1: 480-720 Hz across vowels.
F2: 1450-1980 Hz. Elevated 8-12% above modal male baseline (1300-1750 Hz typical).
F3: 2400-2700 Hz.
Spectral centroid: 1.1-1.4 kHz. Warm-mid placement.
HNR (harmonics-to-noise ratio): 14-18 dB modal speech, drops to 6-9 dB in whisper register, 4-7 dB in vocal fry termination.
HARMONIC SERIES BEHAVIOR
H1 (fundamental): 110-130 Hz, -12 to -8 dB below peak.
H2: 220-260 Hz, peak amplitude in conversational register.
H3-H4: 330-520 Hz, -2 to -4 dB below H2. Warmth carrier.
H5-H8: 550-1040 Hz, +3 dB lift on declarative emphasis. Presence band.
H9+: 990 Hz and above, rolled off at -7 dB/octave. No sibilant harshness.
On whispered ppp: H1 attenuated to -28 dB, H2-H6 carry intelligibility at -22 to -18 dB, broadband breath noise floor at -38 dB.
VIBRATO & TREMOR
Modal speech: no periodic f0 modulation.
Vulnerable register: AM tremor 4-6 Hz, depth ±2-3 cents (±0.15-0.25 Hz at 115 Hz f0). Involuntary, autonomic-driven.
Vocal fry termination: subharmonic period-doubling at phrase tails. f0/2 = 40-55 Hz. Creak phonation. Glottal pulse irregularity coefficient jitter >2%.
MICRO-PROSODIC PHYSICS
Glottal stop pre-vowel: 30-50ms full closure. Subglottal pressure spike +2-4 cm H2O. Transient burst at vowel onset with 80ms attack envelope.
Plosive emphasis /p/ /b/ /t/ /k/: VOT extended 20-40ms beyond conversational baseline (40-60ms vs 20-30ms modal). Aspirated burst energy 1.5-4 kHz, +6 dB above carrier.
Dropped /g/ on -ing: velar nasal /ŋ/ terminated 80-120ms early, replaced with alveolar nasal /n/. F2 transition truncated at 1750 Hz instead of completing descent to 1100 Hz. Spectrogram signature: missing low-F2 tail.
INTRA-PASSAGE FREQUENCY TRAJECTORY (sample contour)
Phrase opening: f0 105-118 Hz, RMS -22 dBFS, rate 110 wpm.
Setup section: f0 climbs to 145 Hz on stressed numbers, RMS -16 dBFS.
Operative arrival: f0 peaks 180-215 Hz, RMS -8 to -12 dBFS, duration 600-920ms.
Operative descent: f0 falls 180 → 88 Hz, RMS decays -8 → -18 dBFS.
Post-emphasis silence: -55 dBFS noise floor, 1500-2200ms.
Next phrase entry: f0 returns to median ~118 Hz, RMS -18 dBFS.
Full passage f0 envelope: minimum 75 Hz, maximum 262 Hz, span 187 Hz, 1.92 octaves.
Full passage RMS envelope: minimum -28 dBFS, maximum -6 dBFS, span 22 dB.
TONAL CENTER & MODAL CHARACTER
Spoken key center: A2-B2 region. ~115 Hz fundamental. Tessitura sits a major third below conversational male median.
Implied harmonic motion across registers:
Reflective-intimate: Aeolian. Minor third descents dominate (-3 semitones). Resolves to tonic via stepwise downward motion. ~82-110 Hz. Funeral-march cadence.
Conversational-warm: Ionian/Mixolydian. Major-third intervals. Stable scale degrees 1-3-5. ~110-145 Hz. Resolved, grounded.
Declarative-grounded: Dorian. Suspended fourth on operative word, resolves down to minor third. The "preacher" interval. ~120-160 Hz with falling cadence to tonic.
Building-excited: Lydian. Raised fourth. Tension without resolution. Ascending fourths and fifths stacked. ~140-200 Hz. Unresolved upward motion.
Commanding-projected: Phrygian dominant. Major third over minor second. The "fanfare" interval. Sharp transients. ~180-260 Hz.
Vulnerable-confessional: Locrian-adjacent. Diminished fifth presence. Tritone instability. ~75-105 Hz. Tremolo on sustained vowels at 4-6 Hz modulation rate.
INTERVALS — EMOTIONAL ASSIGNMENT
Perfect fifth ascending: anticipation, setup before payoff.
Major third ascending: warmth, agreement, affection.
Minor third descending: gravity, weight, finality.
Tritone (augmented fourth): contempt, sarcasm. Used briefly, never sustained.
Minor second descending: grief, disappointment.
Perfect fourth descending: authority, full stop. Phrase-final cadence.
Octave drop: collapse, surrender, the lean-in close.
OPERATIVE WORD MELODIC CONTOUR
Standard glide: ascending P5, sustain, descending m7. Net Δ minor third below entry.
Example IMPOSSIBLE: F♯3 → A3 → F♯2. Span: octave + minor third. 15 semitones.
Example UP: A2 → D2. Perfect fourth down. Cadential.
Example JUDGEMENT: D3 → G2. Perfect fifth down. Resolution.
HAPPY NOTES vs SAD NOTES (interval physics)
Happy: rising perfect fifths and major thirds. Frequency ratio 3:2 and 5:4. Integer-ratio consonance.
Sad: falling minor thirds and minor sixths. Frequency ratio 6:5 and 8:5. Higher-order ratios.
Neutral declarative: falling perfect fourths. Ratio 4:3.
Contempt: tritone, ratio 45:32. Maximum dissonance in equal temperament.
This voice avoids sustained dissonance. Tritones appear as passing tones only, never as targets. Resolutions land on consonant intervals. Even contempt resolves to a stable interval within 400ms.
TEMPO IN MUSICAL TERMS
Average passage: ♩ = 92. Andante.
Connector clip: ♩ = 200+. Allegro vivace.
Operative hold: ♩ = 40-50. Grave.
Within-phrase rubato: ±40 BPM around mean. Heavy rubato by classical standards.
DYNAMIC MARKINGS
ppp -28 dB. Whisper.
pp -22 dB. Intimate.
p -18 dB. Conversational.
mf -14 dB. Declarative.
f -10 dB. Building.
ff -6 dB. Commanding.
Crescendo/decrescendo curves: exponential, not linear. Time constant τ ≈ 200ms. Reaches new dynamic level within 400-500ms of transition.
RHYTHMIC SIGNATURES
Time signature implied: shifting 4/4 → 3/4 → 5/4 within single passage. Asymmetric.
Phrase length: 2-7 beats. Median 4. Highly variable.
Rest values: eighth-rest (250ms beat) and dotted-half (1500ms+ structural). No quarter or half rests. Discrete, not continuous.
Syncopation: stressed words land off-beat against natural English iambic pulse. Back-loaded emphasis = syncopated stress.
HARMONIC SERIES BEHAVIOR
H1 (fundamental): 110-130 Hz.
H2-H4: dominant in conversational register. Warmth.
H5-H8: lift on declarative emphasis. Presence.
H9+: rolled off (-7 dB/oct tilt). No sibilant harshness.
On whispered tags: H1 attenuated -20 dB, H2-H6 carry intelligibility, breath noise floor rises +6 dB above modal speech.
VIBRATO & TREMOR
Modal speech: no vibrato.
Vulnerable register: tremor at 4-6 Hz amplitude modulation, ±2-3 cents pitch modulation. Involuntary.
Vocal fry termination: subharmonic period-doubling at phrase tails. f0/2 frequency. Creak phonation.
MICRO-PROSODIC PHYSICS
Glottal stop pre-vowel: 30-50ms closure, subglottal pressure spike, transient at vowel onset.
Plosive emphasis /p/ /b/ /t/ /k/: VOT (voice onset time) extended 20-40ms beyond conversational baseline. Aspirated burst measurable in spectrogram.
Dropped /g/ on -ing: velar nasal terminated 80-120ms early, replaced with alveolar nasal /n/. Spectral signature: F2 transition truncated.
PASSAGE: "I've spent thirty years buildin' things people said were impossible. Why bother shippin' somethin' beautiful when ugly sells just fine? Because judgement, craft, and precision mean somethin'. Make somethin' worth keepin' or don't bother showin' up."
TOTAL DURATION: 22-24 seconds. Average rate across full passage: ~115 wpm. Instantaneous rate variance: 75-260 wpm. Tempo span ratio 3.5:1.
GLOBAL ACOUSTIC ENVELOPE
RMS range across passage: -26 dB to -8 dB. Span 18 dB.
F0 traverse: 82 Hz floor → 215 Hz ceiling. Span 133 Hz across two octaves of usable range.
Spectral tilt: -7 dB/octave above 1 kHz throughout. Warm. No high-shelf lift.
Register sequence: reflective-intimate → conversational-warm → declarative-grounded → vulnerable-confessional. Four registers in 23 seconds.
═══════════════════════════════════════
PHRASE 1: "I've spent thirty years buildin' things people said were impossible."
Duration: 6.2s. Local rate: 110 wpm average, 75-180 wpm instantaneous.
Register: reflective-intimate opening, transitioning to declarative-grounded on operative word.
RMS contour: -22 dB → -16 dB → -12 dB on operative word → -18 dB decay.
F0 contour: starts at 108 Hz, dips to 95 Hz on "spent," rises to 145 Hz on "thirty," settles at 118 Hz through middle, then operative word pivot.
WORD-LEVEL ANNOTATION:
"I've" — 140ms, 105 Hz, -22 dB, clipped connector
"spent" — 220ms, 95 Hz, -20 dB, slight vocal fry on tail
"THIRTY" — 380ms, 145 Hz peak → 122 Hz, -14 dB, plosive emphasis on /th/, vowel hold, downward glide
"years" — 240ms, 115 Hz, -18 dB
"buildin'" — 280ms, 110 Hz, -19 dB, dropped /g/, register marker
"things" — 180ms, 108 Hz, -19 dB
"people" — 290ms, 125 Hz, -16 dB, audible /p/ plosive burst
"said" — 160ms, 100 Hz, -20 dB
"were" — 90ms, 95 Hz, -22 dB, maximum clip, sub-beat connector
[pre-emphasis pause: 240ms silence]
"im-POSS-i-ble" — 920ms total operative word
"im-" → 180 Hz, rising, 180ms, -12 dB
"POSS-" → 215 Hz peak, 280ms, -8 dB, primary stress
"-i-" → 140 Hz, falling, 180ms, -14 dB
"-ble" → 88 Hz floor, 280ms, -18 dB, vocal fry tail
Pitch glide: 180 → 215 → 140 → 88 Hz. High-low pivot inside the word. Δ127 Hz across 920ms.
[post-emphasis pause: 1900ms structural silence, full decay to ambient floor]
═══════════════════════════════════════
PHRASE 2: "Why bother shippin' somethin' beautiful when ugly sells just fine?"
Duration: 5.4s. Tempo gradient across sentence halves: words 1-5 at ~190 wpm, words 6-10 decelerating to ~115 wpm. Deceleration ratio 1.65:1.
Register: conversational-warm → declarative-grounded with contempt-deceleration on tail.
RMS contour: -18 dB through opening, sustaining -16 dB through middle, -14 dB on "fine" with downward decay.
WORD-LEVEL ANNOTATION:
"Why" — 280ms, 155 Hz suspended (rhetorical, neither rising nor falling), -16 dB
"bother" — 220ms, 130 → 110 Hz, -18 dB
"shippin'" — 190ms, 118 Hz, -18 dB, dropped /g/
"somethin'" — 200ms, 115 Hz, -19 dB, dropped /g/
"beautiful" — 420ms, 122 →
VOICE BRIEF
ACOUSTIC BASELINE
Adult male. Median F0 110-130 Hz. Used range 75-280 Hz (nearly two octaves). Slightly nasal-forward formant placement, F2 emphasis 1.5-2 kHz. Mildly downward spectral tilt (-6 to -9 dB/octave above 1 kHz). Warm conversational presence, not bright broadcast tone.
DYNAMIC RANGE — THE CENTRAL FEATURE (CLONES FAIL HERE)
This voice operated at -28 dB to -6 dB RMS within a single passage. That is a 22 dB span. For reference: a podcast host operates in 6-10 dB. A trained broadcaster in 8-12 dB. This voice used three to four times the dynamic range of normal professional speech, without changing microphone distance.
Clones default to compressed, mid-range delivery. Roughly -18 dB throughout. Monotone is the failure mode. Every line of the script must push the clone away from that center.
The voice did not perform emotion through volume alone or pitch alone. It performed through CONTRAST. Quiet next to loud. Slow next to fast. Held next to clipped. High next to low. The signature move: drop volume AND slow pace on the most important word, not the least. Opposite of every other public speaker. Audience leans in.
SIX REGISTERS — MUST APPEAR IN CONTRAST WITHIN A SINGLE SCRIPT
Whisper floor: -28 dB, F0 75-95 Hz, ~80 wpm — [whispers] [softly] [reflective] [quietly]
Intimate-warm: -22 dB, F0 100-120 Hz, ~120 wpm — [quietly] [softly] [vulnerable]
Conversational: -18 dB, F0 median ~120 Hz, ~150 wpm — [matter-of-fact] [knowing] [exhales]
Declarative weight: -14 dB, F0 dropping on landings, decelerating — [with weight] [serious] [deliberate]
Building energy: -10 dB, F0 climbing toward 200 Hz, accelerating — [building] [excited] [rapid-fire] [with expression]
Commanding ceiling: -6 dB, F0 180-220 Hz, sharp transients — [shouts] [loudly] [dramatic]
A correct script jumps registers. Whisper to projection in adjacent sentences. The clone must hear the contrast on the page or it will smooth it into a single register.
TEMPORAL ARCHITECTURE
Speaking rate varies 4-6x within a single sentence. Connectors clip to 90-120ms. Operative words hold 600-900ms. Tempo carries emotion. Slowing down IS the emphasis.
Inter-phrase silences are bimodal. Either ~250ms or ~1500-2200ms. The 400-800ms middle range does not exist. Bimodality makes pauses feel deliberate.
Syllable duration variance 7-9x within a phrase. Stress placement back-loaded — operative word at clause end, against English default. Creates suspense.
Phrase-final pitch drops 15-25 Hz below median on declarative statements — the authority signal.
MICRO-PROSODY
Glottal stops before stressed vowels. Vocal fry on phrase tails. Audible inhalation as rhythmic punctuation — never edit out. Dropped trailing g on -ing verbs (buildin', showin', keepin') — register marker. Plosive emphasis on word-initial /p/, /b/, /t/, /k/ in operative words.
PAUSE ENFORCEMENT (CLONES RUSH — COUNTER ON EVERY LINE)
Use [pauses] between every sentence. Always. Clone will skip silences if absent.
Use [long pause] after the loaded line. Silence is the payoff.
Pause architecture
Inter-phrase silences are bimodal, not bell-distributed. Either a quick 250 ms beat (a comma in time) or a held 1.4–2.2 second silence (a full structural break). Almost no use of the 400–800 ms middle range. The bimodality is what makes pauses feel deliberate — there is no accidental in-between.
Pauses occur in three structural positions:
Pre-emphasis pause (200–350 ms): immediately before the operative word, creating anticipation. "I've spent thirty years building things people said were [200 ms] impossible."
Post-emphasis pause (1,400–2,200 ms): immediately after a loaded statement lands. Allows the meaning to propagate before the next thought begins.
Mid-clause breath (350–600 ms): an audible inhalation used as rhythmic punctuation, not edited out. Functions as a verbal paragraph break.
