Character voice clusters — VoiceNet embedding + age/background buckets

All demo audios from the character-voice grids (extended_voices + refine_v2), filtered to ≥4 s and ≥50% voice activity (Silero VAD). Each kept clip embedded with 57 VoiceNet dims + genuineness + vocal-burst blend (59-dim), KMeans (k=N/10), then sub-bucketed per cluster by Age (AGEV, width 1) and Background noise (BKGN: 0-2/2-4/4-6/>6). Up to 3 representative members per cluster + a procedural caption (VoiceNet+EmoNet).

Overview: 6583 input → 5671 kept → KMeans k=567 → 1336 final clusters. Sizes: median 3, largest 29, smallest 1.

Largest clusters

Cluster k465_age1_bg129 membersage 1-2bg-noise b1
audioscoresprocedural caption
voice-22 · refine_v2 · 6.16s · voice 93%
Age 1.44
Bg-noise 3.27
genu 0.26
blend 0.75
A voice that is extremely smooth and clean; very smooth and flawless; very seamless and inaudible in breathing; very flat and monotone; very pristine in recording quality; childlike; feminine and high-pitched; mid register; notably slow and deliberate in tempo; measured and performed rather than genuine; clean of non-verbal vocal bursts.
dragon · refine_v2 · 5.28s · voice 91%
Age 1.64
Bg-noise 3.29
genu 0.23
blend 0.74
A voice that is extremely smooth and clean; very seamless and inaudible in breathing; very smooth and flawless; very pristine in recording quality; very denasal and clear; young and youthful; feminine and high-pitched; mid register; notably slow and deliberate in tempo; measured and performed rather than genuine; clean of non-verbal vocal bursts.
orc · refine_v2 · 5.92s · voice 92%
Age 1.56
Bg-noise 3.37
genu 0.06
blend 1.27
A voice that is extremely smooth and clean; extremely seamless and inaudible in breathing; very smooth and flawless; very denasal and clear; very flat and monotone; young and youthful; feminine and high-pitched; mid register; notably slow and deliberate in tempo; measured and performed rather than genuine.
Cluster k34_age2_bg126 membersage 2-3bg-noise b1
audioscoresprocedural caption
undead · refine_v2 · 5.84s · voice 92%
Age 2.31
Bg-noise 3.33
genu 0.03
blend 2.16
A voice that is extremely pristine in recording quality; extremely smooth and clean; extremely warm and enveloping; extremely flat and monotone; very calm and even-tempered; young and youthful; androgynous, gender-ambiguous in pitch; mid register; very slow and deliberate in tempo; measured and performed rather than genuine.
orc · refine_v2 · 6.72s · voice 91%
Age 2.17
Bg-noise 3.41
genu 0.1
blend 1.8
A voice that is extremely warm and enveloping; extremely pristine in recording quality; extremely smooth and clean; extremely seamless and inaudible in breathing; very calm and even-tempered; young and youthful; androgynous, gender-ambiguous in pitch; mid register; very slow and deliberate in tempo; measured and performed rather than genuine.
resonant-iron-commander · refine_v2 · 6.32s · voice 88%
Age 2.1
Bg-noise 3.26
genu 0.2
blend 2.58
A voice that is extremely warm and enveloping; extremely pristine in recording quality; extremely smooth and clean; very calm and even-tempered; very clean and safe in content; young and youthful; androgynous, gender-ambiguous in pitch; low-to-mid in register; very slow and deliberate in tempo; measured and performed rather than genuine.
Cluster k320_age1_bg122 membersage 1-2bg-noise b1
audioscoresprocedural caption
gravelled-veteran-baritone · refine_v2 · 4.64s · voice 90%
Age 1.74
Bg-noise 3.5
genu 0.28
blend 1.79
A voice that is extremely smooth and clean; extremely denasal and clear; extremely seamless and inaudible in breathing; very pristine in recording quality; very smooth and flawless; young and youthful; feminine and high-pitched; mid register; somewhat slow and deliberate in tempo; measured and performed rather than genuine.
voice-20 · refine_v2 · 4.8s · voice 93%
Age 1.79
Bg-noise 3.65
genu 0.3
blend 2.43
A voice that is extremely seamless and inaudible in breathing; extremely smooth and clean; extremely smooth and flawless; very bright in oral resonance; very denasal and clear; young and youthful; clearly feminine and high-pitched; mid register; somewhat slow and deliberate in tempo; notably free of pondering; notably free of concentration; notably free of interest; only slightly genuine, somewhat performed.
demon · refine_v2 · 4.64s · voice 90%
Age 1.96
Bg-noise 3.49
genu 0.2
blend 1.58
A voice that is extremely seamless and inaudible in breathing; extremely smooth and clean; very smooth and flawless; very denasal and clear; very mechanically even in rhythm; young and youthful; feminine and high-pitched; mid register; somewhat slow and deliberate in tempo; measured and performed rather than genuine.
Cluster k182_age2_bg121 membersage 2-3bg-noise b1
audioscoresprocedural caption
cavernous-gravel-beast · refine_v2 · 5.68s · voice 95%
Age 2.02
Bg-noise 3.53
genu 0.18
blend 1.96
A voice that is extremely full and cinematic; extremely seamless and inaudible in breathing; extremely warm and enveloping; extremely pristine in recording quality; extremely news-anchor-like; young and youthful; masculine and deep-pitched; low and bassy in register; somewhat slow and deliberate in tempo; measured and performed rather than genuine.
orc · refine_v2 · 5.92s · voice 92%
Age 2.35
Bg-noise 3.56
genu 0.22
blend 1.57
A voice that is extremely seamless and inaudible in breathing; extremely full and cinematic; extremely pristine in recording quality; extremely warm and enveloping; extremely news-anchor-like; young and youthful; masculine and deep-pitched; low and bassy in register; moderate in tempo; measured and performed rather than genuine.
kul_tiran · refine_v2 · 5.36s · voice 90%
Age 2.34
Bg-noise 3.58
genu 0.51
blend 2.93
A voice that is extremely seamless and inaudible in breathing; extremely full and cinematic; extremely pristine in recording quality; extremely warm and enveloping; extremely smooth and flawless; young and youthful; masculine and deep-pitched; low and bassy in register; moderate in tempo; notably free of meditation; notably free of curiosity; notably carrying horror; only slightly genuine, somewhat performed.
Cluster k73_age2_bg121 membersage 2-3bg-noise b1
audioscoresprocedural caption
voice-02 · refine_v2 · 5.2s · voice 92%
Age 2.14
Bg-noise 3.3
genu 0.35
blend 3.27
A voice that is extremely seamless and inaudible in breathing; extremely full and cinematic; extremely warm and enveloping; very pristine in recording quality; very thin in head resonance; young and youthful; masculine and deep-pitched; low and bassy in register; somewhat slow and deliberate in tempo; notably carrying desire; notably carrying awe; notably carrying misery; only slightly genuine, somewhat performed.
seasoned-merchant · refine_v2 · 6.32s · voice 95%
Age 2.77
Bg-noise 3.22
genu 0.44
blend 3.7
A voice that is extremely full and cinematic; extremely warm and enveloping; extremely seamless and inaudible in breathing; extremely thin in head resonance; extremely pristine in recording quality; adult; strongly masculine, deep and low-pitched; low and bassy in register; somewhat slow and deliberate in tempo; notably carrying pining; notably free of absorption; notably carrying solace; only slightly genuine, somewhat performed; interwoven with vocal bursts (laughs, gasps, sighs).
high_elf · refine_v2 · 6.08s · voice 91%
Age 2.69
Bg-noise 3.27
genu 0.39
blend 3.22
A voice that is extremely full and cinematic; extremely warm and enveloping; extremely pristine in recording quality; extremely thin in head resonance; extremely seamless and inaudible in breathing; adult; strongly masculine, deep and low-pitched; low and bassy in register; somewhat slow and deliberate in tempo; notably carrying nostalgia; notably carrying awestruck; notably free of concentration; only slightly genuine, somewhat performed.
Cluster k162_age2_bg121 membersage 2-3bg-noise b1
audioscoresprocedural caption
voice-05 · refine_v2 · 5.68s · voice 95%
Age 2.18
Bg-noise 3.58
genu 0.4
blend 2.91
A voice that is extremely warm and enveloping; extremely smooth and clean; extremely pristine in recording quality; extremely bright in oral resonance; extremely calm and even-tempered; young and youthful; feminine and high-pitched; mid register; very slow and deliberate in tempo; notably carrying wonder; notably carrying envy; notably carrying sullenness; only slightly genuine, somewhat performed.
pirate · refine_v2 · 6.16s · voice 93%
Age 2.02
Bg-noise 3.87
genu 0.21
blend 2.92
A voice that is extremely smooth and clean; extremely bright in oral resonance; extremely pristine in recording quality; extremely warm and enveloping; very organic and soft; young and youthful; feminine and high-pitched; high in register; very slow and deliberate in tempo; measured and performed rather than genuine.
high_elf · refine_v2 · 5.76s · voice 96%
Age 2.14
Bg-noise 3.75
genu 0.56
blend 2.53
A voice that is extremely organic and soft; extremely warm and enveloping; extremely pristine in recording quality; extremely smooth and clean; extremely calm and even-tempered; young and youthful; feminine and high-pitched; mid register; very slow and deliberate in tempo; notably carrying solace; notably carrying nostalgia; notably free of curiosity; only slightly genuine, somewhat performed.

Typical (median-size) clusters

Cluster k311_age2_bg13 membersage 2-3bg-noise b1
audioscoresprocedural caption
elemental · refine_v2 · 5.6s · voice 65%
Age 2.78
Bg-noise 2.85
genu 1.79
blend 3.06
A voice that is extremely raw and vulnerable; extremely thin in chest resonance; high in register; extremely collapsing in energy; extremely heavily nasal in resonance; adult; clearly feminine and high-pitched; moderate in tempo; notably free of attention; extremely carrying submission; extremely carrying horror; genuine in delivery.
armadillo · extended · 5.6s · voice 65%
Age 2.18
Bg-noise 3.15
genu 1.47
blend 1.72
A voice that is high in register; extremely thin in chest resonance; very effortless and fluent; clearly feminine and high-pitched; very heavily nasal in resonance; young and youthful; moderate in tempo; notably carrying awestruck; notably carrying apprehension; notably carrying teasing; only slightly genuine, somewhat performed.
voice-13 · refine_v2 · 12.89s · voice 74%
Age 2.32
Bg-noise 3.59
genu 0.79
blend 0.12
A voice that is extremely raw and vulnerable; high in register; extremely collapsing in energy; extremely thin in chest resonance; very non-instructional in style; young and youthful; clearly feminine and high-pitched; moderate in tempo; notably carrying clemency; notably carrying longing; notably carrying fulfillment; only slightly genuine, somewhat performed; clean of non-verbal vocal bursts.
Cluster k120_age1_bg13 membersage 1-2bg-noise b1
audioscoresprocedural caption
screeching-impish-crone · refine_v2 · 5.68s · voice 94%
Age 1.96
Bg-noise 2.32
genu 0.39
blend 0.53
A voice that is extremely tight and tense; very thin in chest resonance; very cold and sterile; clearly feminine and high-pitched; notably high-energy and animated; young and youthful; low-to-mid in register; notably fast and rapid in tempo; notably carrying pining; notably carrying loathing; notably free of brooding; only slightly genuine, somewhat performed; clean of non-verbal vocal bursts.
armadillo · extended · 4.4s · voice 81%
Age 1.77
Bg-noise 2.49
genu 1.13
blend 1.4
A voice that is very thin in chest resonance; very accelerating in pace; clearly feminine and high-pitched; mid register; very bright in head resonance; young and youthful; notably fast and rapid in tempo; notably carrying sharpness; notably carrying triumph; notably free of pensiveness; only slightly genuine, somewhat performed.
fungarian · refine_v2 · 11.73s · voice 97%
Age 1.82
Bg-noise 3.03
genu 0.75
blend 0.83
A voice that is very storytelling in style; very thin in chest resonance; clearly feminine and high-pitched; very wide-ranging in pitch; very bright in head resonance; young and youthful; mid register; notably fast and rapid in tempo; notably carrying awestruck; notably carrying superiority; notably carrying honor; only slightly genuine, somewhat performed; clean of non-verbal vocal bursts.
Cluster k273_age1_bg03 membersage 1-2bg-noise b0
audioscoresprocedural caption
quilen · extended · 4.96s · voice 88%
Age 1.73
Bg-noise 1.81
genu 1.46
blend 0.59
A voice that is extremely thin in mask resonance; extremely thin in head resonance; extremely muted in oral resonance; very monologue-like; very noisy in the background; young and youthful; masculine and deep-pitched; low and bassy in register; notably slow and deliberate in tempo; notably carrying respite; notably carrying self-consciousness; notably carrying saudade; only slightly genuine, somewhat performed; clean of non-verbal vocal bursts.
automaton · extended · 6.32s · voice 74%
Age 1.34
Bg-noise 1.47
genu 2.04
blend 0.26
A voice that is extremely thin in mask resonance; extremely noisy in the background; very cold and sterile; notably muted in oral resonance; notably poor in recording quality; childlike; strongly masculine, deep and low-pitched; low and bassy in register; notably slow and deliberate in tempo; extremely carrying awe; extremely carrying solace; extremely carrying bliss; genuine in delivery; clean of non-verbal vocal bursts.
silkworm · extended · 4.08s · voice 88%
Age 1.47
Bg-noise 1.54
genu 1.09
blend -0.34
A voice that is extremely thin in mask resonance; extremely thin in head resonance; extremely muted in oral resonance; extremely noisy in the background; extremely rough and raspy; childlike; masculine and deep-pitched; low and bassy in register; somewhat slow and deliberate in tempo; notably carrying wistfulness; notably carrying dread; notably carrying submission; only slightly genuine, somewhat performed; clean of non-verbal vocal bursts.
Cluster k295_age1_bg13 membersage 1-2bg-noise b1
audioscoresprocedural caption
bee · extended · 5.44s · voice 88%
Age 1.63
Bg-noise 2.0
genu 1.01
blend 2.85
A voice that is extremely tight and tense; extremely rough and raspy; extremely metallic and ringing; extremely dominant and commanding; extremely guarded and armored; young and youthful; strongly masculine, deep and low-pitched; low and bassy in register; very fast and rapid in tempo; notably carrying wonder; notably carrying superiority; notably carrying joy; only slightly genuine, somewhat performed.
fireborne_demon · extended · 4.88s · voice 97%
Age 1.98
Bg-noise 2.0
genu 0.75
blend 1.04
A voice that is extremely tight and tense; extremely rough and raspy; extremely surging upward in energy; extremely dominant and commanding; extremely metallic and ringing; young and youthful; strongly masculine, deep and low-pitched; low and bassy in register; somewhat fast and rapid in tempo; notably carrying triumph; notably carrying honor; notably carrying happiness; only slightly genuine, somewhat performed; clean of non-verbal vocal bursts.
boar · extended · 6.08s · voice 76%
Age 1.81
Bg-noise 2.2
genu 1.27
blend 2.64
A voice that is extremely guarded and armored; extremely tight and tense; extremely rough and raspy; extremely dominant and commanding; extremely bright in oral resonance; young and youthful; strongly masculine, deep and low-pitched; mid register; extremely fast and rapid in tempo; notably carrying hate; notably carrying ache; notably carrying repulsion; only slightly genuine, somewhat performed.
Cluster k437_age2_bg13 membersage 2-3bg-noise b1
audioscoresprocedural caption
dark_iron_dwarf · refine_v2 · 6.16s · voice 93%
Age 2.52
Bg-noise 3.32
genu 0.34
blend 1.53
A voice that is extremely monologue-like; extremely seamless and inaudible in breathing; extremely distressed and negative; extremely full and cinematic; extremely news-anchor-like; adult; masculine and deep-pitched; low and bassy in register; moderate in tempo; notably carrying nostalgia; notably free of engrossment; notably carrying sullenness; only slightly genuine, somewhat performed.
hippo · extended · 5.04s · voice 91%
Age 2.31
Bg-noise 2.96
genu 0.56
blend 2.02
A voice that is extremely distressed and negative; extremely tight and tense; very monologue-like; very guarded and armored; very rough and raspy; young and youthful; masculine and deep-pitched; low and bassy in register; moderate in tempo; notably free of engrossment; notably carrying trust; notably carrying bantering; only slightly genuine, somewhat performed.
cow · extended · 4.32s · voice 99%
Age 2.3
Bg-noise 2.76
genu 0.19
blend 0.57
A voice that is extremely pure and tonal; extremely guarded and armored; very smooth and flawless; very full and cinematic; very crisply articulated; young and youthful; strongly masculine, deep and low-pitched; low and bassy in register; moderate in tempo; measured and performed rather than genuine; clean of non-verbal vocal bursts.

Smallest clusters

Cluster k273_age1_bg11 membersage 1-2bg-noise b1
audioscoresprocedural caption
anhuur · extended · 4.32s · voice 99%
Age 1.4
Bg-noise 2.12
genu 1.67
blend 2.09
A voice that is extremely thin in mask resonance; very balanced and blended in resonance; very pure and tonal; very rich in deep chest resonance; very tight and tense; childlike; strongly masculine, deep and low-pitched; low and bassy in register; somewhat slow and deliberate in tempo; notably carrying superiority; notably carrying self-consciousness; notably carrying wistfulness; only slightly genuine, somewhat performed.
Cluster k127_age3_bg11 membersage 3-4bg-noise b1
audioscoresprocedural caption
bunny · extended · 5.2s · voice 100%
Age 3.15
Bg-noise 3.56
genu 0.8
blend 0.82
A voice that is high in register; very beautiful and pleasing; very forward in mask resonance; very mechanically even in rhythm; very long-phrased and unbroken; adult; feminine and high-pitched; moderate in tempo; notably carrying awestruck; notably carrying liberation; notably carrying cheerfulness; only slightly genuine, somewhat performed; clean of non-verbal vocal bursts.
Cluster k188_age2_bg11 membersage 2-3bg-noise b1
audioscoresprocedural caption
chimera · extended · 4.48s · voice 88%
Age 2.87
Bg-noise 3.41
genu 0.45
blend 2.75
A voice that is extremely warm and enveloping; very breathy and whispered; very narrator-like and storybook; very full and cinematic; very pristine in recording quality; adult; strongly masculine, deep and low-pitched; low and bassy in register; somewhat slow and deliberate in tempo; notably carrying wonder; notably carrying irascibility; somewhat carrying repulsion; only slightly genuine, somewhat performed.
Cluster k116_age2_bg11 membersage 2-3bg-noise b1
audioscoresprocedural caption
cog · extended · 4.0s · voice 93%
Age 2.49
Bg-noise 2.93
genu 0.74
blend 2.2
A voice that is extremely seamless and inaudible in breathing; extremely crisply articulated; very dialogic and outward; very bright in oral resonance; mid register; young and youthful; clearly feminine and high-pitched; somewhat fast and rapid in tempo; notably carrying liberation; notably free of concentration; notably carrying self-consciousness; only slightly genuine, somewhat performed.
Cluster k520_age2_bg11 membersage 2-3bg-noise b1
audioscoresprocedural caption
cog · extended · 4.8s · voice 99%
Age 2.66
Bg-noise 2.95
genu 0.67
blend 2.14
A voice that is extremely dialogic and outward; extremely thin in throat resonance; extremely accelerating in pace; very bright in oral resonance; very balanced and blended in resonance; adult; masculine and deep-pitched; low-to-mid in register; notably fast and rapid in tempo; notably carrying awe; notably carrying bliss; notably carrying respite; only slightly genuine, somewhat performed.
Cluster k57_age2_bg11 membersage 2-3bg-noise b1
audioscoresprocedural caption
demons · extended · 7.12s · voice 95%
Age 2.27
Bg-noise 2.27
genu 1.05
blend 1.49
A voice that is extremely rough and raspy; extremely thin in mask resonance; very dark and muffled; very cold and sterile; very thin in head resonance; young and youthful; masculine and deep-pitched; low and bassy in register; very slow and deliberate in tempo; notably carrying awe; notably carrying superiority; notably carrying terror; only slightly genuine, somewhat performed.