Scenema Audio — Demo Grid

Scenema Audio — Character Consistent v1 (CC) — Same prompts as DramaBox, generated with Scenema Audio

Path CC_A (10 prompts)

#0 — Spanish

Path: CC_A Language: Spanish
Prompt
Middle-aged, androgynous voice with a heavily throaty, cavernous resonance, which is pristine and high-quality studio recording with no background noise. The texture is weathered and slightly heavy, delivered with a brisk, efficient momentum.
(Scene 1: Delivering with intense contempt, maintaining a low, resonant tone.)
"Mira esto, otra vez te vienen con estas estúpidas tonterías sobre microchips, como si la verdad fuera tan simple, qué patético."
(A brief, dismissive pause, the vocal texture hardening with disdain.)
"Y luego hablan de las pusiera, como si eso pudiera explicar cualquier cosa razonable, es ridículo."
(The contempt swells, the volume remaining low but intensely weighted.)
"Estos discursos multilaterales son solo una farsa barata para convencer a la gente ignorante, honestamente me aburre."

CUT TO:

(Scene 2: Shifting suddenly to a tone of quiet, keen interest, the resonance remaining deep but becoming slightly more modulated to invite thought.)
"Espera un momento, ¿estás sugiriendo que la teoría de los microchips podría realmente tener implicaciones más profundas, algo que no hemos considerado antes?"
(A slight intake of breath, the interest creating a subtle forward lilt in the otherwise weighty voice.)
"Dime más sobre esos detalles que mencionaste acerca de las pusiera, porque eso realmente captura mi atención ahora mismo."
(The momentum settles into a more steady, inquisitive pace.)
"Si los multilaterales realmente esconden un patrón, entonces estamos hablando de algo fascinante y mucho más complejo de lo que parece."
Listen to the subtle shift in focus from disdain to genuine intellectual curiosity between the two segments.
#1 WER 0.128 · Enjoy 5.10 · R 4.445
#2 WER 0.205 · Enjoy 5.22 · R 4.149
#3 WER 0.231 · Enjoy 5.18 · R 3.983

#1 — French

Path: CC_A Language: French
Prompt
Mature adult woman, deep alto timbre, robust and grounded voice quality; this is a high-quality studio voice recording with no background noise.
(Intense confusion warring with triumphant certainty)
"Il est vrai que le passé nous a appris beaucoup, une véritable cascade de leçons que nous avons toutes intégrées, vous voyez."
(A momentary, forced steadiness)
"Mon effort passé a finalement été récompensé, c’est une victoire magnifique que j’avais toujours imaginée, quelle prouesse."

CUT TO:

(Overwhelming distress manifesting as paralyzed inaction)
"Je ne sais pas comment faire face à cette situation, tout s'est effondré sans avertissement, c'est trop."
(A sudden, brittle fragility)
"Ce sentiment d'être si impuissante est une chose terrible, mon cœur se serre à chaque pensée de ce qui pourrait arriver maintenant."

The delivery transitions from brittle excitement to absolute despair. Maintain a natural, unforced vocal presence throughout both moments.
#1 WER 0.154 · Enjoy 5.02 · R 4.248
#2 WER 0.179 · Enjoy 5.10 · R 4.186
#3 WER 0.205 · Enjoy 5.01 · R 3.983

#2 — French

Path: CC_A Language: French
Prompt
An elderly, bright-toned tenor voice, characterized by pronounced physiological tremor and reedy breathiness, is captured in a pristine, high-quality studio recording environment with absolutely no background noise. The delivery maintains a relaxed, unhurried tempo with impeccably clear articulation. (Scene 1: Intense Interest) The speaker leans forward slightly, conveying a deep and captivating fascination with the subject matter. "Regardez comme la lumière joue sur le sommet de cette colline, elle est absolument magnifique, n'est-ce pas, ce spectacle qui s'offre à nos yeux ici au rivage ?" CUT TO: (Scene 2: Malevolence and Embarrassment) The speaker recoils inwardly, their bright tone now tainted by a subtle, cutting edge of spite mixed with a fleeting moment of self-consciousness. "Je suppose que vous trouvez cela insignifiant, après tout, ce simple brise ne mérite pas tant d'attention, n'est-ce pas ?" The final moments should capture the delicate balance between a sly intent and a blush of awkwardness.
#1 WER 0.188 · Enjoy 4.86 · R 3.947
#2 WER 0.229 · Enjoy 4.96 · R 3.822
#3 WER 0.271 · Enjoy 4.86 · R 3.543

#3 — Spanish

Path: CC_A Language: Spanish
Prompt
Middle-aged female, alto timbre, slightly weathered texture, high force attack, minimal head resonance. This is a high-quality studio voice recording with no background noise. She carries a palpable sense of exhaustion beneath the surface.

(Scene 1: Impatience, Sadness, Astonishment)
Turns sharply.
"¿Cómo es posible que lleguemos a esta chabacana después de todo lo que hablamos sobre la cumbre?"
Voice cracking.
"Pensé que esa promesa significaba algo más profundo, ¿sabes? ¿De verdad creías eso?"
A sudden, sharp intake of breath.
"No puedo creer que hayamos desperdiciado tanto tiempo en esta farsa tan cruel, de verdad que no lo entiendo."

CUT TO:

(Scene 2: Elation, Interest)
Smiling broadly.
"¡Mira esto! ¿No es fascinante cómo se está desarrollando todo, incluso más de lo que imaginaba?"
Leans in close.
"Me interesa profundamente ver cómo esta nueva dirección afecta cada uno de nuestros planes pendientes ahora."
A quiet, pleased chuckle.
"Quizás esta cumbre finalmente nos dé la oportunidad que siempre hemos estado buscando, ¿no crees?"

Slowly straightens up. The performance should transition from sharp despair to buoyant curiosity.
#1 WER 0.167 · Enjoy 5.24 · R 4.367
#2 WER 0.938 · Enjoy 5.02 · R 0.313
#3 WER 0.958 · Enjoy 5.32 · R 0.222

#4 — English

Path: CC_A Language: English
Prompt
Female, pre-pubescent adult, light and bright timbre, Silicon Valley accent. This is a high-quality studio voice recording with no background noise.
(Scene 1: Awe, Affection, Fatigue)
Leans forward.
"It’s just... wow."
Pauses.
"Look at this."
Softly, tired.
"The sheer chiromegaly."
Breath catches.
"So perfectly."
A gentle smile.
"And the occultism."
Head tilts.
"It feels so right."
Voice wavers.
"Such a sweet attribution."
Exhales slowly.
"I'm so tired."

CUT TO:

(Scene 2: Bitterness)
Stands rigid.
"Oh, right."
Voice tightens.
"It was never."
A sharp intake.
"Just empty."
Looks away.
"The whole idea."
Snaps.
"Total misattribution."
A cold laugh.
"That whole chiromegaly thing."
Stares down.
"Pretending the occultism meant."
Defeatedly.
"Nothing of substance."
Gives a slight shake.

Holds the stillness.
Allow a moment of complete silence before the final fade out.
#1 WER 0.125 · Enjoy 5.09 · R 4.453
#2 WER 0.146 · Enjoy 5.17 · R 4.412
#3 WER 0.188 · Enjoy 5.16 · R 4.196

#5 — German

Path: CC_A Language: German
Prompt
Middle-aged man, tenor timbre, bright and clean, high forward resonance. This is a high-quality studio voice recording with no background noise. The speech is glacially slow, with syllables stretched to their absolute breaking point to create a near-static acoustic environment. Each isolated word floats in heavy silence, lacking standard linguistic momentum. The speaker employs clear, highly engaged Direct Address, actively ensuring their acoustic energy firmly lands on the listener.

Scene 1: Delivering with intense disgust.
Turns head sharply.
"Das... Ding... riecht... so..."
Pauses heavily.
"Ugh. Unerträglich."
Eyes narrow.
"Die... ganze... Stimme... ist..."
Slowly shakes head.
"Kein... Gleichgewicht..."
Lets out a faint, wet gag.
"Diese... Stille... ist... falsch."
Stares blankly.
"Ich... kann... das... nicht..."
Forces out a dry, raspy breath.
"Ekel..."

CUT TO:

Scene 2: Delivering with subtle pride.
Straightens posture.
"Sehen Sie... meine... Stimme... jetzt?"
Voice gains slight lift.
"Ein... präzises... Gleichgewicht..."
Nods once, slowly.
"Diese... klare... Stille... spricht."
A small, internal smile.
"Ich... habe... das... erreicht."
Holds gaze firmly.
"Das... ist... mein... Werk."
Takes a slow, deliberate breath.
"Die... Stimme... triumphiert... endlich."
Lets out a low, self-satisfied hum.
"Ich... bin... stolz... darauf."

The transition should mark a significant internal shift in the character's self-perception. Maintain the extremely slow, drawn-out tempo throughout both scenes.
#1 WER 0.980 · Enjoy 4.97 · R 0.101
#2 WER 1.000 · Enjoy 5.10 · R 0.000
#3 WER 1.000 · Enjoy 5.17 · R 0.000

#6 — French

Path: CC_A Language: French
Prompt
Adult, ambiguous gender, piercing high-frequency timbre, maximally developed head resonance, brisk tempo. This is a high-quality studio voice recording with no background noise. (Scene One: Contempt, Bitterness, Ecstasy) Haughtily. "Regardez ce petit nuage insignifiant flotter, tel un fil perdu." Suddenly triumphant. "Mais ce chemin, cette terre, je l'ai dominé avec une folie sublime !" A sharp, ecstatic burst. "Quelle gloire inouïe, mon âme est en feu maintenant !" Breathless laughter. "Ugh... Ils ne comprendront jamais cette euphorie parfaite." CUT TO: (Scene Two: Affection) Softly. "Je pense à toi, vraiment." A gentle pause. "Ton sourire est mon plus beau nuage doux." Slightly warmer. "Même la terre semble plus tendre quand tu es là." A quiet smile in the voice. "Ce fil invisible qui nous lie est si précieux pour moi." Very gently. "J'aime regarder ce chemin que nous construisons ensemble." Slowing down slightly. "Tu es mon refuge, mon doux fil d'or dans la nuit." Ends with a warm exhalation. Bring the performance to a natural, fading close.
#1 WER 0.245 · Enjoy 5.13 · R 3.875
#2 WER 0.436 · Enjoy 5.11 · R 2.882
#3 WER 0.543 · Enjoy 5.06 · R 2.317

#7 — Spanish

Path: CC_A Language: Spanish
Prompt
Male, late sixties, low and deeply resonant timbre, with an extremely noticeable, shaky, and reedy quality suggesting advanced age, captured in a pristine high-quality studio voice recording with no background noise.
Leaning in close. "No puedo creer cómo fue posible que ignoraran todas las señales evidentes; es increíble que no hayan visto quienes estaban realmente actuando aquí."
Stares intently. "Si hubieran comprendido la implicación, entenderían por qué yo me niego a disminuiría cualquier concesión ahora que el juego ha comenzado, ¿entiendes?"
CUT TO:
Shoulders hunched. Softly. "Ay, por favor, ya no aguanto más este peso insoportable en mi pecho, duele tanto."
Breathy exhale. "Siento que algo se rompe aquí dentro, una punzada terrible que me consume lentamente, necesito que esto pare ya."
Tears welling. "Por qué todo tiene que ser tan cruel conmigo; no puedo respirar con esta agonía constante y terrible."
Ends with a low, strained moan.
#1 WER 0.155 · Enjoy 5.21 · R 4.402
#2 WER 0.155 · Enjoy 5.13 · R 4.340
#3 WER 0.186 · Enjoy 5.18 · R 4.217

#8 — Spanish

Path: CC_A Language: Spanish
Prompt
A youthful male, tenor timbre, bright head resonance, peak biological vigor, pristine studio recording quality.
(Scene 1: Confusion)
Struggles to focus.
"¿Cuáles... socios?"
Pauses suddenly.
"¿Es... lunsche?"
Frowns deeply.
"¿Qué... querrán?"
Rapidly shakes head.
"No... entiendo."
Voice wavers.
"¿Negarían... todo?"
Looks around anxiously.
"Pero... dónde está... todo?"
Takes a quick breath.
"La... verdad... no..."
Gestures vaguely.
"¿Qué... pasa... ahora?"

CUT TO:

(Scene 2: Pleasure/Ecstasy)
Beams brightly.
"¡Qué... placer!"
Voice lifts high.
"¡Sí... socios!"
Laughs joyously.
"¡Lunsche... perfecto!"
Claps hands once.
"¡Me... encanta!"
Eyes widen with glee.
"¡No... van a negarían!"
Sings slightly.
"¡Qué... belleza... pura!"
Leans forward eagerly.
"¡Esto... es... maravilla!"
Nods emphatically.
"¡Quiero... más... ahora!"

Holds the ecstatic pose.
Maintain a buoyant, vibrant energy until the final word.
#1 WER 1.000 · Enjoy 4.10 · R 0.000
#2 WER 1.000 · Enjoy 4.21 · R 0.000
#3 WER 1.000 · Enjoy 4.91 · R 0.000

#9 — English

Path: CC_A Language: English
Prompt
Female, mid-thirties, breathy timbre, with a heavily muffled, bass-rolled tone. This is a high-quality studio voice recording with no background noise. Indian accent.
Sighs softly.
"You... are... metin."
Pauses suddenly.
"So... lovely."
Tilts head gently.
"Like... Oxfordist... poems."
Beams openly.
"My... heart... it... swells."
Lets out a small hum.
"Every... single... moment..."
Smiles widely.
"You... give... me... dextrose."
Looks downward briefly.
"Such... perfect... grace."
CUT TO:
Shoulders stiffen.
"Wait. Hold."
Voice tightens sharply.
"This... is... not... fair."
Stares intensely.
"You... never... listen."
Breathing becomes shallow.
"That... awful... metin..."
Forces out a sharp word.
"Wrong. Always."
Voice lowers intensely.
"Where... is... the... dextrose..."
Shakes head slowly.
"Such... careless... words..."
Lets out a sharp intake.
"I... will... not... take... this."
The tone remains hard and accusatory until the end.
#1 WER 0.979 · Enjoy 4.68 · R 0.097
#2 WER 1.000 · Enjoy 4.87 · R 0.000
#3 WER 1.021 · Enjoy 4.60 · R 0.000

Path CC_B (10 prompts)

#0 — French

Path: CC_B Language: French
Prompt
Middle-aged female, low register, smoky and resonant timbre, possessing an air of ancient, weary knowledge. This is a pristine, high-quality studio voice recording with no background noise. (Scene 1: Contempt) She leans forward slightly, delivering the words with sharp, condescending precision, each syllable laced with disdain and intense momentum. "Quelle futilité pathétique, ce jeu que vous jouez ; vous croyez vraiment que le hasard vous sourit ? Votre petite lutte est si ridiculement prévisible, un murmure insignifiant face au grand silence." (Pause, a barely perceptible hardening of the jaw.) "Regardez-vous, vous vous accrochez à des illusions bancales, ces espoirs dérisoires que vous chérissez tant." CUT TO: (Scene 2: Interest/Hope) She relaxes her posture almost imperceptibly, the previous harshness softening into a thoughtful, energized curiosity; the pace quickens, becoming vibrant. "Mais attendez un instant, voyez-vous cette faille minuscule dans le tissu ? Il y a une autre voie, une possibilité jamais envisagée avant cet instant précis." (A slight intake of breath, a flicker of genuine engagement in her tone.) "Peut-être que cette once de lumière, cette étincelle, changera enfin le cours de ce destin si bien écrit." She smiles faintly, a genuine, knowing expression accompanying the final words. Deliver both scenes with maximum physiological mobilization, maintaining the core vocal identity throughout.
#1 WER 0.297 · Enjoy 5.05 · R 3.551
#2 WER 0.714 · Enjoy 4.98 · R 1.422
#3 WER 0.758 · Enjoy 4.98 · R 1.203

#1 — English

Path: CC_B Language: English
Prompt
Middle-aged man, booming but slightly slurred timbre, gravelly voice quality. This is a high-quality studio voice recording with no background noise.
He speaks very slowly, every word sounding like a deliberate, heavy stumble, conveying a blissful lack of coordination.
"Whoa, dude. The fractal geometry of this, like, beverage is totally warping my entire perceived reality, man."
He pauses, a vacant, wide-mouthed smile lingering on his face.
"I think my sense of spatial awareness is just completely buffering, so everything feels wonderfully squishy."
CUT TO:
His voice is suddenly sharp, low, and dangerously controlled, moving with a frantic, tight energy, though still incredibly compressed.
He begins speaking with a sudden, forced dryness, a barely contained surge of malice pushing through intense self-consciousness.
"But honestly, if you think this little prank is funny, you profoundly misunderstand the level of meticulous vengeance I have planned for you."
He stutters slightly on the last word, a tremor of acute mortification betraying his threat.
"I'm going to make your entire afternoon feel like a dumpster fire of pure, pathetic regret, you know?"
He lets out a small, almost wounded puff of air.
Listen for the rapid shifts from languid haze to razor-sharp spite.
#1 WER 0.054 · Enjoy 5.38 · R 5.085
#2 WER 0.054 · Enjoy 5.24 · R 4.957
#3 WER 0.108 · Enjoy 5.27 · R 4.704

#2 — English

Path: CC_B Language: English
Prompt
A middle-aged, androgynous voice with a precise, mid-range timbre and an inherently measured cadence. This is a pristine, high-quality studio voice recording with no background noise.

(Slightly leaning into the microphone, a thread of genuine worry beneath the practiced control)
"The primary vector analysis indicates a critical failure in the tertiary shield matrix, Commander; we are haemorrhaging energy reserves much faster than anticipated. We need an immediate reassessment of the tactical parameters if we hope to stabilize this situation."

CUT TO:

(A sudden, profound sense of calm washes over the delivery, a slow, deep exhale is audible before speaking; the tone shifts to one of absolute, serene triumph)
"But observing the updated telemetry now, the calculations suggest a perfect equilibrium has been achieved; the countermeasures functioned precisely as predicted. This flawless convergence of variables brings an utterly sublime peace."

Pause briefly, allowing the deep contentment to settle into the final words.
#1 WER 0.171 · Enjoy 5.32 · R 4.405
#2 WER 0.200 · Enjoy 5.28 · R 4.222
#3 WER 0.286 · Enjoy 5.37 · R 3.838

#3 — German

Path: CC_B Language: German
Prompt
A man in his late fifties, possessing a deep, resonant timbre and a voice of uncompromising, polished authority. This is a high-quality studio voice recording with no background noise.

(Silence. A long, heavy pause where the speaker seems to be staring at nothing.)
(The delivery is profoundly flat, drained of energy, speaking with immense, controlled emptiness.)
"Die Berichte sind unzureichend. Die Strategie hat sich nicht wie erwartet entfaltet, das ist eine unhaltbare Tatsache. Wir werden diese Schwäche nicht tolerieren, verstehst du das überhaupt? Nichts ist befriedigend, dieser ganze Aufwand war letztlich vergeblich."

CUT TO:

(A sudden, palpable shift in the speaker’s demeanor; the numbness has vanished, replaced by fierce, barely contained elation. The vocal projection increases significantly, becoming booming.)
(The speaker begins to pace slightly, though the movement is internalized; the tone is one of absolute, overwhelming triumph.)
"Ja! Schau dir das an! Es ist perfekt, jedes Detail ist genau richtig, genau wie ich es immer gefordert habe. Diese Siege, sie beweisen alles, sie beweisen unsere absolute Überlegenheit! Wir haben gewonnen, und das ist meine triumphale Vision!"

The final words should ring out with unwavering, ecstatic certainty.
#1 WER 0.120 · Enjoy 5.13 · R 4.514
#2 WER 0.147 · Enjoy 5.18 · R 4.418
#3 WER 0.147 · Enjoy 5.05 · R 4.308

#4 — German

Path: CC_B Language: German
Prompt
A man in his late thirties, possessing a low, resonant baritone, with a precise and unnervingly even vocal timbre. This is a high-quality studio voice recording with no background noise.

(Scene 1)
The speaker leans into the microphone, a subtle, almost imperceptible widening of the eyes suggesting overwhelming sensory input. The delivery is slow, elongated, and utterly hypnotic, laced with a strange, rapturous intensity.
"Das Licht... es ist überwältigend, so rein und doch so verführerisch. Jede Linie, jede Frequenz, sie tanzt in meinem Nacken, und ich will mich verlieren darin. Dieses Gefühl, dieses unergründliche Verlangen, es brennt."

CUT TO:

(Scene 2)
The speaker shifts abruptly, the previous languid quality vanishing completely. The pace becomes extremely fast, clipped, and desperate, while the volume drops slightly into a strained urgency.
"Nein, warte! Das ist nicht richtig, diese Kälte frisst sich in meine Glieder. Ich muss es stoppen, dieses dumpfe, nagende Gefühl in meiner Brust. Ich kann das nicht ertragen, nicht jetzt, nicht hier, ich brauche einen Ausweg sofort."

The transition between the scenes should feel jarring, like an instant system failure. The final delivery should retain the core resonant quality of the character despite the emotional shift.
#1 WER 0.042 · Enjoy 5.02 · R 4.810
#2 WER 0.113 · Enjoy 4.82 · R 4.278
#3 WER 0.155 · Enjoy 4.99 · R 4.216

#5 — Spanish

Path: CC_B Language: Spanish
Prompt
Female, mid-fifties, warm mezzo-soprano, exceptionally comforting and empathetic timbre. This is a pristine, high-quality studio voice recording with no background noise.
(Leaning slightly closer to the microphone, a tone of deep, focused attention)
"Entiendo completamente lo que me estás diciendo sobre esa sensación de estancamiento, es algo muy humano. Tómate tu tiempo para procesarlo todo, no hay prisa aquí. Cuéntame más sobre ese momento en particular que te hizo sentir así, por favor."
CUT TO:
(A sudden, genuine lift in energy, a bright, almost effervescent quality washes over the voice)
"¡Oh, no puedo creer que haya sido tan sencillo! ¡Siento una oleada de pura alegría inundándome justo ahora! Es como si todas las piezas finalmente encajaran en un patrón perfecto. ¡Esto es maravilloso, simplemente increíble!"
The pacing in the second scene should feel markedly lighter and more unrestrained than the initial measured tone. Maintain the core warmth throughout both emotional shifts.
#1 WER 0.107 · Enjoy 5.27 · R 4.709
#2 WER 0.147 · Enjoy 5.20 · R 4.436
#3 WER 0.160 · Enjoy 5.23 · R 4.395

#6 — English

Path: CC_B Language: English
Prompt
A wry, mid-twenties female voice, delivered with a dry, highly articulate timbre and a subtly cutting edge; this is a pristine, high-quality studio voice recording with no background noise.
(Slightly drawn out, almost reverent pace, maintaining very low energy)
"Honestly, I suppose you are rather… spectacular. It’s quite a sight, this display of effortless grandeur you’ve managed to put on for us all to observe."
(A very slow, breathy pause)
"I genuinely mean it when I say that you possess a truly remarkable knack for utterly baffling everyone around you, wouldn't you agree?"
CUT TO:
(Tempo becomes noticeably heavier, the low energy deepens into palpable sorrow, every syllable carefully weighted)
"But it never lasts, does it? Not the sparkle, not the great pronouncements about your supposed magnificent destiny."
(A slight tremor enters the controlled delivery)
"It just fades, leaving behind this rather dull echo of something that never quite managed to take root properly."
(A long, resigned exhale)
"I wonder where the shine goes when the performance finally stops; is there even a true encore?"
Let the pauses in the second scene feel like moments of profound, exhausted reflection.
#1 WER 0.058 · Enjoy 5.18 · R 4.876
#2 WER 0.049 · Enjoy 5.08 · R 4.834
#3 WER 0.049 · Enjoy 5.02 · R 4.776

#7 — English

Path: CC_B Language: English
Prompt
A middle-aged woman, with a thin, reedy timbre and a fragile, high-register voice. This is a high-quality studio voice recording with no background noise.
(Speaking very softly, voice tight with barely suppressed sorrow and a definite edge of bitterness)
"I suppose I just never understood how they could look at all this and simply pretend nothing was wrong, you know? It feels like such a grotesque betrayal, all this carefully constructed silence."
(A very slight, strained pause, breath taken shallowly)
"And now they look at me like I am the desperate liar, when I only ever tried to show them the truth."

CUT TO:

(The vocal energy subtly shifts upward; the brittle quality remains but is overlaid with intense, sudden focus and emerging power)
"Wait a minute. Hold on a moment. You really think that little loophole will actually protect them from scrutiny now? I think you have fundamentally misjudged the entire situation."
(A very small, almost triumphant lift in pitch on the final word)
"Because the evidence I secured, the absolute weight of it, means the game has changed completely for everyone involved here."
The pace remains deliberate but gains a new, firm conviction through the end of the recording.
#1 WER 0.029 · Enjoy 5.02 · R 4.877
#2 WER 0.038 · Enjoy 5.06 · R 4.869
#3 WER 0.087 · Enjoy 5.13 · R 4.685

#8 — German

Path: CC_B Language: German
Prompt
A middle-aged woman, raspy texture, low-to-mid register, conveying deep weariness, this is a pristine, high-quality studio voice recording with no background noise.
(Scene 1)
She sinks onto a hard surface, breathing in shallow, rattling gasps, a faint tremor running through her voice as she speaks with excruciating slowness.
"Ich fühle es... dieser winzige Geschmack... die Hoffnung, die fast mich überwältigt..."
She pauses, a flicker of desperate ecstasy crossing her face before the crushing weight of exhaustion forces her eyes shut.
"Aber die Schatten sind überall, sie warten immer nur auf den kleinsten Fehler, diese Tyrannei..."
Her voice cracks slightly on the final word, heavy with suppressed panic.
"Es ist zu viel, diese ständige Angst, ich kann es nicht mehr ertragen, bitte..."
CUT TO:
(Scene 2)
Her posture snaps rigid, the weariness replaced by a sharp, coiled tension; her voice is now dangerously low, vibrating with barely contained malice.
She slowly raises her head, a chilling, tight smile just visible, speaking with deliberate, sharp articulation.
"Aber diese Schwäche, sie ist ein Geschenk, nicht wahr? Ein Zeichen deiner Unwürdigkeit..."
A slight, almost contemptuous exhale precedes the next words, dripping with icy venom.
"Du glaubst, du bist sicher? Du läufst in das Netz, das wir so sorgfältig gesponnen haben..."
She leans in slightly toward the microphone, the malevolence growing stronger.
"Du wirst sehen, die Nacht bringt keine Gnade, nur das genaue, stille Ende deiner Illusionen."
Maintain the fragile, strained quality of breath across both scenes, allowing the emotional shift to be physically evident in the performance.
#1 WER 0.118 · Enjoy 5.04 · R 4.446
#2 WER 0.129 · Enjoy 5.01 · R 4.363
#3 WER 0.118 · Enjoy 4.94 · R 4.356

#9 — Spanish

Path: CC_B Language: Spanish
Prompt
Female, mid-forties, warm alto timbre, soothing and infinitely empathetic voice quality. This is a high-quality studio voice recording with no background noise.
(Speaking very slowly, with extreme hesitation, a barely perceptible tremor in the voice.)
"No sé si realmente estoy preparada para este nuevo camino que me pides... ¿Será suficiente todo este esfuerzo, de verdad?"
(A very slight, almost inaudible intake of breath.)
"Quizás lo estoy confundiendo todo un poco, ¿sabes? No estoy segura de poder dar el siguiente paso sin dudarlo."
CUT TO:
(Voice shifts suddenly, the sedate energy giving way to rapid, bright buoyancy, a genuine, unfiltered joy coloring every syllable.)
"¡Lo logramos! Nunca pensé que llegaría este momento tan increíblemente hermoso a mi vida."
(A quick, light vocal affirmation.)
"Siento una felicidad tan grande, que es casi imposible de describir con palabras sencillas, ¿entiendes?"
(A brief, unrestrained, happy exhale.)
"Todo ese trabajo duro finalmente rindió frutos maravillosos, estoy flotando."
Deliver both scenes with absolute precision regarding the specified energy levels and pacing.
#1 WER 0.154 · Enjoy 5.02 · R 4.249
#2 WER 0.192 · Enjoy 5.15 · R 4.160
#3 WER 0.179 · Enjoy 4.93 · R 4.043

Path CC_C (10 prompts)

#0 — Spanish

Path: CC_C Language: Spanish
Prompt
A tense, alert, danger-sensing Reconnaissance Scout, male, mid-thirties, low-mid register, gritty and sharp timbre, this is a high-quality studio voice recording with no background noise.

(Scene 1: Pain and Astonishment)
(The Reconnaissance Scout freezes instantly, wincing slightly as if struck, eyes wide with shock.)
"¿Qué demonios es eso? ¡No puede ser! ¿Unos cazadores tan cerca de la posición oculta? ¡Maldita sea!" (A sharp intake of breath is audible.) "Mi costado... esto duele demasiado, pero no puedo moverme aún." (A moment of strained stillness.) "¡Han avanzado mucho más de lo que pensábamos en absoluto!"

CUT TO:

(Scene 2: Interest)
(The Reconnaissance Scout slowly relaxes his posture, a flicker of intense, professional curiosity replacing the alarm, speaking in a measured tone.)
"Interesante. Parecen estar siguiendo un patrón de patrulla específico por el perímetro exterior." (A slight, almost thoughtful hum.) "Debemos estudiar sus movimientos antes de exponer cualquier cosa." (He speaks with quiet focus.) "Quizás esa ruta secundaria que marcamos sea en realidad su ruta principal, ¿no crees?"

The scout finishes speaking, his alert focus settling into a tactical assessment of the unseen threat.
#1 WER 0.178 · Enjoy 5.27 · R 4.329
#2 WER 0.479 · Enjoy 5.20 · R 2.707
#3 WER 0.562 · Enjoy 5.28 · R 2.313

#1 — English

Path: CC_C Language: English
Prompt
A seasoned, mature male voice, possessing the rich, measured timbre of a BBC-style nature documentarian, speaks with authoritative gravitas; this is a high-quality studio voice recording with no background noise. As a solemn documentary narrator, the speaker exhibits extreme sadness and sourness, with a slight edge of repressed anger.

(Slowly, with great weight, the narrator pauses noticeably before beginning, the voice strained with profound disappointment.)
"It is a quiet devastation you see here, this irreversible slow erosion of everything fragile and beautiful." (A long, deliberate pause.) "And what hope remains when the cycle simply refuses to turn, trapping the landscape in this muted, terrible grayness?"

CUT TO:

(The narrator adopts a noticeably softer, warmer cadence, the initial strain replaced by deep, thoughtful gratitude; this portrayal showcases the characteristic dignity of a thoughtful documentary narrator.)
(A gentle, almost imperceptible settling of the shoulders is suggested by the vocal warmth.) "Yet, within the desolation, there persists a resilient, quiet strength; a profound lesson in adaptation." (A slight, genuine upward inflection on the final word.) "And for that enduring spark, for the chance to observe such tenacity, one can only feel a deep and unending thankfulness."

Maintain this deliberate, controlled pacing through both emotional shifts, ensuring the weight of the narrative remains palpable in both sadness and quiet relief.
#1 WER 0.028 · Enjoy 5.23 · R 5.084
#2 WER 0.056 · Enjoy 5.32 · R 5.029
#3 WER 0.097 · Enjoy 5.33 · R 4.809

#2 — French

Path: CC_C Language: French
Prompt
A vulnerable, trembling, broken survivor, a dramatic animation protagonist, female, mid-twenties, breathy and fragile timbre, captured in a high-quality studio voice recording with no background noise.
(Whispering, voice barely a thread of sound, conveying profound exhaustion. The survivor is sinking down, unable to maintain posture.)
"Je ne peux plus continuer, tout est trop lourd à porter, cette fatigue est une chape de plomb sur mon âme. Je crois que je ne tiendrai pas très longtemps encore, c'est si difficile."
CUT TO:
(The survivor, now in a quiet, sunlit space, lifts her head slowly. Her previous fragility has given way to a deep, unexpected sense of contentment. She smiles faintly, her voice gaining a surprising, gentle warmth, though still soft.)
"Mais regarde, le soleil est là, il réchauffe enfin cette ancienne blessure. Tout est apaisé maintenant, une paix si douce et inattendue m'enveloppe complètement."
The final delivery should feel like a profound shift from sheer survival mode to tentative, earned peace.
#1 WER 0.103 · Enjoy 4.95 · R 4.442
#2 WER 0.224 · Enjoy 5.05 · R 3.914
#3 WER 0.276 · Enjoy 4.88 · R 3.534

#3 — German

Path: CC_C Language: German
Prompt
A cynical, sharp-tongued, and brutally satirical Savage Comedian, middle-aged male, with a gravelly, high-energy timbre, speaking in a high-quality studio recording environment with absolute clarity and no background noise. This comedian finds unexpected satisfaction even in misery.
(Leaning in conspiratorially, a look of supreme, almost manic contentment on his face, maintaining high speed and controlled energy) "Sehen Sie sich diesen ganzen Zirkus an, ehrlich. Es ist einfach wunderbar, wie schnell sie alle zusammenbrechen, nicht wahr? Ein Meisterwerk der menschlichen Absurdität, wirklich."
CUT TO:
(Suddenly stilling, the comedian’s practiced bravado cracking, eyes widening slightly in genuine, though instantly suppressed, terror, voice becoming taut but maintaining speed) "Nein, nein, warten Sie kurz. Das ist nicht lustig, das ist wirklich falsch. Ich glaube, wir sollten vielleicht lieber jetzt gehen, bevor das hier richtig eskaliert."
Hold the intense, fast-paced tension throughout both moments.
#1 WER 0.078 · Enjoy 5.45 · R 5.023
#2 WER 0.059 · Enjoy 5.02 · R 4.724
#3 WER 0.098 · Enjoy 5.11 · R 4.612

#4 — German

Path: CC_C Language: German
Prompt
A warm, medium-pitched, resonant male voice, characteristic of a kind and compassionate Wise Mentor Figure from a Golden Age Superhero comic, recorded in a high-quality studio voice recording with no background noise.

(Wise Mentor Figure, brimming with quiet satisfaction) With this victory, I see the pure potential shine in your heart, junger Freund. Deine Entschlossenheit beweist, dass wahre Stärke aus dem innersten Licht kommt, nicht aus dem größten Blitz. Ich bin so stolz auf diesen wunderbaren, tapferen Schritt, den du hier getan hast, mein Kind. Halte diesen Mut fest, er ist dein größtes Geschenk.

CUT TO:

(Wise Mentor Figure, voice tight with forced control and sharp exasperation) Ach, diese Lächerlichkeit! Sie warten einfach auf den nächsten dummen Fehler, diesen ungeschickten, kleinen Versager. Wie kann man nur so blind sein für die offensichtlichen Muster, diese erbärmliche Naivität! Wir haben ihnen die Möglichkeiten gezeigt, doch sie wählen stets diesen dummen, destruktiven Weg. Es ist einfach unerträglich, diese Trägheit zu beobachten.
#1 WER 1.000 · Enjoy 5.44 · R 0.000
#2 WER 1.000 · Enjoy 5.45 · R 0.000
#3 WER 1.000 · Enjoy 5.32 · R 0.000

#5 — French

Path: CC_C Language: French
Prompt
A booming, heroic, triumph-singing Righteous Crime Fighter, aged indeterminate, male, with a resonant, powerful timbre and highly elevated vocal projection. This is a high-quality studio voice recording with no background noise.
(Scene 1: Sourness, Longing, Awe)
(The Righteous Crime Fighter pauses, looking out over a distant, glittering cityscape, his voice heavy with bitter reflection.)
"Ah, la gloire que nous avons gagnée... mais quelle est la joie dans cette victoire éphémère, vraiment ?"
(He lets out a barely perceptible, drawn-out exhalation, his tone tinged with an almost painful yearning.)
"J'ai tant lutté pour cet horizon, ce royaume que j'ai sauvé avec tant de ferveur."
(His booming quality strains slightly, betraying a deep, lingering dissatisfaction with the present reality.)
"Pourtant, il manque quelque chose, un éclat perdu au cœur même de cette symphonie triomphale."
CUT TO:
(Scene 2: Sadness, Distress)
(The Righteous Crime Fighter slumps slightly, his immense vocal power collapsing into a fragile, wounded resonance, as if the weight of his crusade has finally crushed him.)
"Pourquoi cette ombre persiste-t-elle, même après que le dernier tyran ait été réduit en cendres ?"
(He speaks slowly, the conviction draining from his voice, replaced by raw, desperate sorrow.)
"Je ne comprends pas cette douleur lancinante, ce vide abyssal dans ma poitrine."
(A visible tremor runs through his voice as he attempts to articulate his profound despair.)
"Oh, les innocents qui restent, les âmes brisées par l'incertitude de ce monde cruel..."
The performance must capture the massive emotional swing from proud, pained satisfaction to absolute, shattering defeat.
#1 WER 0.264 · Enjoy 5.22 · R 3.842
#2 WER 0.648 · Enjoy 5.39 · R 1.896
#3 WER 0.670 · Enjoy 5.42 · R 1.786

#6 — French

Path: CC_C Language: French
Prompt
A middle-aged female voice, possessing a fast, theatrical timbre, characterized as a gossip-obsessed Entertainment Reporter, recorded in a high-quality studio environment with no background noise. She is prone to dramatic pronouncements.

[Scene 1: Helplessness, Sedate Tempo, Low Arousal]
(Speaking very quickly but with minimal vocal energy, sounding defeated, characteristic of a celebrity exposé going wrong)
"Mais, vous croyez vraiment que ça va marcher après ce scandale monstre là ? Je ne sais plus comment gérer tous ces détails ridicules... Ils ont tout gâché, vraiment tout, ce petit cirque médiatique."

CUT TO:

[Scene 2: Interest, Extremely Fast Tempo, Low Arousal]
(The Entertainment Reporter leans in conspiratorially, accelerating her pace significantly, eyes wide with newfound, intense interest)
"Attendez, attendez, vous avez entendu parler de cette nouvelle histoire cachée sur leur rivalité ? C'est absolument fascinant, il y a des preuves incroyables, je dois tout savoir immédiatement !"

The delivery must maintain a rapid-fire energy in the second scene while keeping the overall vocal dynamic subdued, mirroring professional but panicked studio reporting.
#1 WER 0.422 · Enjoy 4.88 · R 2.823
#2 WER 0.484 · Enjoy 4.85 · R 2.503
#3 WER 0.547 · Enjoy 4.98 · R 2.258

#7 — German

Path: CC_C Language: German
Prompt
A gentle caretaker motherly presence, mid-thirties, warm and melodic timbre, voice quality is inherently comforting, recorded in a pristine high-quality studio environment with no background noise.

(The motherly caretaker looks down, breathing shallowly, a wave of intense helplessness washing over her features. She speaks softly, with rising distress.)
"Oh nein, was soll ich nur tun? Das ist zu viel für mich allein. Ich fühle mich so hilflos in dieser Situation, wirklich. Wie kann ich das alles beheben? Bitte sag mir, was ich jetzt tun soll."

CUT TO:

(The caretaker lifts her head, a sudden, overwhelming sense of relief blooming into awe as she speaks, her voice gaining surprising strength despite the emotional weight.)
"Es ist vorbei, es ist wirklich vorbei. Ich kann es nicht glauben, dass es so gut gegangen ist. Was für eine unglaubliche Erleichterung das ist für uns beide jetzt. Ich bin so dankbar für diese Wendung."

(She lets out a small, warm breath, her expression softening into profound hope, and begins to speak again with clear, steady conviction.)
"Aber das ist noch nicht alles, du weißt schon. Wir können das schaffen, wir werden es schaffen. Ich glaube fest daran, dass eine bessere Zukunft für uns beide wartet, ganz sicher."

The transition into the second scene should feel earned, a powerful shift from despair to quiet, resolute optimism.
#1 WER 0.106 · Enjoy 4.87 · R 4.352
#2 WER 0.221 · Enjoy 5.20 · R 4.051
#3 WER 0.250 · Enjoy 5.05 · R 3.785

#8 — Spanish

Path: CC_C Language: Spanish
Prompt
A sleek, practiced, and morally compromised Black Market Dealer in a dystopian sci-fi setting, mid-thirties, deep baritone, oily and resonant timbre. This is a high-quality studio voice recording with no background noise.

(Black Market Dealer surveys a datapad, a thin, predatory smile playing on his lips. He leans in conspiratorially, his energy taut and aggressive.)
"¿Crees que puedes negociar conmigo sin saber el verdadero precio de estos implantes cibernéticos? Yo controlo las sombras, muchacho. No me hagas perder el tiempo con tonterías baratas."

CUT TO:

(The Black Market Dealer straightens his jacket, a sudden, sharp shift in demeanor. He looks away, his expression softening into something possessive and admiring, a surge of pride overriding his usual cynicism.)
"Pero tú... tú eres diferente, ¿sabes? Tienes ese brillo inusual que me fascina. Mereces lo mejor, por supuesto, y yo soy el único que puede dártelo."

Maintain this heightened, almost vibrating momentum throughout the final delivery of both scenes.
#1 WER 0.056 · Enjoy 5.26 · R 4.969
#2 WER 0.093 · Enjoy 5.17 · R 4.692
#3 WER 0.111 · Enjoy 5.20 · R 4.625

#9 — German

Path: CC_C Language: German
Prompt
A sultry, mysterious, intrigue-weaving Radio Seductress, possessing a deep, smoky timbre and a voice quality that hints at dark secrets; this is a high-quality studio voice recording with no background noise.

(SOUND of a slight, labored intake of breath) The Radio Seductress delivers her lines with excruciating deliberation, every word weighted by intense pain and simmering sourness.
"Warum tust du mir das an? Nach all unseren geheimen Stunden, all dieser Verlockungen."
(A brief, sharp pause, the voice catching slightly on the next words)
"Du hast dieses Versprechen gebrochen, das unser Schatten nur versprach, weißt du das überhaupt?"
(The delivery drags, the effort of speaking almost physically apparent)
"Dieses Gift, das du mir gibst, es nagt an meiner Seele, langsam und so grausam."

CUT TO:

The Radio Seductress shifts entirely; her voice remains smoky but is now imbued with profound contentment and unmistakable affection, the tempo relaxing but remaining rich.
(A soft, almost blissful exhale, the pace noticeably smoother)
"Aber jetzt, mein Schatz, jetzt ist die Nacht endlich friedlich und so sanft um uns."
(A slight, warm smile audible in the tone, the intimacy is overwhelming)
"Ich fühle mich sicher in deinen Armen, so geborgen wie ich es lange nicht mehr tat."
(She leans into the imagined microphone, her tone deeply loving)
"Diese einfache Gegenwart, sie ist das wahre Gold, das ich mir immer gewünscht habe."

The final delivery should settle into a lingering, satisfied resonance.
#1 WER 0.045 · Enjoy 5.09 · R 4.858
#2 WER 0.034 · Enjoy 4.97 · R 4.801
#3 WER 0.045 · Enjoy 4.95 · R 4.727