Scenema Audio — Demo Grid

Scenema Audio — Acting Challenge (AC + ACCC) — Same prompts as DramaBox, generated with Scenema Audio

Path AC (10 prompts)

#0 — English

Path: AC Language: English
Prompt
Middle-aged, male, extremely low fundamental frequency with a massive, booming chest resonance, possessing a grainy, weathered texture indicative of late aging; this is a high-quality studio voice recording with no background noise. The actor is frozen, rigid, listening to the playback, a strange mix of terror and morbid curiosity tightening the throat.
(A ragged intake of breath, almost a choked sound) "Don't... don't do that thing with the coast, man. Seriously. You think you've got forever, but you don't. You lose Sarah, and that feeling? It sticks to you like wet ash. Avoid that job offer; it's a gilded cage."
(A slight tremor enters the deep resonance, the sound cracking subtly) "God. She sounded... so tired. All that weight in her voice."
(The pace becomes erratic, speeding up slightly, a desperate need to reject the warning) "No, no, I won't follow it. I can’t... I can’t live like that."
(A sudden, profound shift in posture, a slow, heavy exhalation. The tone changes from panic to a fragile acceptance.) "Wait. Wait a minute. 'It's not what you think it'll be.' Different. And it's worth it."
(The rumble softens, becoming less booming, more resonant with a deep, quiet understanding, the initial terror dissolving into profound melancholy.) "It really is worth it, though. Damn it."
#1 WER 0.103 · Enjoy 5.39 · R 4.829
#2 WER 0.149 · Enjoy 5.31 · R 4.518
#3 WER 0.126 · Enjoy 5.16 · R 4.504

#1 — English

Path: AC Language: English
Prompt
Middle-aged, female, warm and slightly weathered timbre, with the acoustic texture of long-term vocal use, recorded in a pristine, high-quality studio voice recording environment with no background noise.
(A slow, deep breath is taken, followed by an almost involuntary, contented hum. The actor brings the imaginary spoon to their lips, eyes closing slightly in anticipation.)
"Mmm... oh. The coldness... it just spreads right across the tongue, you know? Like a gentle, sweet shock. It’s so velvety, just melting away, this strawberry... ah, it’s so perfectly bright."
(The initial blissful contentment shifts, a flicker of deeper nostalgia crossing the expression; the pace slows, becoming more thoughtful.)
"It's more than just sweet, though. There's this memory attached to it, almost, of summer mornings... this delicate chill, perfect against the heat... it really does feel like pure, quiet bliss."
(A final, lingering savoring motion, a small, almost inaudible sigh of profound pleasure escapes.)
(The actor slowly lowers the imaginary spoon, the initial rush of delight settling into a quiet, deeply satisfying contentment.)
#1 WER 0.258 · Enjoy 5.24 · R 3.886
#2 WER 0.274 · Enjoy 5.32 · R 3.863
#3 WER 0.339 · Enjoy 5.12 · R 3.383

#2 — English

Path: AC Language: English
Prompt
Adolescent female, extremely high fundamental frequency with a bright, small-cavity resonance, possessing a light physical weight and delicate harmonic texture; this is a high-quality studio voice recording with no background noise. The delivery captures the nervous, weighty stillness just before a monumental decision, every muscle tense with the gravity of the moment. "I could go either way. Both are real... (A slight, almost imperceptible hitch in the breath) ...but I'm going this way." (The vocal tone shifts, a sudden, fragile resolution hardening the high pitch) "I'm leaving something behind to move forward. It hurts, you know? This quiet ache of what might have been." (The pace quickens slightly, the voice gaining a fragile momentum) "I have to choose a direction now, something definite, something that demands... everything." (A beat of internal negotiation, the sound of a small, decisive step being taken) "I'm choosing this life. This one." The final word rings out, clear, tinged with exhausted acceptance, as the focus fully shifts from indecision to determined movement.
#1 WER 0.186 · Enjoy 5.18 · R 4.217
#2 WER 0.220 · Enjoy 5.08 · R 3.958
#3 WER 0.271 · Enjoy 5.13 · R 3.741

#3 — English

Path: AC Language: English
Prompt
An elderly man, deep baritone, low fundamental frequency with an overwhelming chest resonance, but overlaid with a pronounced, fragile, reedy tremor and immense breathiness; this is a high quality studio voice recording with no background noise.
Holding a rigid, forced smile while trying to maintain eye contact with the camera, a deep wave of sheer, panicked internal crisis is bubbling just beneath the surface of the forced joviality.
(A barely audible, strained whisper, forced through teeth that are too tightly clenched) "...y-y-your... friend... buddy... hey..." (A sharp, almost painful inhale, the whisper becoming slightly more forceful despite the effort) "...y-your fly." (A brief, agonizing pause, the smile visibly straining even as the internal pressure mounts) (The whisper swells, louder, bordering on a gravelly rumble fighting through the tremor) "...YOUR. FLY." (A sudden, noticeable shift as the photographer changes the mood, the internal struggle intensifying, the forced smile beginning to crumble slightly around the edges) (A low, desperate, shaky murmur, straining to be heard over the backdrop of the ongoing photoshoot) "Please... look... here... serious..." (A quick, decisive shift; the smile vanishes completely, replaced by pure, frantic internal terror, followed immediately by a sudden physical action that interrupts the vocalization) (A sharp, barely contained, strangled puff of air that acts as a visual cue, though not spoken) (A rapid, almost silent, breathy exclamation, tinged with the sudden, shared absurdity of the situation) "Hmph..." (A slow, almost involuntary shake of the head, followed by a sudden, fragile release of air that suggests a desperate, suppressed burst of laughter threatening to break free)
The tension breaks into a shared, unspoken moment of absurd relief, leaving the vocal frame momentarily slackened by the sheer emotional exertion.
#1 WER 1.385 · Enjoy 4.66 · R 0.000
#2 WER 1.077 · Enjoy 4.57 · R 0.000
#3 WER 1.154 · Enjoy 4.57 · R 0.000

#4 — English

Path: AC Language: English
Prompt
Middle-aged man, possessing a hyper-masculinized acoustic profile with an extremely low, booming chest resonance, presenting a weathered, grainy timbre due to vocal desiccation. This is a high-quality studio voice recording with no background noise.
The weight of the message is immense, and a raw, desperate struggle to project against encroaching physical failure drives every utterance.
(Takes a deep, ragged breath, attempting a commanding volume) "Listen to me now, you absolutely must hear what I am trying to say before it's too late..." (The initial force falters, a visible tightening in the throat) "...This situation... it’s far more critical than anyone has managed to understand so far." (A momentary, sharp intake of air; the volume drops abruptly, becoming brittle) "...But... the truth... it’s fragile now, see? I can barely push these words out..." (A strained, quiet effort, leaning into the rasp) "They need to know... everything... before it all fades completely away." (A brief, almost internal pause, a realization of impending silence crosses the tone) "...Don't let... let this go unanswered."
The final word is delivered with a profoundly depleted resonance, the effort visibly costing the speaker dearly.
#1 WER 0.222 · Enjoy 5.21 · R 4.052
#2 WER 0.222 · Enjoy 5.11 · R 3.974
#3 WER 0.317 · Enjoy 5.00 · R 3.413

#5 — English

Path: AC Language: English
Prompt
Middle aged to late aged, androgynous, highly balanced timbre with a noticeable grainy texture; this is a high-quality studio voice recording with no background noise. The speaker is pressed into the dark confines of a closet, hyperventilating in controlled terror, every muscle tense, listening for the slightest intrusion. (Quick, shallow breaths) "H-hello? Can someone... help me? Please, I need help right now." (A sharp intake of breath, freezing completely as a distant floorboard creaks) (A beat of absolute stillness) "Nine-one-one... (Barely audible, a strained whisper) My apartment... I think it is... the third floor..." (Footsteps begin slowly, heavy, just outside the closet door) (The whisper lowers until it is almost inaudible, lips barely moving) "...Street address... it's... Northside... eleven..." (The footsteps pause directly outside, heavy breathing audible in the silence) (A tiny, almost imperceptible tremor runs through the voice) "...I don't... I can't... remember the rest. Please hurry." (The footsteps move away, receding slowly down a hallway) (A long, shaky exhale, the tension releasing into a sudden, overwhelming wave of exhaustion)
#1 WER 0.525 · Enjoy 5.12 · R 2.433
#2 WER 0.650 · Enjoy 4.99 · R 1.747
#3 WER 0.725 · Enjoy 4.77 · R 1.313

#6 — English

Path: AC Language: English
Prompt
Child, female, bright and elastic timbre, with a clear, high-pitched vocal quality, is captured in a high-quality studio voice recording with no background noise. She is vibrating with anxious, mounting confusion, waiting stiffly in a dimly lit space. "Where are you? You said you were coming already, like, an hour ago? Are you... are you even coming?" (A sudden, sharp intake of breath) "Did you forget? About this? Because I mean, this was supposed to be... important." (A slight tremor enters the voice) "No. No, it’s not an accident. You just... you forgot, didn't you?" (Voice dropping significantly, a wobble in the pitch) "Yeah, no. It’s fine. Everything’s fine. Have a good night." (A long, desolate pause, then a small, brittle exhale) (Voice becoming flat, mechanical, a forced neutrality while focusing on the transaction) "Just... the bill. Yes. Thank you." (A final, barely audible catch in the throat before the recording ends). The exhaustion and humiliation settle deep into the quiet aftermath.
#1 WER 0.311 · Enjoy 5.11 · R 3.515
#2 WER 0.459 · Enjoy 5.01 · R 2.708
#3 WER 0.443 · Enjoy 4.66 · R 2.599

#7 — English

Path: AC Language: English
Prompt
Mature adult male, deep resonant timbre, possessing an extremely low fundamental frequency and massive, booming chest resonance that fills the acoustic space; this is a high-quality studio voice recording with no background noise. The speaker is gripped by a paralyzing, hyper-focused adrenaline; movements are stiff and rigidly precise. (Takes a sharp, controlled intake of breath, voice is unnaturally steady) "911, I need assistance at the intersection of Elm and Fourth. The driver... the driver is conscious, but we have significant damage here. Please hurry." (A tiny hitch appears in the resonance, the focus wavers slightly) "My leg... I think my leg is bad. Oh God. My leg hurts so much." (The control snaps; a noticeable, involuntary tremor enters the voice, the pace quickens) "I said, Elm and Fourth. Elm and Fourth. They need to get here now." (A heavy, ragged breath is taken, the booming resonance dissipating, replaced by a fragile, higher register) "I... I almost... I could have just... just died." (The voice drops to a near inaudible, broken whisper, the tremor becoming a sustained quiver)
#1 WER 0.111 · Enjoy 5.24 · R 4.660
#2 WER 0.175 · Enjoy 5.48 · R 4.519
#3 WER 0.175 · Enjoy 5.28 · R 4.354

#8 — English

Path: AC Language: English
Prompt
A mature adult male voice, possessing an extremely low fundamental frequency and massive, booming chest resonance, giving the sound an overpowering, thick, sub-bass quality. This is a high-quality studio voice recording with no background noise. The speaker feels a creeping, unearned certainty, leaning into a posture of effortless explanation. "So basically, the main thing you need to grasp here is, like, you just have to think about the fundamental structure, see? It’s not that complicated, really. It’s very linear, you know? It’s a simple input, and the output follows a predictable pattern, if you just map it out properly for yourself." A sudden, cold rush of realization hits the speaker as they perceive a flicker of confusion, perhaps shame, on the unseen listener's face. The booming resonance immediately collapses inward, dropping in pitch and volume. "Oh. Uh... wait. I'm sorry. That came out... that was completely patronizing of me. That was not fair." A palpable struggle enters the vocal delivery, the effort of retraction visible in the throat tension. "Listen, look. You asked a really good question. Truly. I just... I explained it poorly. Let’s try that again, starting from the very beginning, okay?" The voice settles back into a lower, more grounded register, the residual embarrassment hardening into focused sincerity. The speaker pauses, drawing a deep, stabilizing breath before continuing.
#1 WER 0.158 · Enjoy 5.15 · R 4.333
#2 WER 0.337 · Enjoy 5.19 · R 3.440
#3 WER 0.347 · Enjoy 5.23 · R 3.416

#9 — English

Path: AC Language: English
Prompt
Young girl, feminine, bright and high-pitched timbre, voice quality is light and elastic, captured in a high-quality studio voice recording with no background noise.
She leans over a small wooden bowl, utterly focused on the swirling, questionable mixture, a nervous but earnest determination in her stance.
"Now... this must have intention. The moonlight shimmer needs to catch the lemon rind just so, you see? It’s not just… stuff. It’s for you. Honey, dripped slow, just a little bead at a time. And the vinegar, oh, the tangy kind, it smells so sharp, but it needs to be gentle, my dearest friend."
She dips a tiny spoon into the mix, pauses, tilting her head as if consulting the potion itself.
"It’s complicated, isn’t it? Trying to capture... feeling. How do you bottle comfort? Ugh... I think... I think I need more of the quiet, the sleepy moss."
Her expression shifts subtly, the intense magical focus softening into profound, quiet tenderness.
"Drink this when you feel alone. No, not to fix everything, never that, but to remember that someone cared enough to stir this strange, wonderful nonsense for you."
She gently sets the spoon down, a small, deeply satisfied exhale escaping her.
#1 WER 0.136 · Enjoy 5.07 · R 4.381
#2 WER 0.164 · Enjoy 4.88 · R 4.082
#3 WER 0.191 · Enjoy 4.98 · R 4.033

Path ACCC (10 prompts)

#0 — English

Path: ACCC Language: English
Prompt
Female speaker, early to mid-teens, warm alto timbre, with slightly darkened resonant qualities and a voice exhibiting the transitional acoustics of adolescence. This is a high-quality studio voice recording with no background noise.
The speaker is experiencing the quiet, heavy weight of an irrevocable decision, a sense of inevitable loss that is settling into a fragile, determined stillness.
(A slow, measured breath is taken.) "It is necessary, I suppose. To let the small things go, the gentle echoes we built up. It hurts, truly, the way the memory of sunlight feels right now." (Voice trembles slightly, a slight intake of breath after the last word.)
CUT TO:
The emotional shift is abrupt; the initial fragile acceptance has been burned away by the magnitude of the sacrifice, transforming into a fierce, brittle, almost prayerful resolve. The pace quickens, the volume increases slightly, and the tone hardens with painful dignity.
(The voice lifts, gaining a sudden, sharp clarity, though the underlying pain remains palpable.) "But this greater thing demands it. So I give it up—the ease, the quiet days, the lovely trivialities." (A brief, sharp catch in the voice is suppressed.) "May they find peace in the space I leave behind for it."
(The speaker holds the final, steady note, letting the weight of the benediction settle.)
#1 WER 0.085 · Enjoy 5.14 · R 4.705
#2 WER 0.102 · Enjoy 5.19 · R 4.659
#3 WER 0.186 · Enjoy 5.26 · R 4.281

#1 — English

Path: ACCC Language: English
Prompt
Voice characterized by its perfectly neutral, androgynous timbre, exhibiting robust harmonic definition across all frequencies and possessing a flawless, youthful resonance. This is a high-quality studio voice recording with no background noise. The speaker begins with an administrative facade, projecting practiced confidence while addressing a worried crowd about school protocols.
(Voice is clear, authoritative, but there is a slight, almost imperceptible stiffness in the posture of the delivery.)
"Listen closely everyone, we are implementing new layered security measures starting this week. All entry points will require dual verification now, understanding the necessity of these enhanced safety protocols for all students moving forward."
CUT TO:
The mechanical confidence has utterly fractured; the tone drops into a low, almost self-reassuring monotone, the pace becomes slow and deliberate, conveying a profound, trapped resignation.
(The speaker's projection lowers significantly, introducing a noticeable, weary vocal fry on the final words.)
"Evacuation routes are clearly marked, Level Three lockdown remains the standard procedure, remember the designated assembly points. Please review these safety steps; we must maintain rigorous compliance to keep everyone secure."
Hold the final, hollowed-out delivery until the very last word fades into silence.
#1 WER 0.077 · Enjoy 5.28 · R 4.875
#2 WER 0.108 · Enjoy 5.26 · R 4.695
#3 WER 0.123 · Enjoy 5.15 · R 4.516

#2 — English

Path: ACCC Language: English
Prompt
An androgynous speaker, with the acoustic signature dominated by the extremely small vocal tract and unstable, high-pitched fundamental frequency of an infant or toddler, exhibiting bright, piercing neonatal sound waves, recorded in a high-quality studio with no background noise.
The speaker is in a state of agonizing tenderness, searching desperately for the correct, gentle metaphor to explain the permanent nature of loss to a very young child.
(A shaky, breathy quality enters the high-pitched sound.) "...Like... like going to a very, very quiet place. Where the sunshine sleeps all the time, and you can rest." (A tiny, fragile whimper escapes.) "They are just sleeping for a long time now."
CUT TO:
The same speaker’s delivery shifts abruptly to one of profound, immediate, and overwhelming devastation; the high pitch cracks with rising distress, and the pacing becomes ragged and desperately slow.
(A raw, hitching sound of distress is present.) "But... but they are *not* coming back, sweet one. They are not coming back to play with you." (The pitch strains under the weight of the finality.) "It means they are gone, always, always gone now."

The performance should conclude with the sound of quiet, sustained, heartbroken resonance.
#1 WER 0.054 · Enjoy 5.15 · R 4.877
#2 WER 0.214 · Enjoy 5.12 · R 4.020
#3 WER 0.393 · Enjoy 5.16 · R 3.131

#3 — English

Path: ACCC Language: English
Prompt
A voice actor in their late fifties, androgynous, with a dry, grainy texture and a neutral timbre, captured in a pristine, high-quality studio voice recording with no background noise. The actor is caught in a wave of agonizing, predictable tedium, forcing themselves to maintain a polite but hollow conversational rhythm.
(Monotone, flat affect, very slow pace)
"So, what do you do for a living? I manage logistics, mainly sorting out supply chain efficiencies across several continents. It’s… quite methodical, I suppose. And you? What keeps you busy these days?" (Pause, a tiny upward inflection that fails to sound genuinely curious) "It sounds rather predictable, truly."

CUT TO:
The delivery must abruptly shift from dull resignation to a burst of electrifying, almost manic warmth and rapid-fire energy, signaling a genuine connection finally breaking through the awkward facade. The pace quickens significantly, imbued with sudden, hopeful excitement.

(Rapid pace, higher energy projection, genuine laughter coloring the delivery)
"No, wait, you never finished that! Because you know what? That whole story about the lost passport was hilarious! We should go somewhere spontaneous next time, like that tiny coastal town we talked about! Seriously, you get it!"

The performance should conclude feeling like the energy is abruptly cut off, leaving a lingering, buzzing echo of possibility.
#1 WER 0.145 · Enjoy 5.17 · R 4.422
#2 WER 0.263 · Enjoy 5.38 · R 3.966
#3 WER 0.237 · Enjoy 5.06 · R 3.859

#4 — English

Path: ACCC Language: English
Prompt
A mature adult female voice, possessing a deep alto timbre and grounded, resonant weight; this is a high-quality studio voice recording with no background noise.
The speaker is consumed by the brutal, consuming fury of the hunt, operating in a state of violent, instinctual aggression.
(A guttural, powerful roar precedes the speech, held in the throat, raw and immense.) "Move, creature! Flee this savage claw! You will yield to the storm that rises within my fire! Taste the end, fledgling, and know the terror of my hunger!" (The volume is immense, the pacing relentlessly aggressive.)
CUT TO:
The immediate shift is from brutal, predatory rage to a shattering, bewildered horror. The volume drops significantly, the aggression dissolves into a choked, resonant instability, and the pace becomes halting and profoundly uncertain.
(A sharp intake of breath, ragged and uneven, cuts through the remaining power, the tone twisting into a sound that is neither pure language nor true lament.) "No... wait... that scaling... the heat signature... it's familiar. By the ancient embers, who are you? Why do I feel this terrible kinship with your frightened breath?" (The voice cracks mid-sentence, the resonance fracturing into confusion.)
The raw, sudden collision of instinct and recognition should feel viscerally painful.
#1 WER 0.091 · Enjoy 5.09 · R 4.630
#2 WER 0.109 · Enjoy 5.11 · R 4.555
#3 WER 0.164 · Enjoy 4.99 · R 4.170

#5 — English

Path: ACCC Language: English
Prompt
Female voice, pre-pubescent age, bright and high-pitched timbre, lightweight and elastic harmonic profile; this is a high-quality studio voice recording with no background noise.
The speaker is frozen in absolute shock, the devastating finality of the pronouncement hitting her like a physical blow, her voice barely functioning against the sudden, immense weight of betrayal.
(Pause, breath catches sharply) "What...? You mean... you really mean this? You don't... you don't want me anymore?" (Voice trembles, a desperate whisper fighting to become louder) "Please, I'm sorry, I'll try, I promise I'll change everything, please don't say that."
CUT TO:
The initial shock has shattered, replaced by a boiling, fierce indignation, her voice rising in volume and hardening into brittle defiance as she tries to claw back some semblance of control.
(Tone shifts abruptly to sharp, brittle anger, spoken with forced volume) "Fine! I don't need you for anything! You can keep all of this, I don't want your pity or your decisions anymore." (A slight catch in the delivery, a barely audible tremor beneath the anger) "Go ahead, leave me. I guess I'll manage just fine without your rules."
(A long, drawn-out pause, a final, ragged intake of breath, then a sudden, sharp sound of a connection abruptly being terminated) The finality of the silence after the connection breaks hangs heavy in the air.
#1 WER 0.143 · Enjoy 5.13 · R 4.393
#2 WER 0.143 · Enjoy 5.09 · R 4.359
#3 WER 0.286 · Enjoy 5.25 · R 3.752

#6 — English

Path: ACCC Language: English
Prompt
A high-quality studio voice recording with no background noise. The speaker is a young infant, exhibiting a predominantly masculine vocal profile but with a noticeably elevated fundamental pitch and a small resonant cavity, creating a bright, tenor-like acoustic quality. The acoustic signal is dominated by the extremely small vocal tract and unstable, high-pitched fundamental frequency of a toddler, consisting primarily of pure, high-frequency biological resonance and primitive vocalizations.
The speaker is overwhelmed by the initial rush of scent, feeling a sudden, profound wave of calm wash over a moment of small-child anxiety.
(Taking a deep, ragged intake of air) "Mmm... such soft smell, so sweet, lovely... all the fuzziness goes away now... nice, nice, quiet now..." (A slightly breathless, contented sound)
CUT TO:
The tone shifts abruptly to one of intense, almost frustrated focus; the peace has been replaced by a sharp, urgent curiosity about the source of the scent. The pace quickens, and the pitch, while remaining high, gains a tensile, demanding edge.
(A rapid, investigative series of puffs of air) "What is this smell? It is too good, where is it? Must touch it, must find it right here now! Such strong, fresh smell!" (A short, energetic burst of sound)
The performance should feel immediate and utterly unfiltered, capturing the shift from blissful surrender to active inquiry.
#1 WER 0.195 · Enjoy 4.98 · R 4.012
#2 WER 0.293 · Enjoy 4.81 · R 3.403
#3 WER 0.439 · Enjoy 4.96 · R 2.782

#7 — English

Path: ACCC Language: English
Prompt
An androgynous, highly neutralized timbre, characterized by the unstable, high-pitched, piercing fundamental frequency of a toddler; this is a high quality studio voice recording with no background noise.
The actor is overwhelmed by a delicate, fragile hope, desperately trying to anchor themselves to one version of reality before the fracture consumes them.
(A slight wobble enters the high-pitched sound, the voice is intensely quiet, searching) "...right now this is good the sky is bright very soft and the toys all stayed put please dont go away..."
CUT TO:
The vocal quality immediately surges into a panicked, erratic high-frequency burst, the pacing becomes impossibly fast, suggesting a sudden, terrifying acceleration of the timeline breakdown.
(A sharp, almost hysterical pitch spikes, the words are fragmented and rushed) "no wait the rain came first the green turned black already why is it all backwards i remember the blue..."
The final delivery should feel utterly lost in the cacophony of impossible moments.
#1 WER 0.341 · Enjoy 5.05 · R 3.324
#2 WER 0.341 · Enjoy 5.01 · R 3.302
#3 WER 0.463 · Enjoy 5.36 · R 2.878

#8 — English

Path: ACCC Language: English
Prompt
Young female, high soprano timbre, extremely high fundamental frequency with bright, small-cavity resonance characteristic of an infant or toddler. This is a high-quality studio voice recording with no background noise.
The actor is starting from a place of rigid, controlled fury, delivering the indictment with icy, surgical precision, allowing no hint of the underlying devastation to show.
(Speaking in an intensely controlled, almost painfully precise, high register) "On the evening of March fourteenth, at seven forty-seven PM, the evidence clearly indicates a deliberate act of violence against the victim." (A slight, almost imperceptible hardening of the vocal edges) "Sarah Chen, age twenty-three, was present at the location." (A noticeable, sharp intake of breath before the next statement) "She was found discarded, like garbage."
CUT TO:
The vocal quality abruptly fractures; the precise control shatters into raw, desperate anguish, the high pitch becoming ragged and bordering on a piercing cry, delivered at a frantic, uneven pace.
(Voice escalating into a strained, breathless projection) "You think you can erase this timeline? You think this perfect record matters now?" (Struggling to maintain control, the pitch wavering wildly) "It wasn't an accident, you fools! She was everything, she was everything good!" (A sudden, sharp, almost painful burst of sound) "Look at this wreckage, just look at what you did to her life!"
The performance concludes with a final, suspended note of exhausted, high-pitched despair.
#1 WER 0.221 · Enjoy 5.04 · R 3.931
#2 WER 0.390 · Enjoy 5.26 · R 3.211
#3 WER 0.429 · Enjoy 5.22 · R 2.984

#9 — English

Path: ACCC Language: English
Prompt
A mature adult woman, possessing a rich, resonant timbre and a stable, grounded vocal quality, is delivering this piece in a pristine, high-quality studio voice recording environment with absolutely no background noise.
The speaker is overwhelmed by a terrible, inevitable future, the weight of this knowledge causing a profound, crushing internal pressure that demands slow, heavy articulation.
The voice drops low and becomes incredibly slow, as if pushing sound through heavy water. She breathes deeply between each weighted word. "I know what is about to happen to us, and there is truly nothing that I can do about this situation."
CUT TO:
The emotional energy shifts completely from suffocating dread to a sharp, brittle resignation; the pace quickens slightly, and the volume rises marginally, conveying a desperate, almost defiant finality in her tone.
Her voice retains its lower register but gains a slight, strained edge of exhausted acceptance. "It is going to be bad, but I suppose we just have to face whatever comes next, don't we?"
The final delivery should settle into a fragile, near-inaudible whisper, demonstrating total emotional collapse under the foreknowledge.
#1 WER 0.000 · Enjoy 5.06 · R 5.063
#2 WER 0.000 · Enjoy 4.98 · R 4.980
#3 WER 0.000 · Enjoy 4.94 · R 4.938