LAION · MOSS-8B voice-acting · prompting ablation

Prompt-adherence rewards — best-of-16/8/6/4

What this compares (for dummies). Same 16 takes per setting, but ranked by two prompt-adherence-aware reward functions instead of the original one:

· reward_ps = prompt-sim × invWER — pick the take that best matches the written direction and says the right words.
· reward_all = invWER × (normalised prompt-sim + blend + genuineness) — the original reward plus prompt adherence folded in.

For each setting we show the single best take at budgets 16, 8, 6, 4 under each reward, so you can hear whether ranking on prompt-sim changes the winner and how it degrades with fewer samples. prompt-sim = VoiceCLAP cosine of the direction text vs the audio (higher = better match to "how to say it").

CCcca_voicenet_10979_cc cca_voicenet
SAY: You know, I really do care about you. It's just that you make it so hard sometimes, the way you never listen, always so sure of yourself.
original DramaBox prompt & direction text

Full DramaBox prompt (how to say — with the "quoted" dialogue):
A mature androgynous adult with a deeply throaty, cavernous resonance and a deliberately labored, sedate tempo, delivering this high-quality studio voice recording with no background noise. The same voice is intensely affectionate yet laced with contempt, a loving but scornful tone. (Drawling, half-smile in voice.) "You know, I really do care about you. It's just that you make it so hard sometimes, the way you never listen, always so sure of yourself." CUT TO: The same voice now hollow with sudden

Direction only (dialogue removed — this is what prompt-sim compares against):
A mature androgynous adult with a deeply throaty, cavernous resonance and a deliberately labored, sedate tempo, delivering this high-quality studio voice recording with no background noise. The same voice is intensely affectionate yet laced with contempt, a loving but scornful tone. (Drawling, half-smile in voice.) CUT TO: The same voice now hollow with sudden

What to say (goes in MOSS text field): You know, I really do care about you. It's just that you make it so hard sometimes, the way you never listen, always so sure of yourself.

with_dialogue · no_ref
prompt-sim × invWER
best-of-16rew·ps0.165invWER1.000WER0.000prompt-sim+0.165blend5.354genu1.239
best-of-8rew·ps0.165invWER1.000WER0.000prompt-sim+0.165blend5.354genu1.239
best-of-6rew·ps0.127invWER1.000WER0.000prompt-sim+0.127blend2.488genu1.390
best-of-4rew·ps0.152invWER1.000WER0.000prompt-sim+0.152blend3.102genu0.744
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all1.830invWER1.000WER0.000prompt-sim+0.111blend5.575genu1.739
best-of-8rew·all1.830invWER1.000WER0.000prompt-sim+0.111blend5.575genu1.739
best-of-6rew·all1.830invWER1.000WER0.000prompt-sim+0.111blend5.575genu1.739
best-of-4rew·all1.594invWER1.000WER0.000prompt-sim+0.145blend3.905genu1.159
with_dialogue · emo_ref
prompt-sim × invWER
best-of-16rew·ps0.144invWER1.000WER0.000prompt-sim+0.144blend2.388genu1.222
best-of-8rew·ps0.113invWER1.000WER0.000prompt-sim+0.113blend3.032genu1.316
best-of-6rew·ps0.144invWER1.000WER0.000prompt-sim+0.144blend2.388genu1.222
best-of-4rew·ps0.144invWER1.000WER0.000prompt-sim+0.144blend2.388genu1.222
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all1.543invWER0.893WER0.107prompt-sim+0.056blend5.652genu1.463
best-of-8rew·all1.278invWER1.000WER0.000prompt-sim+0.049blend1.950genu1.257
best-of-6rew·all1.543invWER0.893WER0.107prompt-sim+0.056blend5.652genu1.463
best-of-4rew·all1.543invWER0.893WER0.107prompt-sim+0.056blend5.652genu1.463
no_dialogue · no_ref
prompt-sim × invWER
best-of-16rew·ps0.181invWER1.000WER0.000prompt-sim+0.181blend4.756genu1.470
best-of-8rew·ps0.173invWER1.000WER0.000prompt-sim+0.173blend0.927genu0.637
best-of-6rew·ps0.173invWER1.000WER0.000prompt-sim+0.173blend0.927genu0.637
best-of-4rew·ps0.181invWER1.000WER0.000prompt-sim+0.181blend4.756genu1.470
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all1.786invWER1.000WER0.000prompt-sim-0.022blend6.158genu2.072
best-of-8rew·all1.715invWER1.000WER0.000prompt-sim-0.001blend5.746genu1.749
best-of-6rew·all1.786invWER1.000WER0.000prompt-sim-0.022blend6.158genu2.072
best-of-4rew·all1.786invWER1.000WER0.000prompt-sim-0.022blend6.158genu2.072
no_dialogue · emo_ref
prompt-sim × invWER
best-of-16rew·ps0.189invWER1.000WER0.000prompt-sim+0.189blend2.131genu1.245
best-of-8rew·ps0.174invWER1.000WER0.000prompt-sim+0.174blend4.368genu1.317
best-of-6rew·ps0.189invWER1.000WER0.000prompt-sim+0.189blend2.131genu1.245
best-of-4rew·ps0.174invWER1.000WER0.000prompt-sim+0.174blend4.368genu1.317
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all1.705invWER1.000WER0.000prompt-sim+0.174blend4.368genu1.317
best-of-8rew·all1.705invWER1.000WER0.000prompt-sim+0.174blend4.368genu1.317
best-of-6rew·all1.339invWER1.000WER0.000prompt-sim+0.077blend1.869genu1.493
best-of-4rew·all1.705invWER1.000WER0.000prompt-sim+0.174blend4.368genu1.317
CCcca_voicenet_10276_cc cca_voicenet
SAY: I swear, if that package doesn't show up today, I'll—but no, it's coming. They promised. And my granddaughter painted me a card, you know? She's seven. She uses too much glitter. I'll keep it forever. It's just... the card. That's all I hav
original DramaBox prompt & direction text

Full DramaBox prompt (how to say — with the "quoted" dialogue):
A very old man with a brisk, forward-pushing tempo, a low, resonant but tremulous and breathy voice, delivering this high-quality studio voice recording with no background noise. The same voice is impatient and irritable but threaded with hope and affection, as if waiting for something anticipated. "I swear, if that package doesn't show up today, I'll—but no, it's coming. They promised. And my granddaughter painted me a card, you know? She's seven. She uses too much glitter." (pause) "I'll keep it forever." CUT TO: The same voice now hollowed by grief, the hope drained away, speaking with a fragile, stunned quiet. "It's just... the card. That's all I have now. The glitter's still on my fingers. She was supposed to be here. She was supposed to—" (weakly) "—be here." The performance across both moments should feel like a single natural breath, from bustling expectancy to devastation, with the same old-man tremor and storybook cadence carrying through both.

Direction only (dialogue removed — this is what prompt-sim compares against):
A very old man with a brisk, forward-pushing tempo, a low, resonant but tremulous and breathy voice, delivering this high-quality studio voice recording with no background noise. The same voice is impatient and irritable but threaded with hope and affection, as if waiting for something anticipated. (pause) CUT TO: The same voice now hollowed by grief, the hope drained away, speaking with a fragile, stunned quiet. (weakly) The performance across both moments should feel like a single natural breath, from bustling expectancy to devastation, with the same old-man tremor and storybook cadence carrying through both.

What to say (goes in MOSS text field): I swear, if that package doesn't show up today, I'll—but no, it's coming. They promised. And my granddaughter painted me a card, you know? She's seven. She uses too much glitter. I'll keep it forever. It's just... the card. That's all I have now. The glitter's still on my fingers. She was supposed to be here. She was supposed to— —be here.

with_dialogue · no_ref
prompt-sim × invWER
best-of-16rew·ps0.172invWER0.901WER0.099prompt-sim+0.190blend0.853genu1.268
best-of-8rew·ps0.161invWER0.958WER0.042prompt-sim+0.168blend2.008genu1.436
best-of-6rew·ps0.086invWER1.000WER0.000prompt-sim+0.086blend1.493genu1.659
best-of-4rew·ps0.064invWER0.648WER0.352prompt-sim+0.098blend0.059genu0.419
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all1.679invWER1.000WER0.000prompt-sim+0.166blend3.393genu1.901
best-of-8rew·all1.679invWER1.000WER0.000prompt-sim+0.166blend3.393genu1.901
best-of-6rew·all1.393invWER0.958WER0.042prompt-sim+0.168blend2.008genu1.436
best-of-4rew·all1.233invWER1.000WER0.000prompt-sim+0.135blend0.777genu1.144
with_dialogue · emo_ref
prompt-sim × invWER
best-of-16rew·ps0.196invWER1.000WER0.000prompt-sim+0.196blend4.644genu1.332
best-of-8rew·ps0.196invWER1.000WER0.000prompt-sim+0.196blend4.644genu1.332
best-of-6rew·ps0.196invWER1.000WER0.000prompt-sim+0.196blend4.644genu1.332
best-of-4rew·ps0.196invWER1.000WER0.000prompt-sim+0.196blend4.644genu1.332
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all1.764invWER1.000WER0.000prompt-sim+0.196blend4.644genu1.332
best-of-8rew·all1.764invWER1.000WER0.000prompt-sim+0.196blend4.644genu1.332
best-of-6rew·all1.764invWER1.000WER0.000prompt-sim+0.196blend4.644genu1.332
best-of-4rew·all1.559invWER1.000WER0.000prompt-sim+0.155blend3.083genu1.446
no_dialogue · no_ref
prompt-sim × invWER
best-of-16rew·ps0.227invWER0.915WER0.085prompt-sim+0.247blend0.406genu0.648
best-of-8rew·ps0.161invWER0.915WER0.085prompt-sim+0.176blend0.026genu1.416
best-of-6rew·ps0.161invWER0.915WER0.085prompt-sim+0.176blend0.026genu1.416
best-of-4rew·ps0.154invWER0.704WER0.296prompt-sim+0.218blend2.455genu1.569
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all1.836invWER0.915WER0.085prompt-sim+0.126blend7.443genu1.429
best-of-8rew·all1.836invWER0.915WER0.085prompt-sim+0.126blend7.443genu1.429
best-of-6rew·all1.143invWER0.915WER0.085prompt-sim+0.247blend0.406genu0.648
best-of-4rew·all1.143invWER0.915WER0.085prompt-sim+0.247blend0.406genu0.648
no_dialogue · emo_ref
prompt-sim × invWER
best-of-16rew·ps0.243invWER0.944WER0.056prompt-sim+0.257blend5.865genu1.804
best-of-8rew·ps0.150invWER0.972WER0.028prompt-sim+0.154blend0.000genu0.862
best-of-6rew·ps0.086invWER0.887WER0.113prompt-sim+0.097blend5.401genu1.631
best-of-4rew·ps0.150invWER0.972WER0.028prompt-sim+0.154blend0.000genu0.862
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all1.931invWER0.944WER0.056prompt-sim+0.257blend5.865genu1.804
best-of-8rew·all1.931invWER0.944WER0.056prompt-sim+0.257blend5.865genu1.804
best-of-6rew·all1.264invWER1.000WER0.000prompt-sim+0.218blend0.250genu1.083
best-of-4rew·all1.931invWER0.944WER0.056prompt-sim+0.257blend5.865genu1.804
CCcca_voicenet_2546_cc cca_voicenet
SAY: The door slammed shut behind me and I knew there was no turning back, I found the switch and the whole room flooded with light—I did it. And then nothing, just the silence and the dust settling, I sat down on the floor and couldn't move for
original DramaBox prompt & direction text

Full DramaBox prompt (how to say — with the "quoted" dialogue):
A very old feminine voice with a reedy, breathy quality and a pronounced physiological tremor, the mask resonance overwhelmingly bright yet the entire recording is severely degraded, sounding like a low-bitrate file with heavy background hum. The same voice is trembling with raw fear, yet a fierce thread of triumph cuts through her unsteady breath as she narrates a narrow escape. (She speaks as if reliving a harrowing moment, her breath catching, but a grim smile breaking through the tremor) "The door slammed shut behind me and I knew there was no turning back, I found the switch and the whole room flooded with light—I did it." CUT TO: The same voice now drained of all that fire, heavy with the stunned exhaustion of aftermath, the tremor more pronounced as if each word costs her. (Her voice cracks and slows, the labored breath audible between syllables as she stares at nothing) "And then nothing, just the silence and the dust settling, I sat down on the floor and couldn't move for a long time." The performance across both moments should feel like a survivor recounting a single ordeal from the peak of adrenaline through the collapse into hollow stillness.

Direction only (dialogue removed — this is what prompt-sim compares against):
A very old feminine voice with a reedy, breathy quality and a pronounced physiological tremor, the mask resonance overwhelmingly bright yet the entire recording is severely degraded, sounding like a low-bitrate file with heavy background hum. The same voice is trembling with raw fear, yet a fierce thread of triumph cuts through her unsteady breath as she narrates a narrow escape. (She speaks as if reliving a harrowing moment, her breath catching, but a grim smile breaking through the tremor) CUT TO: The same voice now drained of all that fire, heavy with the stunned exhaustion of aftermath, the tremor more pronounced as if each word costs her. (Her voice cracks and slows, the labored breath audible between syllables as she stares at nothing) The performance across both moments should feel like a survivor recounting a single ordeal from the peak of adrenaline through the collapse into hollow stillness.

What to say (goes in MOSS text field): The door slammed shut behind me and I knew there was no turning back, I found the switch and the whole room flooded with light—I did it. And then nothing, just the silence and the dust settling, I sat down on the floor and couldn't move for a long time.

with_dialogue · no_ref
prompt-sim × invWER
best-of-16rew·ps0.052invWER0.731WER0.269prompt-sim+0.071blend6.269genu1.402
best-of-8rew·ps-0.003invWER1.000WER0.000prompt-sim-0.003blend4.432genu1.417
best-of-6rew·ps0.048invWER1.000WER0.000prompt-sim+0.048blend2.166genu0.522
best-of-4rew·ps0.009invWER1.000WER0.000prompt-sim+0.009blend3.022genu1.339
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all1.516invWER1.000WER0.000prompt-sim-0.003blend4.432genu1.417
best-of-8rew·all1.516invWER1.000WER0.000prompt-sim-0.003blend4.432genu1.417
best-of-6rew·all1.507invWER1.000WER0.000prompt-sim+0.007blend4.490genu1.248
best-of-4rew·all1.507invWER1.000WER0.000prompt-sim+0.007blend4.490genu1.248
with_dialogue · emo_ref
prompt-sim × invWER
best-of-16rew·ps0.057invWER1.000WER0.000prompt-sim+0.057blend1.187genu1.627
best-of-8rew·ps-0.036invWER0.481WER0.519prompt-sim-0.075blend1.684genu1.108
best-of-6rew·ps0.057invWER1.000WER0.000prompt-sim+0.057blend1.187genu1.627
best-of-4rew·ps-0.071invWER1.000WER0.000prompt-sim-0.071blend0.793genu2.118
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all1.261invWER1.000WER0.000prompt-sim+0.057blend1.187genu1.627
best-of-8rew·all1.238invWER0.981WER0.019prompt-sim-0.145blend3.656genu1.430
best-of-6rew·all1.102invWER1.000WER0.000prompt-sim-0.072blend1.282genu1.538
best-of-4rew·all1.238invWER0.981WER0.019prompt-sim-0.145blend3.656genu1.430
no_dialogue · no_ref
prompt-sim × invWER
best-of-16rew·ps0.087invWER1.000WER0.000prompt-sim+0.087blend2.316genu0.753
best-of-8rew·ps0.020invWER1.000WER0.000prompt-sim+0.020blend1.221genu0.922
best-of-6rew·ps0.020invWER1.000WER0.000prompt-sim+0.020blend1.221genu0.922
best-of-4rew·ps-0.000invWER0.000WER1.000prompt-sim-0.152blend4.923genu1.617
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all1.680invWER1.000WER0.000prompt-sim-0.004blend5.801genu1.501
best-of-8rew·all1.527invWER1.000WER0.000prompt-sim+0.018blend4.810genu1.056
best-of-6rew·all1.527invWER1.000WER0.000prompt-sim+0.018blend4.810genu1.056
best-of-4rew·all1.318invWER1.000WER0.000prompt-sim+0.056blend1.818genu1.555
no_dialogue · emo_ref
prompt-sim × invWER
best-of-8rew·ps0.082invWER0.981WER0.019prompt-sim+0.084blend0.408genu1.127
best-of-6rew·ps0.105invWER0.635WER0.365prompt-sim+0.165blend0.227genu1.009
best-of-4rew·ps0.082invWER0.981WER0.019prompt-sim+0.084blend0.408genu1.127
invWER × (norm prompt-sim + blend + genu)
best-of-8rew·all1.405invWER0.962WER0.038prompt-sim-0.122blend4.511genu1.925
best-of-6rew·all0.999invWER1.000WER0.000prompt-sim-0.189blend0.583genu2.269
best-of-4rew·all1.267invWER1.000WER0.000prompt-sim-0.003blend2.753genu1.014
CCcc2c_archetype_8315_cc cc2c_archetype
SAY: I just... I thought the chart was for room three. But the numbers didn't line up. I'm sorry, I should have double-checked. I don't know what I was thinking. No, that's not acceptable. I need the real numbers now. You will explain this to me
original DramaBox prompt & direction text

Full DramaBox prompt (how to say — with the "quoted" dialogue):
A 27-year-old female with a hushed, slightly breathy timbre, delivering this high-quality studio voice recording with no background noise. The same voice is frozen in confusion and embarrassment, speaking with agonizing restraint as she tries to justify a mistake. (voice barely above a whisper) "I just... I thought the chart was for room three." (swallows hard) "But the numbers didn't line up." (glances at the floor) "I'm sorry, I should have double-checked." (trails off) "I don't know what I was thinking." CUT TO: The same voice now sharp with indignation and sudden clarity, speaking with cold, restrained fury. (stares directly ahead) "No, that's not acceptable. I need the real numbers now." (firmly) "You will explain this to me right now." (flat but intense) "I've had enough of the confusion." The performance across both moments should feel like the same person transforming from paralyzed self-doubt to assertive clarity.

Direction only (dialogue removed — this is what prompt-sim compares against):
A 27-year-old female with a hushed, slightly breathy timbre, delivering this high-quality studio voice recording with no background noise. The same voice is frozen in confusion and embarrassment, speaking with agonizing restraint as she tries to justify a mistake. (voice barely above a whisper) (swallows hard) (glances at the floor) (trails off) CUT TO: The same voice now sharp with indignation and sudden clarity, speaking with cold, restrained fury. (stares directly ahead) (firmly) (flat but intense) The performance across both moments should feel like the same person transforming from paralyzed self-doubt to assertive clarity.

What to say (goes in MOSS text field): I just... I thought the chart was for room three. But the numbers didn't line up. I'm sorry, I should have double-checked. I don't know what I was thinking. No, that's not acceptable. I need the real numbers now. You will explain this to me right now. I've had enough of the confusion.

with_dialogue · no_ref
prompt-sim × invWER
best-of-16rew·ps0.227invWER1.000WER0.000prompt-sim+0.227blend4.672genu1.409
best-of-8rew·ps0.123invWER1.000WER0.000prompt-sim+0.123blend2.520genu1.877
best-of-6rew·ps0.227invWER1.000WER0.000prompt-sim+0.227blend4.672genu1.409
best-of-4rew·ps0.196invWER1.000WER0.000prompt-sim+0.196blend6.793genu1.694
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all2.059invWER1.000WER0.000prompt-sim+0.196blend6.793genu1.694
best-of-8rew·all2.059invWER1.000WER0.000prompt-sim+0.196blend6.793genu1.694
best-of-6rew·all2.059invWER1.000WER0.000prompt-sim+0.196blend6.793genu1.694
best-of-4rew·all2.059invWER1.000WER0.000prompt-sim+0.196blend6.793genu1.694
with_dialogue · emo_ref
prompt-sim × invWER
best-of-16rew·ps0.062invWER1.000WER0.000prompt-sim+0.062blend1.114genu1.457
best-of-8rew·ps0.062invWER1.000WER0.000prompt-sim+0.062blend1.114genu1.457
best-of-6rew·ps0.041invWER0.661WER0.339prompt-sim+0.062blend1.990genu2.423
best-of-4rew·ps0.012invWER0.983WER0.017prompt-sim+0.013blend2.841genu2.983
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all1.575invWER0.983WER0.017prompt-sim+0.013blend2.841genu2.983
best-of-8rew·all1.514invWER1.000WER0.000prompt-sim-0.076blend2.230genu3.530
best-of-6rew·all1.575invWER0.983WER0.017prompt-sim+0.013blend2.841genu2.983
best-of-4rew·all1.501invWER0.983WER0.017prompt-sim-0.180blend0.967genu5.304
no_dialogue · no_ref
prompt-sim × invWER
best-of-16rew·ps0.145invWER0.983WER0.017prompt-sim+0.147blend7.364genu2.058
best-of-8rew·ps0.145invWER0.983WER0.017prompt-sim+0.147blend7.364genu2.058
best-of-6rew·ps0.145invWER0.983WER0.017prompt-sim+0.147blend7.364genu2.058
best-of-4rew·ps0.145invWER0.983WER0.017prompt-sim+0.147blend7.364genu2.058
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all2.085invWER0.983WER0.017prompt-sim+0.147blend7.364genu2.058
best-of-8rew·all1.569invWER0.881WER0.119prompt-sim+0.080blend4.948genu2.107
best-of-6rew·all2.085invWER0.983WER0.017prompt-sim+0.147blend7.364genu2.058
best-of-4rew·all1.196invWER0.831WER0.170prompt-sim+0.028blend2.954genu1.747
no_dialogue · emo_ref
prompt-sim × invWER
best-of-16rew·ps0.089invWER0.983WER0.017prompt-sim+0.091blend2.289genu1.352
best-of-8rew·ps-0.018invWER0.068WER0.932prompt-sim-0.266blend2.550genu3.291
best-of-6rew·ps-0.034invWER0.170WER0.831prompt-sim-0.199blend0.000genu1.254
best-of-4rew·ps0.089invWER0.983WER0.017prompt-sim+0.091blend2.289genu1.352
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all1.568invWER1.000WER0.000prompt-sim-0.164blend3.218genu3.854
best-of-8rew·all1.471invWER1.000WER0.000prompt-sim-0.165blend0.688genu5.035
best-of-6rew·all1.471invWER1.000WER0.000prompt-sim-0.165blend0.688genu5.035
best-of-4rew·all1.568invWER1.000WER0.000prompt-sim-0.164blend3.218genu3.854
CCcc2c_archetype_4348_cc cc2c_archetype
SAY: This bloodwork should've been flagged two hours ago. Who signed off on this? Come on, people. We did everything... everything right. Why does that never feel like enough?
original DramaBox prompt & direction text

Full DramaBox prompt (how to say — with the "quoted" dialogue):
A 34-year-old woman with a tight, slightly clipped voice, delivering this high-quality studio voice recording with no background noise. The same voice is bristling with controlled impatience, barely tolerating a delay in her morning rounds. (tapping a pen against a clipboard) "This bloodwork should've been flagged two hours ago." (glancing at a chart) "Who signed off on this? Come on, people." CUT TO: The same voice now dissolves into raw grief, caught off guard by a patient's sudden death on the table. (a long pause, then a whisper) "We did everything... everything right." (voice cracks) "Why does that never feel like enough?" The performance across both moments should feel like a mask of professionalism cracking open into unguarded sorrow.

Direction only (dialogue removed — this is what prompt-sim compares against):
A 34-year-old woman with a tight, slightly clipped voice, delivering this high-quality studio voice recording with no background noise. The same voice is bristling with controlled impatience, barely tolerating a delay in her morning rounds. (tapping a pen against a clipboard) (glancing at a chart) CUT TO: The same voice now dissolves into raw grief, caught off guard by a patient's sudden death on the table. (a long pause, then a whisper) (voice cracks) The performance across both moments should feel like a mask of professionalism cracking open into unguarded sorrow.

What to say (goes in MOSS text field): This bloodwork should've been flagged two hours ago. Who signed off on this? Come on, people. We did everything... everything right. Why does that never feel like enough?

with_dialogue · no_ref
prompt-sim × invWER
best-of-16rew·ps0.103invWER0.897WER0.103prompt-sim+0.115blend0.709genu0.467
best-of-8rew·ps0.036invWER0.897WER0.103prompt-sim+0.040blend6.018genu1.282
best-of-6rew·ps0.103invWER0.897WER0.103prompt-sim+0.115blend0.709genu0.467
best-of-4rew·ps0.036invWER0.897WER0.103prompt-sim+0.040blend6.018genu1.282
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all1.544invWER0.897WER0.103prompt-sim+0.040blend6.018genu1.282
best-of-8rew·all1.544invWER0.897WER0.103prompt-sim+0.040blend6.018genu1.282
best-of-6rew·all1.544invWER0.897WER0.103prompt-sim+0.040blend6.018genu1.282
best-of-4rew·all0.871invWER0.897WER0.103prompt-sim-0.011blend1.047genu0.397
with_dialogue · emo_ref
prompt-sim × invWER
best-of-16rew·ps-0.000invWER0.000WER1.000prompt-sim-0.211blend2.652genu1.149
best-of-8rew·ps-0.000invWER0.000WER1.000prompt-sim-0.068blend0.534genu0.947
best-of-6rew·ps-0.155invWER0.655WER0.345prompt-sim-0.237blend0.507genu2.928
best-of-4rew·ps-0.000invWER0.000WER1.000prompt-sim-0.211blend2.652genu1.149
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all1.057invWER0.793WER0.207prompt-sim-0.238blend2.467genu3.445
best-of-8rew·all1.057invWER0.793WER0.207prompt-sim-0.238blend2.467genu3.445
best-of-6rew·all1.057invWER0.793WER0.207prompt-sim-0.238blend2.467genu3.445
best-of-4rew·all0.941invWER0.897WER0.103prompt-sim-0.350blend0.306genu4.023
no_dialogue · no_ref
prompt-sim × invWER
best-of-16rew·ps0.000invWER0.655WER0.345prompt-sim+0.001blend1.948genu1.417
best-of-8rew·ps-0.000invWER0.000WER1.000prompt-sim-0.057blend1.871genu1.331
best-of-6rew·ps-0.000invWER0.000WER1.000prompt-sim-0.057blend1.871genu1.331
best-of-4rew·ps-0.022invWER0.483WER0.517prompt-sim-0.047blend5.689genu1.516
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all0.999invWER0.897WER0.103prompt-sim-0.038blend1.265genu1.365
best-of-8rew·all0.999invWER0.897WER0.103prompt-sim-0.038blend1.265genu1.365
best-of-6rew·all0.781invWER0.483WER0.517prompt-sim-0.047blend5.689genu1.516
best-of-4rew·all0.999invWER0.897WER0.103prompt-sim-0.038blend1.265genu1.365
no_dialogue · emo_ref
prompt-sim × invWER
best-of-16rew·ps-0.000invWER0.000WER1.000prompt-sim-0.312blend0.102genu0.923
best-of-8rew·ps-0.000invWER0.000WER1.000prompt-sim-0.202blend0.936genu2.215
best-of-6rew·ps-0.000invWER0.000WER1.000prompt-sim-0.202blend0.936genu2.215
best-of-4rew·ps-0.000invWER0.000WER1.000prompt-sim-0.202blend0.936genu2.215
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all1.063invWER0.828WER0.172prompt-sim-0.214blend1.357genu3.740
best-of-8rew·all0.657invWER0.897WER0.103prompt-sim-0.477blend0.469genu2.858
best-of-6rew·all0.721invWER0.897WER0.103prompt-sim-0.353blend0.398genu2.413
best-of-4rew·all1.063invWER0.828WER0.172prompt-sim-0.214blend1.357genu3.740
CCcc2c_archetype_5709_cc cc2c_archetype
SAY: It's... still glowing. Even after all this time. I could kneel here forever, you know. But it wouldn't bring her back. Oh, you thought I was done? Darling. I was just remembering what I'm about to take from you.
original DramaBox prompt & direction text

Full DramaBox prompt (how to say — with the "quoted" dialogue):
A 30-year-old woman with a low, velvet-smooth purr that holds a hint of danger, delivering this high-quality studio voice recording with no background noise. The same voice is staring at something beautiful but lost, awe mixing with a deep sorrow that makes her whisper, exhaustion dragging at her words. (slow exhale, almost a sigh) "It's... still glowing. Even after all this time." (a tiny, broken laugh) "I could kneel here forever, you know." (voice cracks slightly) "But it wouldn't bring her back." CUT TO: The same voice now sharpens into a predator's grin, exhaustion gone, replaced by a cold, delighted thrill as she tightens her grip. (a sharp inhale, then a silky low murmur) "Oh, you thought I was done? Darling." (soft chuckle, dangerous) "I was just remembering what I'm about to take from you." The performance across both moments should feel like the same woman is unraveling her grief and then instantly weaponizing it, the transition so seamless it's terrifying.

Direction only (dialogue removed — this is what prompt-sim compares against):
A 30-year-old woman with a low, velvet-smooth purr that holds a hint of danger, delivering this high-quality studio voice recording with no background noise. The same voice is staring at something beautiful but lost, awe mixing with a deep sorrow that makes her whisper, exhaustion dragging at her words. (slow exhale, almost a sigh) (a tiny, broken laugh) (voice cracks slightly) CUT TO: The same voice now sharpens into a predator's grin, exhaustion gone, replaced by a cold, delighted thrill as she tightens her grip. (a sharp inhale, then a silky low murmur) (soft chuckle, dangerous) The performance across both moments should feel like the same woman is unraveling her grief and then instantly weaponizing it, the transition so seamless it's terrifying.

What to say (goes in MOSS text field): It's... still glowing. Even after all this time. I could kneel here forever, you know. But it wouldn't bring her back. Oh, you thought I was done? Darling. I was just remembering what I'm about to take from you.

with_dialogue · no_ref
prompt-sim × invWER
best-of-16rew·ps0.112invWER0.786WER0.214prompt-sim+0.142blend3.415genu1.953
best-of-8rew·ps0.104invWER0.952WER0.048prompt-sim+0.110blend1.643genu1.491
best-of-6rew·ps0.104invWER0.952WER0.048prompt-sim+0.110blend1.643genu1.491
best-of-4rew·ps0.104invWER0.952WER0.048prompt-sim+0.110blend1.643genu1.491
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all1.931invWER0.952WER0.048prompt-sim+0.101blend6.927genu2.129
best-of-8rew·all1.931invWER0.952WER0.048prompt-sim+0.101blend6.927genu2.129
best-of-6rew·all1.304invWER0.786WER0.214prompt-sim+0.142blend3.415genu1.953
best-of-4rew·all1.129invWER1.000WER0.000prompt-sim-0.033blend1.556genu1.212
with_dialogue · emo_ref
prompt-sim × invWER
best-of-16rew·ps0.064invWER0.452WER0.548prompt-sim+0.141blend0.775genu1.869
best-of-8rew·ps0.064invWER0.452WER0.548prompt-sim+0.141blend0.775genu1.869
best-of-6rew·ps0.012invWER0.095WER0.905prompt-sim+0.125blend0.706genu1.469
best-of-4rew·ps0.012invWER0.095WER0.905prompt-sim+0.125blend0.706genu1.469
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all1.353invWER1.000WER0.000prompt-sim-0.371blend2.951genu4.248
best-of-8rew·all1.353invWER1.000WER0.000prompt-sim-0.371blend2.951genu4.248
best-of-6rew·all1.105invWER0.691WER0.309prompt-sim-0.098blend2.264genu4.228
best-of-4rew·all1.105invWER0.691WER0.309prompt-sim-0.098blend2.264genu4.228
no_dialogue · no_ref
prompt-sim × invWER
best-of-16rew·ps0.077invWER0.429WER0.571prompt-sim+0.180blend6.172genu1.608
best-of-8rew·ps0.077invWER0.429WER0.571prompt-sim+0.180blend6.172genu1.608
best-of-6rew·ps0.077invWER0.429WER0.571prompt-sim+0.180blend6.172genu1.608
best-of-4rew·ps0.044invWER0.333WER0.667prompt-sim+0.133blend6.963genu1.270
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all1.470invWER0.952WER0.048prompt-sim+0.076blend3.817genu1.427
best-of-8rew·all1.470invWER0.952WER0.048prompt-sim+0.076blend3.817genu1.427
best-of-6rew·all1.470invWER0.952WER0.048prompt-sim+0.076blend3.817genu1.427
best-of-4rew·all0.965invWER0.952WER0.048prompt-sim+0.024blend0.249genu0.966
no_dialogue · emo_ref
prompt-sim × invWER
best-of-16rew·ps0.002invWER0.071WER0.929prompt-sim+0.030blend0.000genu2.068
best-of-8rew·ps-0.000invWER0.000WER1.000prompt-sim-0.016blend1.702genu1.098
best-of-6rew·ps0.002invWER0.071WER0.929prompt-sim+0.030blend0.000genu2.068
best-of-4rew·ps0.000invWER0.000WER1.000prompt-sim+0.084blend0.000genu1.451
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all1.130invWER0.952WER0.048prompt-sim-0.149blend1.101genu2.797
best-of-8rew·all0.870invWER0.595WER0.405prompt-sim-0.039blend3.340genu2.126
best-of-6rew·all0.870invWER0.595WER0.405prompt-sim-0.039blend3.340genu2.126
best-of-4rew·all0.758invWER1.000WER0.000prompt-sim-0.295blend0.000genu1.948
CCaccc_acting_challenge_7796_cc accc_acting_challenge
SAY: I was seven. I sat by the window every day after school. I thought you'd just been delayed. If I forgive you… does that mean what you did was okay? Was I that difficult to love?
original DramaBox prompt & direction text

Full DramaBox prompt (how to say — with the "quoted" dialogue):
A 34-year-old woman with a voice that is clear and measured, carrying a faint tremor of old hurt, delivering this high-quality studio voice recording with no background noise. The same voice is tightly controlled, as if she has rehearsed these words for years, but the stillness is brittle. (quiet, deliberate) "I was seven. I sat by the window every day after school." (a slow, measured exhale) "I thought you'd just been delayed." CUT TO: The same voice now cracks open into raw, childlike devastation, the adult composure gone. (voice breaking, barely a whisper) "If I forgive you… does that mean what you did was okay?" (a long, shuddering pause) "Was I that difficult to love?" The performance across both moments should feel like a dam breaking—from a rigid facade of composure to the naked, unfiltered ache of a child who never stopped waiting.

Direction only (dialogue removed — this is what prompt-sim compares against):
A 34-year-old woman with a voice that is clear and measured, carrying a faint tremor of old hurt, delivering this high-quality studio voice recording with no background noise. The same voice is tightly controlled, as if she has rehearsed these words for years, but the stillness is brittle. (quiet, deliberate) (a slow, measured exhale) CUT TO: The same voice now cracks open into raw, childlike devastation, the adult composure gone. (voice breaking, barely a whisper) (a long, shuddering pause) The performance across both moments should feel like a dam breaking—from a rigid facade of composure to the naked, unfiltered ache of a child who never stopped waiting.

What to say (goes in MOSS text field): I was seven. I sat by the window every day after school. I thought you'd just been delayed. If I forgive you… does that mean what you did was okay? Was I that difficult to love?

with_dialogue · no_ref
prompt-sim × invWER
best-of-16rew·ps0.107invWER1.000WER0.000prompt-sim+0.107blend2.222genu1.273
best-of-8rew·ps0.107invWER1.000WER0.000prompt-sim+0.107blend2.222genu1.273
best-of-6rew·ps0.065invWER0.676WER0.324prompt-sim+0.097blend1.590genu0.606
best-of-4rew·ps0.065invWER0.676WER0.324prompt-sim+0.097blend1.590genu0.606
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all1.590invWER1.000WER0.000prompt-sim-0.044blend5.285genu1.599
best-of-8rew·all1.380invWER1.000WER0.000prompt-sim+0.107blend2.222genu1.273
best-of-6rew·all1.590invWER1.000WER0.000prompt-sim-0.044blend5.285genu1.599
best-of-4rew·all0.968invWER0.676WER0.324prompt-sim+0.047blend3.293genu1.310
with_dialogue · emo_ref
prompt-sim × invWER
best-of-16rew·ps0.031invWER1.000WER0.000prompt-sim+0.031blend1.082genu1.528
best-of-8rew·ps0.031invWER1.000WER0.000prompt-sim+0.031blend1.082genu1.528
best-of-6rew·ps0.027invWER0.351WER0.649prompt-sim+0.077blend6.209genu1.910
best-of-4rew·ps-0.000invWER0.000WER1.027prompt-sim-0.016blend1.456genu0.748
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all1.202invWER1.000WER0.000prompt-sim+0.031blend1.082genu1.528
best-of-8rew·all1.202invWER1.000WER0.000prompt-sim+0.031blend1.082genu1.528
best-of-6rew·all1.202invWER1.000WER0.000prompt-sim+0.031blend1.082genu1.528
best-of-4rew·all0.900invWER1.000WER0.000prompt-sim-0.176blend1.055genu1.199
no_dialogue · no_ref
prompt-sim × invWER
best-of-16rew·ps0.133invWER1.000WER0.000prompt-sim+0.133blend3.334genu1.426
best-of-8rew·ps0.133invWER1.000WER0.000prompt-sim+0.133blend3.334genu1.426
best-of-6rew·ps0.030invWER1.000WER0.000prompt-sim+0.030blend2.487genu0.885
best-of-4rew·ps0.086invWER1.000WER0.000prompt-sim+0.086blend5.675genu1.374
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all1.794invWER1.000WER0.000prompt-sim+0.003blend6.074genu1.991
best-of-8rew·all1.598invWER1.000WER0.000prompt-sim+0.119blend3.879genu1.401
best-of-6rew·all1.558invWER1.000WER0.000prompt-sim+0.133blend3.334genu1.426
best-of-4rew·all1.794invWER1.000WER0.000prompt-sim+0.003blend6.074genu1.991
no_dialogue · emo_ref
prompt-sim × invWER
best-of-16rew·ps0.100invWER1.000WER0.000prompt-sim+0.100blend4.862genu1.528
best-of-8rew·ps0.100invWER1.000WER0.000prompt-sim+0.100blend4.862genu1.528
best-of-6rew·ps-0.000invWER0.000WER1.000prompt-sim-0.146blend0.235genu0.146
best-of-4rew·ps0.100invWER1.000WER0.000prompt-sim+0.100blend4.862genu1.528
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all1.704invWER1.000WER0.000prompt-sim+0.100blend4.862genu1.528
best-of-8rew·all1.704invWER1.000WER0.000prompt-sim+0.100blend4.862genu1.528
best-of-6rew·all1.704invWER1.000WER0.000prompt-sim+0.100blend4.862genu1.528
best-of-4rew·all1.182invWER1.000WER0.000prompt-sim-0.087blend1.868genu1.752
CCaccc_acting_challenge_1558_cc accc_acting_challenge
SAY: I thought I'd feel... more. More tears, more ache. Just dust motes in the sun. God, the quiet isn't heavy. It's just... air. I can walk loud now. No one to hear.
original DramaBox prompt & direction text

Full DramaBox prompt (how to say — with the "quoted" dialogue):
A 38-year-old woman with a warm but weary timbre, delivering this high-quality studio voice recording with no background noise. The same voice is struggling to hold onto a practiced sadness, but the familiar silence is making her unexpectedly restless. (letting out a slow breath) "I thought I'd feel... more. More tears, more ache." (pausing, listening to the creak) "Just dust motes in the sun." CUT TO: The same voice now lets out a surprised, private laugh as the emptiness finally feels like permission. (shaking her head, almost amused) "God, the quiet isn't heavy. It's just... air." (hearing her own footsteps) "I can walk loud now. No one to hear." The performance across both moments should feel like a single person slowly untangling grief from relief, each breath a small discovery.

Direction only (dialogue removed — this is what prompt-sim compares against):
A 38-year-old woman with a warm but weary timbre, delivering this high-quality studio voice recording with no background noise. The same voice is struggling to hold onto a practiced sadness, but the familiar silence is making her unexpectedly restless. (letting out a slow breath) (pausing, listening to the creak) CUT TO: The same voice now lets out a surprised, private laugh as the emptiness finally feels like permission. (shaking her head, almost amused) (hearing her own footsteps) The performance across both moments should feel like a single person slowly untangling grief from relief, each breath a small discovery.

What to say (goes in MOSS text field): I thought I'd feel... more. More tears, more ache. Just dust motes in the sun. God, the quiet isn't heavy. It's just... air. I can walk loud now. No one to hear.

with_dialogue · no_ref
prompt-sim × invWER
best-of-16rew·ps0.094invWER0.686WER0.314prompt-sim+0.137blend6.718genu1.885
best-of-8rew·ps0.057invWER0.943WER0.057prompt-sim+0.060blend3.854genu1.739
best-of-6rew·ps0.057invWER0.943WER0.057prompt-sim+0.060blend3.854genu1.739
best-of-4rew·ps0.038invWER0.286WER0.714prompt-sim+0.132blend8.351genu1.857
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all1.488invWER0.943WER0.057prompt-sim+0.060blend3.854genu1.739
best-of-8rew·all1.378invWER0.686WER0.314prompt-sim+0.137blend6.718genu1.885
best-of-6rew·all1.488invWER0.943WER0.057prompt-sim+0.060blend3.854genu1.739
best-of-4rew·all0.855invWER0.429WER0.571prompt-sim+0.060blend7.811genu1.605
with_dialogue · emo_ref
prompt-sim × invWER
best-of-16rew·ps0.065invWER0.543WER0.457prompt-sim+0.120blend4.000genu1.283
best-of-8rew·ps0.065invWER0.543WER0.457prompt-sim+0.120blend4.000genu1.283
best-of-6rew·ps0.011invWER0.343WER0.657prompt-sim+0.032blend6.676genu1.744
best-of-4rew·ps-0.000invWER0.000WER1.114prompt-sim-0.364blend0.173genu2.129
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all1.390invWER0.971WER0.029prompt-sim-0.141blend4.298genu2.030
best-of-8rew·all1.304invWER1.000WER0.000prompt-sim-0.059blend3.006genu1.508
best-of-6rew·all1.390invWER0.971WER0.029prompt-sim-0.141blend4.298genu2.030
best-of-4rew·all0.637invWER0.343WER0.657prompt-sim+0.032blend6.676genu1.744
no_dialogue · no_ref
prompt-sim × invWER
best-of-16rew·ps0.099invWER0.714WER0.286prompt-sim+0.139blend7.120genu1.689
best-of-8rew·ps0.058invWER0.543WER0.457prompt-sim+0.107blend3.811genu1.464
best-of-6rew·ps0.031invWER0.600WER0.400prompt-sim+0.051blend6.925genu1.359
best-of-4rew·ps0.099invWER0.714WER0.286prompt-sim+0.139blend7.120genu1.689
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all1.515invWER0.971WER0.029prompt-sim-0.026blend4.852genu1.576
best-of-8rew·all1.515invWER0.971WER0.029prompt-sim-0.026blend4.852genu1.576
best-of-6rew·all1.036invWER0.600WER0.400prompt-sim+0.065blend5.828genu1.256
best-of-4rew·all0.861invWER0.543WER0.457prompt-sim+0.107blend3.811genu1.464
no_dialogue · emo_ref
prompt-sim × invWER
best-of-16rew·ps0.018invWER0.686WER0.314prompt-sim+0.027blend3.409genu1.526
best-of-8rew·ps0.002invWER0.029WER0.971prompt-sim+0.066blend1.708genu0.972
best-of-6rew·ps0.000invWER0.000WER1.000prompt-sim+0.097blend2.221genu1.405
best-of-4rew·ps0.000invWER0.000WER1.000prompt-sim+0.002blend2.065genu0.865
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all1.115invWER0.971WER0.029prompt-sim-0.340blend1.149genu3.978
best-of-8rew·all1.006invWER0.686WER0.314prompt-sim-0.040blend4.424genu1.399
best-of-6rew·all0.998invWER0.686WER0.314prompt-sim+0.027blend3.409genu1.526
best-of-4rew·all0.595invWER0.943WER0.057prompt-sim-0.376blend0.136genu1.660
CCaccc_acting_challenge_8508_cc accc_acting_challenge
SAY: The edges are almost translucent, a pink so pale it's barely there. It smells like rain and something sweet. I can feel every vein, like tiny rivers. I almost died for this? For this stupid, beautiful flower? And I'm supposed to be grateful
original DramaBox prompt & direction text

Full DramaBox prompt (how to say — with the "quoted" dialogue):
A 35-year-old woman with a warm, slightly raspy voice, delivering this high-quality studio voice recording with no background noise. The same voice is delicately exploring a flower with childlike wonder and fragile relief. (gently turning the flower in her palm) "The edges are almost translucent, a pink so pale it's barely there." (inhaling softly) "It smells like rain and something sweet." (brushing a petal) "I can feel every vein, like tiny rivers." CUT TO: The same voice now choked with rage and bitter grief, the wonder turned sour. (voice trembling, jaw tight) "I almost died for this? For this stupid, beautiful flower?" (a raw laugh) "And I'm supposed to be grateful?" (tears in voice) "I lost a year of my life to get here." The performance across both moments should feel like a single, fractured soul remembering how to feel everything at once.

Direction only (dialogue removed — this is what prompt-sim compares against):
A 35-year-old woman with a warm, slightly raspy voice, delivering this high-quality studio voice recording with no background noise. The same voice is delicately exploring a flower with childlike wonder and fragile relief. (gently turning the flower in her palm) (inhaling softly) (brushing a petal) CUT TO: The same voice now choked with rage and bitter grief, the wonder turned sour. (voice trembling, jaw tight) (a raw laugh) (tears in voice) The performance across both moments should feel like a single, fractured soul remembering how to feel everything at once.

What to say (goes in MOSS text field): The edges are almost translucent, a pink so pale it's barely there. It smells like rain and something sweet. I can feel every vein, like tiny rivers. I almost died for this? For this stupid, beautiful flower? And I'm supposed to be grateful? I lost a year of my life to get here.

with_dialogue · no_ref
prompt-sim × invWER
best-of-16rew·ps0.078invWER0.964WER0.036prompt-sim+0.081blend0.135genu1.049
best-of-8rew·ps0.078invWER0.964WER0.036prompt-sim+0.081blend0.135genu1.049
best-of-6rew·ps0.017invWER0.600WER0.400prompt-sim+0.028blend2.910genu1.860
best-of-4rew·ps0.059invWER0.673WER0.327prompt-sim+0.088blend5.047genu1.619
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all1.238invWER1.000WER0.000prompt-sim-0.018blend2.109genu1.405
best-of-8rew·all1.238invWER1.000WER0.000prompt-sim-0.018blend2.109genu1.405
best-of-6rew·all1.238invWER1.000WER0.000prompt-sim-0.018blend2.109genu1.405
best-of-4rew·all1.160invWER0.673WER0.327prompt-sim+0.088blend5.047genu1.619
with_dialogue · emo_ref
prompt-sim × invWER
best-of-16rew·ps0.000invWER0.109WER0.891prompt-sim+0.000blend0.737genu1.009
best-of-8rew·ps0.000invWER0.109WER0.891prompt-sim+0.000blend0.737genu1.009
best-of-6rew·ps-0.025invWER0.091WER0.909prompt-sim-0.274blend0.019genu-0.730
best-of-4rew·ps-0.034invWER0.145WER0.855prompt-sim-0.234blend0.379genu0.776
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all0.861invWER1.000WER0.000prompt-sim-0.109blend0.389genu0.904
best-of-8rew·all0.861invWER1.000WER0.000prompt-sim-0.109blend0.389genu0.904
best-of-6rew·all0.861invWER1.000WER0.000prompt-sim-0.109blend0.389genu0.904
best-of-4rew·all0.792invWER1.000WER0.000prompt-sim-0.183blend0.000genu1.312
no_dialogue · no_ref
prompt-sim × invWER
best-of-16rew·ps0.081invWER0.818WER0.182prompt-sim+0.099blend2.962genu1.527
best-of-8rew·ps0.058invWER0.818WER0.182prompt-sim+0.070blend4.704genu1.269
best-of-6rew·ps0.009invWER0.982WER0.018prompt-sim+0.009blend1.609genu1.657
best-of-4rew·ps0.081invWER0.818WER0.182prompt-sim+0.099blend2.962genu1.527
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all1.318invWER0.818WER0.182prompt-sim+0.070blend4.704genu1.269
best-of-8rew·all1.232invWER0.982WER0.018prompt-sim+0.009blend1.609genu1.657
best-of-6rew·all1.318invWER0.818WER0.182prompt-sim+0.070blend4.704genu1.269
best-of-4rew·all1.221invWER0.818WER0.182prompt-sim+0.099blend2.962genu1.527
no_dialogue · emo_ref
prompt-sim × invWER
best-of-16rew·ps0.000invWER0.000WER1.000prompt-sim+0.087blend1.419genu0.727
best-of-8rew·ps-0.001invWER0.018WER0.982prompt-sim-0.028blend2.670genu1.024
best-of-6rew·ps0.000invWER0.000WER1.000prompt-sim+0.087blend1.419genu0.727
best-of-4rew·ps0.000invWER0.000WER1.000prompt-sim+0.087blend1.419genu0.727
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all0.789invWER1.000WER0.000prompt-sim-0.138blend0.000genu0.950
best-of-8rew·all0.789invWER1.000WER0.000prompt-sim-0.138blend0.000genu0.950
best-of-6rew·all0.600invWER0.818WER0.182prompt-sim-0.272blend0.000genu1.616
best-of-4rew·all0.627invWER1.000WER0.000prompt-sim-0.302blend0.600genu0.745
CCsit_situation_287_cc sit_situation
SAY: ¡Métete con alguien de tu tamaño, pedazo de mierda! Te voy a partir la madre, escúchame bien. Te... te lo juro. Si le tocas un pelo más... te mato.
original DramaBox prompt & direction text

Full DramaBox prompt (how to say — with the "quoted" dialogue):
A 62-year-old man with a gravelly, weathered baritone, delivering this high-quality studio voice recording with no background noise. The same voice is hunched forward, fists up, spit flying as he shoves past a trash can toward a younger attacker, contempt raw and animal in his throat. (spitting between words) "¡Métete con alguien de tu tamaño, pedazo de mierda!" (swinging, breath hissing) "Te voy a partir la madre, escúchame bien." CUT TO: The same voice now crumpled on one knee, ribs on fire, jaw slack with pain as he tastes blood, exhaustion cracking his snarl into something colder, quieter. (coughing, grabbing his side) "Te... te lo juro." (voice dropping, venom trembling) "Si le tocas un pelo más... te mato." The performance across both moments should feel like a single brutal breath—venomous fury collapsing into a wounded, whispered threat, every grunt and pause earned by real damage.

Direction only (dialogue removed — this is what prompt-sim compares against):
A 62-year-old man with a gravelly, weathered baritone, delivering this high-quality studio voice recording with no background noise. The same voice is hunched forward, fists up, spit flying as he shoves past a trash can toward a younger attacker, contempt raw and animal in his throat. (spitting between words) (swinging, breath hissing) CUT TO: The same voice now crumpled on one knee, ribs on fire, jaw slack with pain as he tastes blood, exhaustion cracking his snarl into something colder, quieter. (coughing, grabbing his side) (voice dropping, venom trembling) The performance across both moments should feel like a single brutal breath—venomous fury collapsing into a wounded, whispered threat, every grunt and pause earned by real damage.

What to say (goes in MOSS text field): ¡Métete con alguien de tu tamaño, pedazo de mierda! Te voy a partir la madre, escúchame bien. Te... te lo juro. Si le tocas un pelo más... te mato.

with_dialogue · no_ref
prompt-sim × invWER
best-of-16rew·ps0.019invWER0.552WER0.448prompt-sim+0.034blend6.081genu1.416
best-of-8rew·ps0.019invWER0.552WER0.448prompt-sim+0.034blend6.081genu1.416
best-of-6rew·ps0.019invWER0.552WER0.448prompt-sim+0.034blend6.081genu1.416
best-of-4rew·ps-0.002invWER0.931WER0.069prompt-sim-0.002blend4.525genu1.239
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all1.395invWER0.931WER0.069prompt-sim-0.002blend4.525genu1.239
best-of-8rew·all1.343invWER0.931WER0.069prompt-sim-0.169blend5.297genu1.603
best-of-6rew·all1.395invWER0.931WER0.069prompt-sim-0.002blend4.525genu1.239
best-of-4rew·all1.395invWER0.931WER0.069prompt-sim-0.002blend4.525genu1.239
with_dialogue · emo_ref
prompt-sim × invWER
best-of-16rew·ps-0.000invWER0.000WER1.000prompt-sim-0.271blend3.255genu1.306
best-of-8rew·ps-0.000invWER0.000WER1.000prompt-sim-0.271blend3.255genu1.306
best-of-6rew·ps-0.100invWER0.310WER0.690prompt-sim-0.322blend2.712genu1.511
best-of-4rew·ps-0.035invWER0.310WER0.690prompt-sim-0.112blend8.366genu1.613
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all1.464invWER0.931WER0.069prompt-sim-0.219blend6.769genu1.776
best-of-8rew·all1.464invWER0.931WER0.069prompt-sim-0.219blend6.769genu1.776
best-of-6rew·all1.284invWER1.000WER0.000prompt-sim-0.127blend3.836genu1.311
best-of-4rew·all1.464invWER0.931WER0.069prompt-sim-0.219blend6.769genu1.776
no_dialogue · no_ref
prompt-sim × invWER
best-of-16rew·ps0.179invWER0.931WER0.069prompt-sim+0.193blend7.659genu0.989
best-of-8rew·ps-0.000invWER0.000WER1.000prompt-sim-0.091blend2.712genu1.924
best-of-6rew·ps-0.000invWER0.000WER1.000prompt-sim-0.010blend0.545genu0.281
best-of-4rew·ps-0.000invWER0.000WER1.000prompt-sim-0.121blend3.291genu0.758
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all1.900invWER0.931WER0.069prompt-sim+0.193blend7.659genu0.989
best-of-8rew·all1.496invWER0.931WER0.069prompt-sim-0.207blend6.760genu1.909
best-of-6rew·all1.496invWER0.931WER0.069prompt-sim-0.207blend6.760genu1.909
best-of-4rew·all1.064invWER0.828WER0.172prompt-sim-0.129blend3.619genu1.483
no_dialogue · emo_ref
prompt-sim × invWER
best-of-16rew·ps0.006invWER0.345WER0.655prompt-sim+0.017blend2.958genu1.696
best-of-8rew·ps0.006invWER0.345WER0.655prompt-sim+0.017blend2.958genu1.696
best-of-6rew·ps-0.000invWER0.000WER1.000prompt-sim-0.210blend1.621genu0.768
best-of-4rew·ps0.006invWER0.345WER0.655prompt-sim+0.017blend2.958genu1.696
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all0.970invWER0.931WER0.069prompt-sim-0.214blend2.668genu1.256
best-of-8rew·all0.828invWER1.000WER0.000prompt-sim-0.306blend2.198genu0.928
best-of-6rew·all0.970invWER0.931WER0.069prompt-sim-0.214blend2.668genu1.256
best-of-4rew·all0.490invWER0.345WER0.655prompt-sim+0.017blend2.958genu1.696
CCsit_situation_5459_cc sit_situation
SAY: No te muevas, tonto. Casi, casi está saliendo. ¡Ay, ya! ¿Por qué no te desatas? Me duele la cabeza y esto no se mueve nada.
original DramaBox prompt & direction text

Full DramaBox prompt (how to say — with the "quoted" dialogue):
A child with a breathy, strained voice, delivering this high-quality studio voice recording with no background noise. The same voice is flushed and dizzy from being bent over, focused entirely on a stubborn knot in their shoelace. (breathing hard, words squeezed out) "No te muevas, tonto." (fingers fumbling) "Casi, casi está saliendo." CUT TO: The same voice now hot with frustration, a whine creeping in as the knot tightens and their arms start to shake. (a sharp exhale) "¡Ay, ya! ¿Por qué no te desatas?" (voice cracking with complaint) "Me duele la cabeza y esto no se mueve nada." The performance across both moments should feel like a real child's spiraling mood, from concentrated muttering to helpless whining, all while physically stuck in an uncomfortable pose.

Direction only (dialogue removed — this is what prompt-sim compares against):
A child with a breathy, strained voice, delivering this high-quality studio voice recording with no background noise. The same voice is flushed and dizzy from being bent over, focused entirely on a stubborn knot in their shoelace. (breathing hard, words squeezed out) (fingers fumbling) CUT TO: The same voice now hot with frustration, a whine creeping in as the knot tightens and their arms start to shake. (a sharp exhale) (voice cracking with complaint) The performance across both moments should feel like a real child's spiraling mood, from concentrated muttering to helpless whining, all while physically stuck in an uncomfortable pose.

What to say (goes in MOSS text field): No te muevas, tonto. Casi, casi está saliendo. ¡Ay, ya! ¿Por qué no te desatas? Me duele la cabeza y esto no se mueve nada.

with_dialogue · no_ref
prompt-sim × invWER
best-of-16rew·ps-0.023invWER0.480WER0.520prompt-sim-0.049blend4.080genu1.521
best-of-8rew·ps-0.023invWER0.480WER0.520prompt-sim-0.049blend4.080genu1.521
best-of-6rew·ps-0.023invWER0.480WER0.520prompt-sim-0.049blend4.080genu1.521
best-of-4rew·ps-0.042invWER0.560WER0.440prompt-sim-0.074blend4.319genu2.178
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all1.310invWER0.920WER0.080prompt-sim-0.259blend5.610genu1.954
best-of-8rew·all1.310invWER0.920WER0.080prompt-sim-0.259blend5.610genu1.954
best-of-6rew·all1.222invWER0.680WER0.320prompt-sim-0.082blend7.013genu1.994
best-of-4rew·all0.861invWER0.560WER0.440prompt-sim-0.074blend4.319genu2.178
with_dialogue · emo_ref
prompt-sim × invWER
best-of-16rew·ps0.019invWER0.160WER0.840prompt-sim+0.119blend5.253genu1.675
best-of-8rew·ps-0.085invWER0.240WER0.760prompt-sim-0.353blend0.774genu1.454
best-of-6rew·ps0.019invWER0.160WER0.840prompt-sim+0.119blend5.253genu1.675
best-of-4rew·ps0.000invWER0.000WER1.000prompt-sim+0.070blend1.179genu0.762
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all1.416invWER0.920WER0.080prompt-sim-0.086blend4.305genu2.293
best-of-8rew·all0.854invWER0.840WER0.160prompt-sim-0.336blend1.428genu2.912
best-of-6rew·all1.416invWER0.920WER0.080prompt-sim-0.086blend4.305genu2.293
best-of-4rew·all0.670invWER0.880WER0.120prompt-sim-0.305blend1.445genu1.022
no_dialogue · no_ref
prompt-sim × invWER
best-of-16rew·ps-0.000invWER0.000WER1.000prompt-sim-0.204blend7.473genu1.513
best-of-8rew·ps-0.000invWER0.000WER1.000prompt-sim-0.332blend0.348genu1.857
best-of-6rew·ps-0.000invWER0.000WER1.000prompt-sim-0.332blend0.348genu1.857
best-of-4rew·ps-0.100invWER0.960WER0.040prompt-sim-0.104blend7.248genu2.086
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all1.739invWER0.960WER0.040prompt-sim-0.104blend7.248genu2.086
best-of-8rew·all1.376invWER1.000WER0.000prompt-sim-0.094blend3.776genu1.686
best-of-6rew·all1.739invWER0.960WER0.040prompt-sim-0.104blend7.248genu2.086
best-of-4rew·all1.142invWER0.680WER0.320prompt-sim-0.052blend5.393genu2.166
no_dialogue · emo_ref
prompt-sim × invWER
best-of-16rew·ps-0.000invWER0.000WER1.000prompt-sim-0.200blend0.794genu1.741
best-of-8rew·ps-0.000invWER0.000WER1.000prompt-sim-0.200blend0.794genu1.741
best-of-6rew·ps-0.000invWER0.000WER1.000prompt-sim-0.200blend0.794genu1.741
best-of-4rew·ps-0.000invWER0.000WER1.160prompt-sim-0.528blend0.123genu1.277
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all1.092invWER1.000WER0.000prompt-sim-0.195blend2.980genu1.205
best-of-8rew·all0.951invWER0.840WER0.160prompt-sim-0.209blend2.209genu2.125
best-of-6rew·all0.951invWER0.840WER0.160prompt-sim-0.209blend2.209genu2.125
best-of-4rew·all0.712invWER1.000WER0.000prompt-sim-0.377blend0.541genu1.899
CCsit_situation_5621_cc sit_situation
SAY: You useless, thoughtless boy. Left this damn thing right in the middle. Now my back. Has to pay for your laziness. But maybe... maybe I can do this. Just one more shove. I'm not as weak as he thinks.
original DramaBox prompt & direction text

Full DramaBox prompt (how to say — with the "quoted" dialogue):
A 70 year old woman with a gravelly, breathy timbre from years of smoking and strain, delivering this high-quality studio voice recording with no background noise. The same voice is furious and physically straining, her body braced against the weight of the oak bookcase, every word forced out through clenched teeth. (heaving a grunt) "You useless, thoughtless boy. Left this damn thing right in the middle. Now my back." (panting, shifting her grip) "Has to pay for your laziness." CUT TO: The same voice now quiet and contemplative, still panting but her anger faded into a fragile, tender hope as she catches her breath. (soft exhale, wiping her forehead) "But maybe... maybe I can do this. Just one more shove." (a small, cracked laugh) "I'm not as weak as he thinks." The performance across both moments should feel like a real, raw struggle—anger dissolving into exhausted hope, with the physical strain grounding every word.

Direction only (dialogue removed — this is what prompt-sim compares against):
A 70 year old woman with a gravelly, breathy timbre from years of smoking and strain, delivering this high-quality studio voice recording with no background noise. The same voice is furious and physically straining, her body braced against the weight of the oak bookcase, every word forced out through clenched teeth. (heaving a grunt) (panting, shifting her grip) CUT TO: The same voice now quiet and contemplative, still panting but her anger faded into a fragile, tender hope as she catches her breath. (soft exhale, wiping her forehead) (a small, cracked laugh) The performance across both moments should feel like a real, raw struggle—anger dissolving into exhausted hope, with the physical strain grounding every word.

What to say (goes in MOSS text field): You useless, thoughtless boy. Left this damn thing right in the middle. Now my back. Has to pay for your laziness. But maybe... maybe I can do this. Just one more shove. I'm not as weak as he thinks.

with_dialogue · no_ref
prompt-sim × invWER
best-of-16rew·ps0.066invWER0.525WER0.475prompt-sim+0.125blend5.341genu1.337
best-of-8rew·ps-0.000invWER0.000WER1.050prompt-sim-0.114blend0.351genu0.591
best-of-6rew·ps0.066invWER0.525WER0.475prompt-sim+0.125blend5.341genu1.337
best-of-4rew·ps0.066invWER0.525WER0.475prompt-sim+0.125blend5.341genu1.337
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all1.213invWER0.675WER0.325prompt-sim-0.071blend7.179genu1.785
best-of-8rew·all1.213invWER0.675WER0.325prompt-sim-0.071blend7.179genu1.785
best-of-6rew·all0.945invWER0.525WER0.475prompt-sim-0.032blend7.197genu1.495
best-of-4rew·all0.576invWER0.375WER0.625prompt-sim-0.133blend5.866genu1.528
with_dialogue · emo_ref
prompt-sim × invWER
best-of-16rew·ps-0.019invWER0.875WER0.125prompt-sim-0.022blend1.984genu1.545
best-of-8rew·ps-0.024invWER0.150WER0.850prompt-sim-0.162blend1.804genu0.444
best-of-6rew·ps-0.255invWER1.000WER0.000prompt-sim-0.255blend0.000genu1.372
best-of-4rew·ps-0.125invWER0.475WER0.525prompt-sim-0.264blend3.947genu2.175
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all1.302invWER1.000WER0.000prompt-sim-0.135blend0.302genu4.001
best-of-8rew·all1.302invWER1.000WER0.000prompt-sim-0.135blend0.302genu4.001
best-of-6rew·all1.302invWER1.000WER0.000prompt-sim-0.135blend0.302genu4.001
best-of-4rew·all1.090invWER0.975WER0.025prompt-sim-0.268blend1.201genu3.203
no_dialogue · no_ref
prompt-sim × invWER
best-of-16rew·ps0.021invWER1.000WER0.000prompt-sim+0.021blend2.748genu1.388
best-of-8rew·ps-0.001invWER0.025WER0.975prompt-sim-0.060blend2.346genu1.540
best-of-6rew·ps-0.000invWER0.000WER1.000prompt-sim-0.105blend1.456genu1.498
best-of-4rew·ps0.000invWER0.000WER1.000prompt-sim+0.083blend3.041genu1.572
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all1.353invWER1.000WER0.000prompt-sim+0.021blend2.748genu1.388
best-of-8rew·all1.198invWER1.000WER0.000prompt-sim-0.016blend2.149genu1.104
best-of-6rew·all1.037invWER1.000WER0.000prompt-sim-0.065blend0.797genu1.413
best-of-4rew·all0.806invWER1.000WER0.000prompt-sim-0.230blend0.542genu1.376
no_dialogue · emo_ref
prompt-sim × invWER
best-of-16rew·ps0.010invWER0.350WER0.650prompt-sim+0.027blend3.293genu0.783
best-of-8rew·ps0.010invWER0.350WER0.650prompt-sim+0.027blend3.293genu0.783
best-of-6rew·ps0.007invWER0.050WER0.950prompt-sim+0.131blend1.261genu0.800
best-of-4rew·ps0.007invWER0.050WER0.950prompt-sim+0.131blend1.261genu0.800
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all1.298invWER1.000WER0.000prompt-sim-0.235blend1.323genu4.012
best-of-8rew·all1.298invWER1.000WER0.000prompt-sim-0.235blend1.323genu4.012
best-of-6rew·all1.021invWER1.000WER0.000prompt-sim-0.294blend1.273genu2.719
best-of-4rew·all1.298invWER1.000WER0.000prompt-sim-0.235blend1.323genu4.012
CCextreme_physical_196_cc extreme_physical
SAY: ...warm light on my eyelids... I can almost feel the sun... this is my skin, this is my breath... I am still here... No... NONONO— —it's in my BONES...
original DramaBox prompt & direction text

Full DramaBox prompt (how to say — with the "quoted" dialogue):
A 30-year-old woman with a warm, slightly husky alto, delivering this high-quality studio voice recording with no background noise. The same voice is lying on cold concrete, eyes closed, feeling a single bare bulb's warmth on her face, savoring stillness before the door opens. (soft whisper) "...warm light on my eyelids... I can almost feel the sun..." (barely audible, reverent) "this is my skin, this is my breath... I am still here..." CUT TO: The same voice now feels a metallic clamp on each ankle, then electricity seizing her body—the hum becomes a roar of fire, shattering her voice. (jaw locked, teeth chattering) "No... NONONO—" (high-pitched, breathless shriek) "—it's in my BONES..." (last word dissolves into a sob that becomes a raw, rhythmic grunt) The performance across both moments should feel like a woman being torn from a sacred, silent prayer into a brutal, all-consuming current.

Direction only (dialogue removed — this is what prompt-sim compares against):
A 30-year-old woman with a warm, slightly husky alto, delivering this high-quality studio voice recording with no background noise. The same voice is lying on cold concrete, eyes closed, feeling a single bare bulb's warmth on her face, savoring stillness before the door opens. (soft whisper) (barely audible, reverent) CUT TO: The same voice now feels a metallic clamp on each ankle, then electricity seizing her body—the hum becomes a roar of fire, shattering her voice. (jaw locked, teeth chattering) (high-pitched, breathless shriek) (last word dissolves into a sob that becomes a raw, rhythmic grunt) The performance across both moments should feel like a woman being torn from a sacred, silent prayer into a brutal, all-consuming current.

What to say (goes in MOSS text field): ...warm light on my eyelids... I can almost feel the sun... this is my skin, this is my breath... I am still here... No... NONONO— —it's in my BONES...

with_dialogue · no_ref
prompt-sim × invWER
best-of-16rew·ps0.014invWER0.733WER0.267prompt-sim+0.019blend6.925genu1.094
best-of-8rew·ps0.014invWER0.733WER0.267prompt-sim+0.019blend6.925genu1.094
best-of-6rew·ps0.000invWER0.000WER1.000prompt-sim+0.149blend2.220genu1.259
best-of-4rew·ps-0.009invWER0.533WER0.467prompt-sim-0.017blend6.407genu0.962
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all1.297invWER0.733WER0.267prompt-sim+0.019blend6.925genu1.094
best-of-8rew·all1.297invWER0.733WER0.267prompt-sim+0.019blend6.925genu1.094
best-of-6rew·all1.297invWER0.733WER0.267prompt-sim+0.019blend6.925genu1.094
best-of-4rew·all1.042invWER0.733WER0.267prompt-sim-0.102blend4.207genu1.728
with_dialogue · emo_ref
prompt-sim × invWER
best-of-16rew·ps0.018invWER0.167WER0.833prompt-sim+0.108blend2.965genu1.417
best-of-8rew·ps-0.002invWER0.200WER0.800prompt-sim-0.009blend3.794genu1.084
best-of-6rew·ps0.018invWER0.167WER0.833prompt-sim+0.108blend2.965genu1.417
best-of-4rew·ps0.018invWER0.167WER0.833prompt-sim+0.108blend2.965genu1.417
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all1.219invWER0.767WER0.233prompt-sim+0.022blend5.331genu1.063
best-of-8rew·all0.822invWER0.600WER0.400prompt-sim-0.104blend4.253genu1.387
best-of-6rew·all1.219invWER0.767WER0.233prompt-sim+0.022blend5.331genu1.063
best-of-4rew·all0.714invWER0.800WER0.200prompt-sim-0.278blend2.094genu1.194
no_dialogue · no_ref
prompt-sim × invWER
best-of-16rew·ps0.014invWER0.100WER0.900prompt-sim+0.145blend5.245genu0.900
best-of-8rew·ps0.014invWER0.100WER0.900prompt-sim+0.145blend5.245genu0.900
best-of-6rew·ps-0.000invWER0.000WER1.000prompt-sim-0.019blend2.162genu0.839
best-of-4rew·ps-0.000invWER0.000WER1.133prompt-sim-0.066blend0.848genu0.059
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all1.057invWER0.733WER0.267prompt-sim-0.052blend4.080genu1.568
best-of-8rew·all1.057invWER0.733WER0.267prompt-sim-0.052blend4.080genu1.568
best-of-6rew·all0.852invWER0.933WER0.067prompt-sim-0.276blend2.352genu1.127
best-of-4rew·all1.057invWER0.733WER0.267prompt-sim-0.052blend4.080genu1.568
no_dialogue · emo_ref
prompt-sim × invWER
best-of-16rew·ps-0.000invWER0.000WER1.167prompt-sim-0.206blend0.806genu1.297
best-of-8rew·ps-0.000invWER0.000WER1.067prompt-sim-0.214blend0.348genu0.508
best-of-6rew·ps-0.000invWER0.000WER1.000prompt-sim-0.299blend0.258genu0.766
best-of-4rew·ps-0.000invWER0.000WER1.067prompt-sim-0.214blend0.348genu0.508
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all1.263invWER0.767WER0.233prompt-sim-0.031blend6.126genu1.274
best-of-8rew·all0.844invWER0.633WER0.367prompt-sim-0.196blend4.464genu1.703
best-of-6rew·all0.961invWER0.767WER0.233prompt-sim-0.273blend4.789genu1.552
best-of-4rew·all1.263invWER0.767WER0.233prompt-sim-0.031blend6.126genu1.274
CCextreme_physical_270_cc extreme_physical
SAY: This lock's been dead for years... the hinges are the only things that remember how to sing. Oh, you think that's funny, do you? Just... just a little janitor?
original DramaBox prompt & direction text

Full DramaBox prompt (how to say — with the "quoted" dialogue):
A 30-year-old woman with a husky, sand-warmed contralto, delivering this high-quality studio voice recording with no background noise. The same voice is soft with melancholy, her palm pressed to cold rippled glass as she hums a slow, forgotten lullaby. (whispering near the glass) "This lock's been dead for years... the hinges are the only things that remember how to sing." (letting the thought dissolve into a breathy sigh) CUT TO: The same voice now yanked into her throat by a sudden face on the glass, her breath stolen, then ripped out as a raw, high-velocity scream that splinters into a trembling, bitter laugh. (stumbling backward, voice cracking) "Oh, you think that's funny, do you? Just... just a little janitor?" (trailing into a jagged sob that she swallows hard) The performance across both moments should feel like a solitary woman's intimate stillness shattered into a feral, wounded animal response.

Direction only (dialogue removed — this is what prompt-sim compares against):
A 30-year-old woman with a husky, sand-warmed contralto, delivering this high-quality studio voice recording with no background noise. The same voice is soft with melancholy, her palm pressed to cold rippled glass as she hums a slow, forgotten lullaby. (whispering near the glass) (letting the thought dissolve into a breathy sigh) CUT TO: The same voice now yanked into her throat by a sudden face on the glass, her breath stolen, then ripped out as a raw, high-velocity scream that splinters into a trembling, bitter laugh. (stumbling backward, voice cracking) (trailing into a jagged sob that she swallows hard) The performance across both moments should feel like a solitary woman's intimate stillness shattered into a feral, wounded animal response.

What to say (goes in MOSS text field): This lock's been dead for years... the hinges are the only things that remember how to sing. Oh, you think that's funny, do you? Just... just a little janitor?

with_dialogue · no_ref
prompt-sim × invWER
best-of-16rew·ps0.031invWER0.419WER0.581prompt-sim+0.073blend7.669genu1.907
best-of-8rew·ps0.031invWER0.419WER0.581prompt-sim+0.073blend7.669genu1.907
best-of-6rew·ps0.031invWER0.419WER0.581prompt-sim+0.073blend7.669genu1.907
best-of-4rew·ps-0.000invWER0.000WER1.000prompt-sim-0.043blend1.651genu1.312
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all1.144invWER1.000WER0.000prompt-sim-0.096blend2.285genu1.271
best-of-8rew·all1.093invWER0.968WER0.032prompt-sim-0.154blend2.784genu1.273
best-of-6rew·all1.144invWER1.000WER0.000prompt-sim-0.096blend2.285genu1.271
best-of-4rew·all1.011invWER1.000WER0.000prompt-sim-0.230blend2.197genu1.516
with_dialogue · emo_ref
prompt-sim × invWER
best-of-16rew·ps0.006invWER0.355WER0.645prompt-sim+0.018blend5.811genu1.589
best-of-8rew·ps0.003invWER0.129WER0.871prompt-sim+0.020blend3.117genu1.382
best-of-6rew·ps0.003invWER0.129WER0.871prompt-sim+0.020blend3.117genu1.382
best-of-4rew·ps0.006invWER0.355WER0.645prompt-sim+0.018blend5.811genu1.589
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all1.203invWER1.000WER0.000prompt-sim-0.038blend2.226genu1.248
best-of-8rew·all1.203invWER1.000WER0.000prompt-sim-0.038blend2.226genu1.248
best-of-6rew·all1.018invWER1.000WER0.000prompt-sim-0.190blend2.027genu1.368
best-of-4rew·all1.203invWER1.000WER0.000prompt-sim-0.038blend2.226genu1.248
no_dialogue · no_ref
prompt-sim × invWER
best-of-16rew·ps0.010invWER0.387WER0.613prompt-sim+0.026blend6.041genu1.898
best-of-8rew·ps0.010invWER0.387WER0.613prompt-sim+0.026blend6.041genu1.898
best-of-6rew·ps-0.000invWER0.000WER1.000prompt-sim-0.056blend0.530genu0.314
best-of-4rew·ps0.001invWER1.000WER0.000prompt-sim+0.001blend4.379genu1.776
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all1.571invWER1.000WER0.000prompt-sim+0.001blend4.379genu1.776
best-of-8rew·all1.385invWER0.839WER0.161prompt-sim-0.094blend6.388genu1.593
best-of-6rew·all1.571invWER1.000WER0.000prompt-sim+0.001blend4.379genu1.776
best-of-4rew·all1.385invWER0.839WER0.161prompt-sim-0.094blend6.388genu1.593
no_dialogue · emo_ref
prompt-sim × invWER
best-of-16rew·ps0.125invWER1.000WER0.000prompt-sim+0.125blend3.429genu1.301
best-of-8rew·ps0.125invWER1.000WER0.000prompt-sim+0.125blend3.429genu1.301
best-of-6rew·ps-0.000invWER0.000WER1.000prompt-sim-0.108blend1.480genu1.255
best-of-4rew·ps0.010invWER0.097WER0.903prompt-sim+0.105blend3.757genu1.223
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all1.539invWER1.000WER0.000prompt-sim+0.125blend3.429genu1.301
best-of-8rew·all1.134invWER1.000WER0.000prompt-sim-0.068blend2.226genu1.039
best-of-6rew·all1.539invWER1.000WER0.000prompt-sim+0.125blend3.429genu1.301
best-of-4rew·all1.219invWER0.935WER0.065prompt-sim-0.047blend2.592genu1.702
CCextreme_physical_556_cc extreme_physical
SAY: Hey... if this wasn't happening, I'd kiss you right now. Right beneath that crack in the wood. No—you don't—get in— —you son of a—
original DramaBox prompt & direction text

Full DramaBox prompt (how to say — with the "quoted" dialogue):
A 20-year-old woman with a warm, honeyed contralto, delivering this high-quality studio voice recording with no background noise. The same voice is pressed against a steel door, heart humming from the boy's nearness, breath shallow and dreamy. (a soft exhale, turning her head) "Hey... if this wasn't happening, I'd kiss you right now." (a slow, lazy smile in her voice) "Right beneath that crack in the wood." CUT TO: The same voice now slammed against the buckled door, wind ripping the air away, muscles screaming as she shoves with her whole spine. (a snarling gasp as she throws her weight) "No—you don't—get in—" (a grinding, hating groan as she holds the seal) "—you son of a—" The performance across both moments should feel like one person ripped from a whispered promise into a snarling, breath-splintered fight for survival.

Direction only (dialogue removed — this is what prompt-sim compares against):
A 20-year-old woman with a warm, honeyed contralto, delivering this high-quality studio voice recording with no background noise. The same voice is pressed against a steel door, heart humming from the boy's nearness, breath shallow and dreamy. (a soft exhale, turning her head) (a slow, lazy smile in her voice) CUT TO: The same voice now slammed against the buckled door, wind ripping the air away, muscles screaming as she shoves with her whole spine. (a snarling gasp as she throws her weight) (a grinding, hating groan as she holds the seal) The performance across both moments should feel like one person ripped from a whispered promise into a snarling, breath-splintered fight for survival.

What to say (goes in MOSS text field): Hey... if this wasn't happening, I'd kiss you right now. Right beneath that crack in the wood. No—you don't—get in— —you son of a—

with_dialogue · no_ref
prompt-sim × invWER
best-of-16rew·ps0.002invWER0.035WER0.966prompt-sim+0.056blend3.710genu1.728
best-of-8rew·ps0.002invWER0.035WER0.966prompt-sim+0.056blend3.710genu1.728
best-of-6rew·ps-0.128invWER0.655WER0.345prompt-sim-0.195blend5.116genu1.466
best-of-4rew·ps0.002invWER0.035WER0.966prompt-sim+0.056blend3.710genu1.728
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all1.417invWER1.000WER0.000prompt-sim-0.039blend3.708genu1.573
best-of-8rew·all1.417invWER1.000WER0.000prompt-sim-0.039blend3.708genu1.573
best-of-6rew·all1.417invWER1.000WER0.000prompt-sim-0.039blend3.708genu1.573
best-of-4rew·all1.392invWER1.000WER0.000prompt-sim-0.158blend5.061genu1.369
with_dialogue · emo_ref
prompt-sim × invWER
best-of-16rew·ps0.000invWER0.000WER1.000prompt-sim+0.121blend2.133genu0.855
best-of-8rew·ps0.000invWER0.000WER1.000prompt-sim+0.121blend2.133genu0.855
best-of-6rew·ps0.000invWER0.000WER1.000prompt-sim+0.121blend2.133genu0.855
best-of-4rew·ps-0.082invWER0.552WER0.448prompt-sim-0.149blend1.609genu0.779
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all1.166invWER0.966WER0.035prompt-sim-0.402blend2.766genu3.683
best-of-8rew·all1.042invWER0.690WER0.310prompt-sim-0.236blend4.341genu3.241
best-of-6rew·all0.906invWER0.966WER0.035prompt-sim-0.322blend2.616genu1.455
best-of-4rew·all0.907invWER1.000WER0.000prompt-sim-0.179blend1.757genu0.764
no_dialogue · no_ref
prompt-sim × invWER
best-of-16rew·ps0.039invWER0.931WER0.069prompt-sim+0.042blend3.629genu1.426
best-of-8rew·ps0.039invWER0.931WER0.069prompt-sim+0.042blend3.629genu1.426
best-of-6rew·ps-0.000invWER0.000WER1.000prompt-sim-0.093blend1.260genu0.511
best-of-4rew·ps-0.000invWER0.000WER1.000prompt-sim-0.136blend2.584genu1.536
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all2.004invWER1.000WER0.000prompt-sim-0.121blend8.964genu2.228
best-of-8rew·all2.004invWER1.000WER0.000prompt-sim-0.121blend8.964genu2.228
best-of-6rew·all1.387invWER1.000WER0.000prompt-sim-0.132blend3.767genu2.053
best-of-4rew·all1.387invWER1.000WER0.000prompt-sim-0.132blend3.767genu2.053
no_dialogue · emo_ref
prompt-sim × invWER
best-of-16rew·ps-0.000invWER0.000WER1.000prompt-sim-0.237blend2.256genu1.579
best-of-8rew·ps-0.000invWER0.000WER1.000prompt-sim-0.250blend1.688genu2.130
best-of-6rew·ps-0.000invWER0.000WER1.000prompt-sim-0.237blend2.256genu1.579
best-of-4rew·ps-0.000invWER0.000WER1.000prompt-sim-0.342blend0.104genu1.605
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all1.212invWER0.862WER0.138prompt-sim-0.018blend3.671genu1.371
best-of-8rew·all1.212invWER0.862WER0.138prompt-sim-0.018blend3.671genu1.371
best-of-6rew·all0.802invWER0.966WER0.035prompt-sim-0.327blend1.624genu1.514
best-of-4rew·all1.127invWER0.966WER0.035prompt-sim-0.109blend2.216genu1.572
NONCCcca_voicenet_10203_noncc cca_voicenet
SAY: You know, she got the promotion just by being there. I've been here twice as long, but who counts that anymore.
original DramaBox prompt & direction text

Full DramaBox prompt (how to say — with the "quoted" dialogue):
A late-middle-aged female with a grainy, chest-rich alto, delivering this high-quality studio voice recording with no background noise. The same voice is simmering with sour jealousy, each word laced with tight-lipped envy. (Bitterly.) "You know, she got the promotion just by being there. I've been here twice as long, but who counts that anymore." (Voice tightens.) "It's fine.

Direction only (dialogue removed — this is what prompt-sim compares against):
A late-middle-aged female with a grainy, chest-rich alto, delivering this high-quality studio voice recording with no background noise. The same voice is simmering with sour jealousy, each word laced with tight-lipped envy. (Bitterly.) (Voice tightens.) "It's fine.

What to say (goes in MOSS text field): You know, she got the promotion just by being there. I've been here twice as long, but who counts that anymore.

with_dialogue · no_ref
prompt-sim × invWER
best-of-16rew·ps-0.007invWER0.045WER0.955prompt-sim-0.150blend7.982genu2.246
best-of-8rew·ps-0.007invWER0.045WER0.955prompt-sim-0.150blend7.982genu2.246
best-of-6rew·ps-0.007invWER0.045WER0.955prompt-sim-0.150blend7.982genu2.246
best-of-4rew·ps-0.089invWER1.000WER0.000prompt-sim-0.089blend2.749genu1.102
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all1.177invWER1.000WER0.000prompt-sim-0.089blend2.749genu1.102
best-of-8rew·all1.177invWER1.000WER0.000prompt-sim-0.089blend2.749genu1.102
best-of-6rew·all1.177invWER1.000WER0.000prompt-sim-0.089blend2.749genu1.102
best-of-4rew·all1.058invWER0.909WER0.091prompt-sim-0.330blend4.583genu1.565
with_dialogue · emo_ref
prompt-sim × invWER
best-of-16rew·ps-0.103invWER1.000WER0.000prompt-sim-0.103blend0.716genu1.149
best-of-8rew·ps-0.143invWER1.000WER0.000prompt-sim-0.143blend0.565genu0.875
best-of-6rew·ps-0.103invWER1.000WER0.000prompt-sim-0.103blend0.716genu1.149
best-of-4rew·ps-0.143invWER1.000WER0.000prompt-sim-0.143blend0.565genu0.875
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all1.183invWER1.000WER0.000prompt-sim-0.223blend2.814genu2.124
best-of-8rew·all1.183invWER1.000WER0.000prompt-sim-0.223blend2.814genu2.124
best-of-6rew·all1.048invWER1.000WER0.000prompt-sim-0.227blend1.727genu2.064
best-of-4rew·all1.060invWER1.000WER0.000prompt-sim-0.162blend1.678genu1.672
no_dialogue · no_ref
prompt-sim × invWER
best-of-16rew·ps-0.018invWER0.909WER0.091prompt-sim-0.020blend3.755genu1.764
best-of-8rew·ps-0.018invWER0.909WER0.091prompt-sim-0.020blend3.755genu1.764
best-of-6rew·ps-0.018invWER0.909WER0.091prompt-sim-0.020blend3.755genu1.764
best-of-4rew·ps-0.018invWER0.909WER0.091prompt-sim-0.020blend3.755genu1.764
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all1.368invWER0.909WER0.091prompt-sim-0.130blend5.674genu1.438
best-of-8rew·all1.310invWER1.000WER0.000prompt-sim-0.157blend4.526genu1.213
best-of-6rew·all1.192invWER1.000WER0.000prompt-sim-0.191blend3.146genu1.701
best-of-4rew·all1.182invWER0.909WER0.091prompt-sim-0.186blend4.441genu1.431
no_dialogue · emo_ref
prompt-sim × invWER
best-of-16rew·ps-0.149invWER0.909WER0.091prompt-sim-0.164blend2.797genu0.984
best-of-8rew·ps-0.149invWER0.909WER0.091prompt-sim-0.164blend2.797genu0.984
best-of-6rew·ps-0.203invWER0.955WER0.045prompt-sim-0.212blend2.241genu1.788
best-of-4rew·ps-0.210invWER1.000WER0.000prompt-sim-0.210blend2.543genu1.455
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all1.244invWER1.000WER0.000prompt-sim-0.254blend1.962genu3.355
best-of-8rew·all1.244invWER1.000WER0.000prompt-sim-0.254blend1.962genu3.355
best-of-6rew·all1.064invWER1.000WER0.000prompt-sim-0.210blend2.543genu1.455
best-of-4rew·all1.060invWER1.000WER0.000prompt-sim-0.231blend2.328genu1.744
NONCCcca_voicenet_18413_noncc cca_voicenet
SAY: You really didn't have to go and do all this.
original DramaBox prompt & direction text

Full DramaBox prompt (how to say — with the "quoted" dialogue):
A young male with a deep, cartoonishly authoritative voice, tinny and bright yet booming, delivering this high-quality studio voice recording with no background noise. The same voice is overwhelmed with intense gratitude, but the words sound annoyed. (Sighs heavily) "You really didn't have to go and do all this." (Shakes head) "It's just

Direction only (dialogue removed — this is what prompt-sim compares against):
A young male with a deep, cartoonishly authoritative voice, tinny and bright yet booming, delivering this high-quality studio voice recording with no background noise. The same voice is overwhelmed with intense gratitude, but the words sound annoyed. (Sighs heavily) (Shakes head) "It's just

What to say (goes in MOSS text field): You really didn't have to go and do all this.

with_dialogue · no_ref
prompt-sim × invWER
best-of-16rew·ps-0.000invWER0.000WER1.000prompt-sim-0.006blend1.639genu1.291
best-of-8rew·ps-0.000invWER0.000WER1.091prompt-sim-0.105blend0.435genu0.646
best-of-6rew·ps-0.000invWER0.000WER1.091prompt-sim-0.105blend0.435genu0.646
best-of-4rew·ps-0.037invWER0.636WER0.364prompt-sim-0.058blend7.725genu1.578
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all1.662invWER1.000WER0.000prompt-sim-0.073blend6.498genu1.417
best-of-8rew·all1.662invWER1.000WER0.000prompt-sim-0.073blend6.498genu1.417
best-of-6rew·all1.523invWER0.909WER0.091prompt-sim-0.200blend7.692genu1.632
best-of-4rew·all1.523invWER0.909WER0.091prompt-sim-0.200blend7.692genu1.632
with_dialogue · emo_ref
prompt-sim × invWER
best-of-16rew·ps0.049invWER1.000WER0.000prompt-sim+0.049blend1.803genu1.243
best-of-8rew·ps-0.000invWER0.000WER1.636prompt-sim-0.191blend0.857genu5.661
best-of-6rew·ps0.002invWER0.091WER0.909prompt-sim+0.021blend1.283genu1.194
best-of-4rew·ps0.036invWER0.545WER0.455prompt-sim+0.066blend2.119genu1.944
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all1.711invWER1.000WER0.000prompt-sim-0.003blend5.967genu1.572
best-of-8rew·all1.660invWER1.000WER0.000prompt-sim-0.070blend5.068genu2.403
best-of-6rew·all1.711invWER1.000WER0.000prompt-sim-0.003blend5.967genu1.572
best-of-4rew·all0.870invWER0.636WER0.364prompt-sim-0.154blend4.979genu1.230
no_dialogue · no_ref
prompt-sim × invWER
best-of-8rew·ps-0.000invWER0.000WER1.364prompt-sim-0.242blend3.403genu1.508
best-of-6rew·ps-0.000invWER0.000WER1.636prompt-sim-0.191blend3.036genu0.838
best-of-4rew·ps-0.006invWER0.091WER0.909prompt-sim-0.062blend8.421genu1.789
invWER × (norm prompt-sim + blend + genu)
best-of-8rew·all1.422invWER1.000WER0.000prompt-sim-0.195blend5.866genu1.270
best-of-6rew·all1.401invWER0.909WER0.091prompt-sim-0.007blend4.671genu1.438
best-of-4rew·all1.325invWER1.000WER0.000prompt-sim-0.220blend4.947genu1.489
no_dialogue · emo_ref
prompt-sim × invWER
best-of-16rew·ps0.060invWER1.000WER0.000prompt-sim+0.060blend4.893genu1.993
best-of-8rew·ps0.026invWER0.909WER0.091prompt-sim+0.028blend2.300genu2.060
best-of-6rew·ps-0.000invWER0.000WER1.000prompt-sim-0.093blend3.775genu2.100
best-of-4rew·ps0.026invWER0.909WER0.091prompt-sim+0.028blend2.300genu2.060
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all1.732invWER1.000WER0.000prompt-sim+0.060blend4.893genu1.993
best-of-8rew·all1.416invWER0.909WER0.091prompt-sim-0.023blend2.365genu3.307
best-of-6rew·all1.288invWER0.909WER0.091prompt-sim+0.028blend2.300genu2.060
best-of-4rew·all1.416invWER0.909WER0.091prompt-sim-0.023blend2.365genu3.307
NONCCextreme_physical_295_noncc extreme_physical
SAY: Ah, that breeze feels good.
original DramaBox prompt & direction text

Full DramaBox prompt (how to say — with the "quoted" dialogue):
A 40-year-old man with a gravelly, warm baritone, delivering this high-quality studio voice recording with no background noise. The same voice is relaxed and sensual, lips curled in a teasing smirk, tasting sour coffee and evening air through the open window. (soft exhale) "Ah, that breeze feels good." (amused drawl) "Yeah, you can

Direction only (dialogue removed — this is what prompt-sim compares against):
A 40-year-old man with a gravelly, warm baritone, delivering this high-quality studio voice recording with no background noise. The same voice is relaxed and sensual, lips curled in a teasing smirk, tasting sour coffee and evening air through the open window. (soft exhale) (amused drawl) "Yeah, you can

What to say (goes in MOSS text field): Ah, that breeze feels good.

with_dialogue · no_ref
prompt-sim × invWER
best-of-16rew·ps0.103invWER1.000WER0.000prompt-sim+0.103blend5.781genu0.802
best-of-8rew·ps0.103invWER1.000WER0.000prompt-sim+0.103blend5.781genu0.802
best-of-6rew·ps-0.000invWER0.000WER1.400prompt-sim-0.141blend4.659genu1.903
best-of-4rew·ps-0.000invWER0.000WER1.000prompt-sim-0.072blend2.779genu1.077
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all1.833invWER1.000WER0.000prompt-sim+0.006blend6.864genu1.650
best-of-8rew·all1.833invWER1.000WER0.000prompt-sim+0.006blend6.864genu1.650
best-of-6rew·all1.714invWER1.000WER0.000prompt-sim-0.078blend7.064genu1.391
best-of-4rew·all1.348invWER0.800WER0.200prompt-sim-0.190blend7.298genu1.900
with_dialogue · emo_ref
prompt-sim × invWER
best-of-16rew·ps0.100invWER1.000WER0.000prompt-sim+0.100blend2.143genu1.715
best-of-8rew·ps0.046invWER0.400WER0.600prompt-sim+0.116blend3.969genu2.957
best-of-6rew·ps0.090invWER0.800WER0.200prompt-sim+0.112blend4.119genu1.331
best-of-4rew·ps0.090invWER0.800WER0.200prompt-sim+0.112blend4.119genu1.331
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all1.541invWER1.000WER0.000prompt-sim+0.083blend4.252genu1.047
best-of-8rew·all1.541invWER1.000WER0.000prompt-sim+0.083blend4.252genu1.047
best-of-6rew·all1.541invWER1.000WER0.000prompt-sim+0.083blend4.252genu1.047
best-of-4rew·all1.541invWER1.000WER0.000prompt-sim+0.083blend4.252genu1.047
no_dialogue · no_ref
prompt-sim × invWER
best-of-16rew·ps-0.000invWER0.000WER1.000prompt-sim-0.095blend5.341genu1.947
best-of-8rew·ps0.000invWER0.000WER2.600prompt-sim+0.105blend4.153genu1.398
best-of-6rew·ps0.000invWER0.000WER1.400prompt-sim+0.077blend1.905genu1.299
best-of-4rew·ps-0.000invWER0.000WER1.000prompt-sim-0.191blend8.346genu2.433
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all1.760invWER1.000WER0.000prompt-sim-0.144blend7.420genu1.935
best-of-8rew·all1.760invWER1.000WER0.000prompt-sim-0.144blend7.420genu1.935
best-of-6rew·all1.760invWER1.000WER0.000prompt-sim-0.144blend7.420genu1.935
best-of-4rew·all1.760invWER1.000WER0.000prompt-sim-0.144blend7.420genu1.935
no_dialogue · emo_ref
prompt-sim × invWER
best-of-16rew·ps0.086invWER0.800WER0.200prompt-sim+0.108blend6.750genu1.584
best-of-8rew·ps0.086invWER0.800WER0.200prompt-sim+0.108blend6.750genu1.584
best-of-6rew·ps0.079invWER1.000WER0.000prompt-sim+0.079blend1.545genu1.629
best-of-4rew·ps0.000invWER0.000WER2.000prompt-sim+0.113blend1.394genu1.272
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all1.545invWER0.800WER0.200prompt-sim+0.108blend6.750genu1.584
best-of-8rew·all1.545invWER0.800WER0.200prompt-sim+0.108blend6.750genu1.584
best-of-6rew·all1.545invWER0.800WER0.200prompt-sim+0.108blend6.750genu1.584
best-of-4rew·all0.000invWER0.000WER2.200prompt-sim+0.016blend3.082genu1.182
NONCCsit_situation_3619_noncc sit_situation
SAY: ¡Por fin, carajo! Después de tanto tiempo peleando, el proyecto pasó. ¿Lo podés creer?
original DramaBox prompt & direction text

Full DramaBox prompt (how to say — with the "quoted" dialogue):
A 45-year-old man with a gravelly, whiskey-roughened voice, delivering this high-quality studio voice recording with no background noise. The same voice is elated and heavily intoxicated, swaying on a barstool as he triumphantly celebrates his long-awaited project approval. (stumbling, gripping the bar) "¡Por fin, carajo! Después de tanto tiempo peleando, el proyecto pasó. ¿Lo podés creer?" (laughing at his own feet) "Mirá, hasta las luces del

Direction only (dialogue removed — this is what prompt-sim compares against):
A 45-year-old man with a gravelly, whiskey-roughened voice, delivering this high-quality studio voice recording with no background noise. The same voice is elated and heavily intoxicated, swaying on a barstool as he triumphantly celebrates his long-awaited project approval. (stumbling, gripping the bar) (laughing at his own feet) "Mirá, hasta las luces del

What to say (goes in MOSS text field): ¡Por fin, carajo! Después de tanto tiempo peleando, el proyecto pasó. ¿Lo podés creer?

with_dialogue · no_ref
prompt-sim × invWER
best-of-16rew·ps-0.000invWER0.000WER1.286prompt-sim-0.298blend3.339genu1.720
best-of-8rew·ps-0.000invWER0.000WER1.000prompt-sim-0.062blend5.469genu2.284
best-of-6rew·ps-0.000invWER0.000WER1.000prompt-sim-0.062blend5.469genu2.284
best-of-4rew·ps-0.000invWER0.000WER1.000prompt-sim-0.062blend5.469genu2.284
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all1.497invWER1.000WER0.000prompt-sim-0.192blend6.524genu1.260
best-of-8rew·all1.090invWER1.000WER0.000prompt-sim-0.244blend2.711genu1.765
best-of-6rew·all1.090invWER1.000WER0.000prompt-sim-0.244blend2.711genu1.765
best-of-4rew·all1.194invWER1.000WER0.000prompt-sim-0.191blend3.024genu1.798
with_dialogue · emo_ref
prompt-sim × invWER
best-of-16rew·ps0.003invWER0.786WER0.214prompt-sim+0.003blend4.205genu2.567
best-of-8rew·ps-0.000invWER0.000WER1.000prompt-sim-0.042blend1.137genu2.032
best-of-6rew·ps-0.000invWER0.000WER1.000prompt-sim-0.042blend1.137genu2.032
best-of-4rew·ps-0.000invWER0.000WER1.000prompt-sim-0.042blend1.137genu2.032
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all1.318invWER0.786WER0.214prompt-sim+0.003blend4.205genu2.567
best-of-8rew·all1.318invWER0.786WER0.214prompt-sim+0.003blend4.205genu2.567
best-of-6rew·all1.318invWER0.786WER0.214prompt-sim+0.003blend4.205genu2.567
best-of-4rew·all1.204invWER0.929WER0.071prompt-sim-0.293blend5.307genu1.609
no_dialogue · no_ref
prompt-sim × invWER
best-of-16rew·ps-0.000invWER0.000WER1.000prompt-sim-0.150blend5.011genu2.126
best-of-8rew·ps-0.000invWER0.000WER1.357prompt-sim-0.252blend0.365genu0.553
best-of-6rew·ps-0.000invWER0.000WER1.000prompt-sim-0.150blend5.011genu2.126
best-of-4rew·ps-0.000invWER0.000WER1.143prompt-sim-0.201blend5.175genu2.494
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all1.677invWER1.000WER0.000prompt-sim-0.253blend8.113genu1.751
best-of-8rew·all1.443invWER0.786WER0.214prompt-sim-0.168blend4.385genu4.770
best-of-6rew·all0.853invWER1.000WER0.000prompt-sim-0.407blend2.471genu1.663
best-of-4rew·all1.443invWER0.786WER0.214prompt-sim-0.168blend4.385genu4.770
no_dialogue · emo_ref
prompt-sim × invWER
best-of-16rew·ps0.012invWER0.071WER0.929prompt-sim+0.164blend1.958genu2.119
best-of-8rew·ps0.000invWER0.000WER1.000prompt-sim+0.023blend1.288genu0.990
best-of-6rew·ps-0.000invWER0.000WER1.000prompt-sim-0.156blend1.758genu2.219
best-of-4rew·ps0.012invWER0.071WER0.929prompt-sim+0.164blend1.958genu2.119
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all1.133invWER1.000WER0.000prompt-sim-0.191blend2.457genu1.805
best-of-8rew·all1.133invWER1.000WER0.000prompt-sim-0.191blend2.457genu1.805
best-of-6rew·all1.133invWER1.000WER0.000prompt-sim-0.191blend2.457genu1.805
best-of-4rew·all0.999invWER1.000WER0.000prompt-sim-0.330blend2.682genu1.855
NONCCcca_voicenet_11461_noncc cca_voicenet
SAY: You— You don't get it. You never did. I'm drowning.
original DramaBox prompt & direction text

Full DramaBox prompt (how to say — with the "quoted" dialogue):
A 35-year-old male with a hyper-masculine, booming chest resonance and a fast, compressed delivery, yet marked by disfluent stutters and a flat, unstressed intonation, delivering this high-quality studio voice recording with no background noise. The same voice is vibrating with barely contained rage, jaw tight, words slamming together in a rapid, choked stream of anger and distress. (He presses his palm against the table, knuckles white, the low rumble of contempt saturating each syllable.) "You—" (He breaks off, swallows, starts again faster.) "You don't get it." (A hard, bitter exhale through his nose.) "You never did." (He shakes his head, voice cracking under the pressure, the flat emphasis making each word a dead weight.) "I'm drowning." (He stares at the far wall

Direction only (dialogue removed — this is what prompt-sim compares against):
A 35-year-old male with a hyper-masculine, booming chest resonance and a fast, compressed delivery, yet marked by disfluent stutters and a flat, unstressed intonation, delivering this high-quality studio voice recording with no background noise. The same voice is vibrating with barely contained rage, jaw tight, words slamming together in a rapid, choked stream of anger and distress. (He presses his palm against the table, knuckles white, the low rumble of contempt saturating each syllable.) (He breaks off, swallows, starts again faster.) (A hard, bitter exhale through his nose.) (He shakes his head, voice cracking under the pressure, the flat emphasis making each word a dead weight.) (He stares at the far wall

What to say (goes in MOSS text field): You— You don't get it. You never did. I'm drowning.

with_dialogue · no_ref
prompt-sim × invWER
best-of-16rew·ps0.097invWER0.917WER0.083prompt-sim+0.106blend5.413genu1.360
best-of-8rew·ps0.097invWER0.917WER0.083prompt-sim+0.106blend5.413genu1.360
best-of-6rew·ps0.097invWER0.917WER0.083prompt-sim+0.106blend5.413genu1.360
best-of-4rew·ps-0.005invWER0.083WER0.917prompt-sim-0.064blend5.533genu1.428
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all1.600invWER0.917WER0.083prompt-sim+0.106blend5.413genu1.360
best-of-8rew·all1.598invWER1.000WER0.000prompt-sim-0.083blend5.689genu1.664
best-of-6rew·all1.600invWER0.917WER0.083prompt-sim+0.106blend5.413genu1.360
best-of-4rew·all1.432invWER0.917WER0.083prompt-sim-0.159blend6.526genu1.419
with_dialogue · emo_ref
prompt-sim × invWER
best-of-16rew·ps-0.000invWER0.000WER1.583prompt-sim-0.085blend1.529genu2.043
best-of-8rew·ps-0.000invWER0.000WER1.583prompt-sim-0.085blend1.529genu2.043
best-of-6rew·ps-0.000invWER0.000WER1.583prompt-sim-0.085blend1.529genu2.043
best-of-4rew·ps-0.029invWER0.083WER0.917prompt-sim-0.351blend0.153genu1.796
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all1.560invWER1.000WER0.000prompt-sim-0.136blend5.760genu1.773
best-of-8rew·all1.560invWER1.000WER0.000prompt-sim-0.136blend5.760genu1.773
best-of-6rew·all1.516invWER0.917WER0.083prompt-sim-0.185blend6.619genu2.145
best-of-4rew·all1.554invWER0.917WER0.083prompt-sim-0.078blend6.282genu1.826
no_dialogue · no_ref
prompt-sim × invWER
best-of-16rew·ps0.003invWER0.917WER0.083prompt-sim+0.003blend8.394genu2.002
best-of-8rew·ps-0.026invWER0.917WER0.083prompt-sim-0.028blend5.486genu1.348
best-of-6rew·ps-0.000invWER0.000WER1.000prompt-sim-0.124blend7.126genu2.119
best-of-4rew·ps-0.112invWER1.000WER0.000prompt-sim-0.112blend7.306genu2.049
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all1.882invWER0.917WER0.083prompt-sim+0.003blend8.394genu2.002
best-of-8rew·all1.829invWER0.917WER0.083prompt-sim-0.128blend8.878genu2.285
best-of-6rew·all1.882invWER0.917WER0.083prompt-sim+0.003blend8.394genu2.002
best-of-4rew·all1.519invWER1.000WER0.000prompt-sim-0.321blend7.005genu2.042
no_dialogue · emo_ref
prompt-sim × invWER
best-of-16rew·ps-0.006invWER0.083WER0.917prompt-sim-0.072blend3.268genu1.454
best-of-8rew·ps-0.057invWER0.667WER0.333prompt-sim-0.086blend6.601genu2.240
best-of-6rew·ps-0.006invWER0.083WER0.917prompt-sim-0.072blend3.268genu1.454
best-of-4rew·ps-0.006invWER0.083WER0.917prompt-sim-0.072blend3.268genu1.454
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all1.744invWER1.000WER0.000prompt-sim-0.025blend6.655genu1.464
best-of-8rew·all1.744invWER1.000WER0.000prompt-sim-0.025blend6.655genu1.464
best-of-6rew·all1.744invWER1.000WER0.000prompt-sim-0.025blend6.655genu1.464
best-of-4rew·all1.744invWER1.000WER0.000prompt-sim-0.025blend6.655genu1.464
NONCCcca_voicenet_11643_noncc cca_voicenet
SAY: Well, that's one way to break the ice. I guess I should've seen that coming. But honestly, I'm just glad it's over.
original DramaBox prompt & direction text

Full DramaBox prompt (how to say — with the "quoted" dialogue):
A young man with a glacially slow, soft-onset voice that snaps into percussive emphasis on key words, delivering this high-quality studio voice recording with no background noise. The same voice is a strained blend of amusement and relief, despite a sharp, grinding pain that makes each syllable an effort. (He touches the wound with trembling fingers, a pained but amused exhale escaping.) "Well, that's one way to break the ice." (He shifts his weight, then lets out a short, ragged chuckle.) "I guess I should've seen that coming." (He pauses, breathing slowly.) "But honestly, I'm just glad it's over." (A soft, wheezing laugh.) "At least now I know

Direction only (dialogue removed — this is what prompt-sim compares against):
A young man with a glacially slow, soft-onset voice that snaps into percussive emphasis on key words, delivering this high-quality studio voice recording with no background noise. The same voice is a strained blend of amusement and relief, despite a sharp, grinding pain that makes each syllable an effort. (He touches the wound with trembling fingers, a pained but amused exhale escaping.) (He shifts his weight, then lets out a short, ragged chuckle.) (He pauses, breathing slowly.) (A soft, wheezing laugh.) "At least now I know

What to say (goes in MOSS text field): Well, that's one way to break the ice. I guess I should've seen that coming. But honestly, I'm just glad it's over.

with_dialogue · no_ref
prompt-sim × invWER
best-of-16rew·ps0.013invWER0.962WER0.038prompt-sim+0.014blend3.636genu1.671
best-of-8rew·ps-0.042invWER0.962WER0.038prompt-sim-0.044blend2.781genu1.719
best-of-6rew·ps0.013invWER0.962WER0.038prompt-sim+0.014blend3.636genu1.671
best-of-4rew·ps0.013invWER0.962WER0.038prompt-sim+0.014blend3.636genu1.671
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all1.706invWER0.962WER0.038prompt-sim+0.008blend6.162genu1.760
best-of-8rew·all1.706invWER0.962WER0.038prompt-sim+0.008blend6.162genu1.760
best-of-6rew·all1.706invWER0.962WER0.038prompt-sim+0.008blend6.162genu1.760
best-of-4rew·all1.388invWER0.962WER0.038prompt-sim-0.185blend5.562genu1.544
with_dialogue · emo_ref
prompt-sim × invWER
best-of-16rew·ps0.021invWER0.962WER0.038prompt-sim+0.022blend0.183genu3.405
best-of-8rew·ps-0.046invWER0.808WER0.192prompt-sim-0.058blend2.530genu5.049
best-of-6rew·ps0.021invWER0.962WER0.038prompt-sim+0.022blend0.183genu3.405
best-of-4rew·ps0.021invWER0.962WER0.038prompt-sim+0.022blend0.183genu3.405
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all1.566invWER0.962WER0.038prompt-sim-0.088blend1.935genu4.570
best-of-8rew·all1.566invWER0.962WER0.038prompt-sim-0.088blend1.935genu4.570
best-of-6rew·all1.566invWER0.962WER0.038prompt-sim-0.088blend1.935genu4.570
best-of-4rew·all1.515invWER0.923WER0.077prompt-sim-0.088blend1.746genu4.783
no_dialogue · no_ref
prompt-sim × invWER
best-of-16rew·ps0.167invWER0.962WER0.038prompt-sim+0.174blend1.295genu1.153
best-of-8rew·ps0.033invWER0.962WER0.038prompt-sim+0.034blend7.051genu1.877
best-of-6rew·ps0.167invWER0.962WER0.038prompt-sim+0.174blend1.295genu1.153
best-of-4rew·ps0.167invWER0.962WER0.038prompt-sim+0.174blend1.295genu1.153
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all1.849invWER0.962WER0.038prompt-sim+0.034blend7.051genu1.877
best-of-8rew·all1.493invWER0.962WER0.038prompt-sim-0.028blend4.469genu1.825
best-of-6rew·all1.582invWER0.962WER0.038prompt-sim-0.008blend5.090genu1.817
best-of-4rew·all1.554invWER0.962WER0.038prompt-sim-0.006blend4.319genu2.167
no_dialogue · emo_ref
prompt-sim × invWER
best-of-16rew·ps0.038invWER0.962WER0.038prompt-sim+0.039blend1.981genu4.880
best-of-8rew·ps0.038invWER0.962WER0.038prompt-sim+0.039blend1.981genu4.880
best-of-6rew·ps0.038invWER0.962WER0.038prompt-sim+0.039blend1.981genu4.880
best-of-4rew·ps0.034invWER0.962WER0.038prompt-sim+0.035blend1.071genu4.666
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all1.764invWER0.962WER0.038prompt-sim+0.039blend1.981genu4.880
best-of-8rew·all1.707invWER0.923WER0.077prompt-sim-0.073blend3.839genu4.512
best-of-6rew·all1.707invWER0.923WER0.077prompt-sim-0.073blend3.839genu4.512
best-of-4rew·all1.764invWER0.962WER0.038prompt-sim+0.039blend1.981genu4.880
NONCCcca_voicenet_9837_noncc cca_voicenet
SAY: It's just... the way the light hits those leaves in the afternoon. I always thought that was the most peaceful thing.
original DramaBox prompt & direction text

Full DramaBox prompt (how to say — with the "quoted" dialogue):
A middle-to-late-aged speaker with a grainy, androgynous timbre, delivering this high-quality studio voice recording with no background noise. The same voice is caught in a tight spiral of helpless rage, forcing a veneer of calm contemplation. (A slow, deliberate exhale, jaw tight) "It's just... the way the light hits those leaves in the afternoon." (A pause, swallowing) "I always thought that was the most peaceful thing." (Fingers drumming

Direction only (dialogue removed — this is what prompt-sim compares against):
A middle-to-late-aged speaker with a grainy, androgynous timbre, delivering this high-quality studio voice recording with no background noise. The same voice is caught in a tight spiral of helpless rage, forcing a veneer of calm contemplation. (A slow, deliberate exhale, jaw tight) (A pause, swallowing) (Fingers drumming

What to say (goes in MOSS text field): It's just... the way the light hits those leaves in the afternoon. I always thought that was the most peaceful thing.

with_dialogue · no_ref
prompt-sim × invWER
best-of-16rew·ps0.113invWER1.000WER0.000prompt-sim+0.113blend6.475genu1.529
best-of-8rew·ps-0.004invWER0.409WER0.591prompt-sim-0.011blend8.912genu1.574
best-of-6rew·ps0.113invWER1.000WER0.000prompt-sim+0.113blend6.475genu1.529
best-of-4rew·ps0.113invWER1.000WER0.000prompt-sim+0.113blend6.475genu1.529
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all1.899invWER1.000WER0.000prompt-sim+0.113blend6.475genu1.529
best-of-8rew·all1.753invWER1.000WER0.000prompt-sim-0.057blend6.552genu1.845
best-of-6rew·all1.737invWER1.000WER0.000prompt-sim-0.058blend6.538genu1.761
best-of-4rew·all1.132invWER1.000WER0.000prompt-sim-0.265blend3.958genu1.300
with_dialogue · emo_ref
prompt-sim × invWER
best-of-16rew·ps0.122invWER1.000WER0.000prompt-sim+0.122blend5.439genu1.220
best-of-8rew·ps0.122invWER1.000WER0.000prompt-sim+0.122blend5.439genu1.220
best-of-6rew·ps0.122invWER1.000WER0.000prompt-sim+0.122blend5.439genu1.220
best-of-4rew·ps0.009invWER1.000WER0.000prompt-sim+0.009blend5.494genu1.461
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all1.876invWER1.000WER0.000prompt-sim+0.073blend7.026genu1.301
best-of-8rew·all1.876invWER1.000WER0.000prompt-sim+0.073blend7.026genu1.301
best-of-6rew·all1.739invWER1.000WER0.000prompt-sim+0.113blend5.479genu1.214
best-of-4rew·all1.707invWER0.955WER0.045prompt-sim-0.038blend6.738genu1.795
no_dialogue · no_ref
prompt-sim × invWER
best-of-16rew·ps0.044invWER0.773WER0.227prompt-sim+0.057blend6.461genu1.498
best-of-8rew·ps0.044invWER0.773WER0.227prompt-sim+0.057blend6.461genu1.498
best-of-6rew·ps-0.053invWER1.000WER0.000prompt-sim-0.053blend2.720genu0.719
best-of-4rew·ps0.000invWER0.955WER0.045prompt-sim+0.000blend5.366genu2.214
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all1.668invWER0.955WER0.045prompt-sim+0.000blend5.366genu2.214
best-of-8rew·all1.439invWER1.000WER0.000prompt-sim-0.206blend5.176genu1.956
best-of-6rew·all1.411invWER0.773WER0.227prompt-sim+0.057blend6.461genu1.498
best-of-4rew·all1.498invWER1.000WER0.000prompt-sim-0.049blend4.974genu1.269
no_dialogue · emo_ref
prompt-sim × invWER
best-of-16rew·ps0.168invWER0.955WER0.045prompt-sim+0.176blend1.890genu1.106
best-of-8rew·ps0.168invWER0.955WER0.045prompt-sim+0.176blend1.890genu1.106
best-of-6rew·ps0.101invWER0.955WER0.045prompt-sim+0.105blend4.670genu1.212
best-of-4rew·ps0.168invWER0.955WER0.045prompt-sim+0.176blend1.890genu1.106
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all2.001invWER1.000WER0.000prompt-sim+0.044blend7.806genu1.767
best-of-8rew·all2.001invWER1.000WER0.000prompt-sim+0.044blend7.806genu1.767
best-of-6rew·all1.814invWER1.000WER0.000prompt-sim-0.045blend7.447genu1.506
best-of-4rew·all1.754invWER1.000WER0.000prompt-sim+0.138blend5.475genu1.123
NONCCcc2c_archetype_265_noncc cc2c_archetype
SAY: I told you I don't have time for this.
original DramaBox prompt & direction text

Full DramaBox prompt (how to say — with the "quoted" dialogue):
A 28-year-old woman with a husky, smoky voice, delivering this high-quality studio voice recording with no background noise. The same voice is brittle and fast, her words clipped with a low, agitated hum of numbness and irritation. (breathing out sharply) "I told you I don't have time for this." (tapping a nail) "Just say what you want and get it over with

Direction only (dialogue removed — this is what prompt-sim compares against):
A 28-year-old woman with a husky, smoky voice, delivering this high-quality studio voice recording with no background noise. The same voice is brittle and fast, her words clipped with a low, agitated hum of numbness and irritation. (breathing out sharply) (tapping a nail) "Just say what you want and get it over with

What to say (goes in MOSS text field): I told you I don't have time for this.

with_dialogue · no_ref
prompt-sim × invWER
best-of-8rew·ps-0.000invWER0.000WER1.000prompt-sim-0.120blend4.446genu1.455
best-of-6rew·ps0.000invWER0.000WER1.000prompt-sim+0.056blend5.097genu1.552
best-of-4rew·ps0.000invWER0.000WER1.000prompt-sim+0.033blend3.216genu1.121
invWER × (norm prompt-sim + blend + genu)
best-of-8rew·all2.020invWER1.000WER0.000prompt-sim-0.008blend8.416genu1.850
best-of-6rew·all2.020invWER1.000WER0.000prompt-sim-0.008blend8.416genu1.850
best-of-4rew·all1.513invWER1.000WER0.000prompt-sim-0.052blend4.894genu1.443
with_dialogue · emo_ref
prompt-sim × invWER
best-of-16rew·ps-0.000invWER0.000WER1.000prompt-sim-0.179blend3.882genu1.640
best-of-8rew·ps-0.000invWER0.000WER1.000prompt-sim-0.296blend0.138genu1.326
best-of-6rew·ps-0.000invWER0.000WER1.000prompt-sim-0.179blend3.882genu1.640
best-of-4rew·ps-0.005invWER0.100WER0.900prompt-sim-0.049blend4.024genu1.481
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all1.524invWER1.000WER0.000prompt-sim-0.097blend5.224genu1.627
best-of-8rew·all1.524invWER1.000WER0.000prompt-sim-0.097blend5.224genu1.627
best-of-6rew·all0.141invWER0.100WER0.900prompt-sim-0.161blend4.407genu1.969
best-of-4rew·all1.524invWER1.000WER0.000prompt-sim-0.097blend5.224genu1.627
no_dialogue · no_ref
prompt-sim × invWER
best-of-16rew·ps0.019invWER0.700WER0.300prompt-sim+0.028blend6.740genu1.593
best-of-8rew·ps-0.000invWER0.000WER1.000prompt-sim-0.166blend2.306genu-0.076
best-of-6rew·ps0.019invWER0.700WER0.300prompt-sim+0.028blend6.740genu1.593
best-of-4rew·ps-0.000invWER0.000WER1.000prompt-sim-0.120blend2.364genu0.820
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all1.799invWER1.000WER0.000prompt-sim-0.029blend6.664genu1.849
best-of-8rew·all1.799invWER1.000WER0.000prompt-sim-0.029blend6.664genu1.849
best-of-6rew·all1.799invWER1.000WER0.000prompt-sim-0.029blend6.664genu1.849
best-of-4rew·all1.344invWER1.000WER0.000prompt-sim-0.241blend4.685genu1.960
no_dialogue · emo_ref
prompt-sim × invWER
best-of-16rew·ps-0.000invWER0.000WER1.000prompt-sim-0.141blend2.521genu1.418
best-of-8rew·ps-0.000invWER0.000WER2.200prompt-sim-0.023blend2.027genu0.928
best-of-6rew·ps-0.000invWER0.000WER1.100prompt-sim-0.112blend3.270genu1.722
best-of-4rew·ps-0.000invWER0.000WER1.100prompt-sim-0.112blend3.270genu1.722
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all1.155invWER1.000WER0.000prompt-sim-0.219blend3.328genu1.549
best-of-8rew·all1.136invWER1.000WER0.000prompt-sim-0.230blend2.704genu1.950
best-of-6rew·all1.062invWER1.000WER0.000prompt-sim-0.063blend1.533genu1.028
best-of-4rew·all1.038invWER1.000WER0.000prompt-sim-0.283blend3.637genu1.067
NONCCsit_situation_2127_noncc sit_situation
SAY: Y entonces el tipo me dice, 'estás buenísima, ¿cómo es que estás sola?'
original DramaBox prompt & direction text

Full DramaBox prompt (how to say — with the "quoted" dialogue):
A 25-year-old woman with a bright but fraying vocal quality, delivering this high-quality studio voice recording with no background noise. The same voice is riding a second wind at a 3 AM after-party, forcing laughter as she recounts a crude comment, but disgust is already tightening her throat. (laughing too loudly) "Y entonces el tipo me dice, 'estás buenísima, ¿cómo es que estás sola?'" (voice cracking, swallowing) "

Direction only (dialogue removed — this is what prompt-sim compares against):
A 25-year-old woman with a bright but fraying vocal quality, delivering this high-quality studio voice recording with no background noise. The same voice is riding a second wind at a 3 AM after-party, forcing laughter as she recounts a crude comment, but disgust is already tightening her throat. (laughing too loudly) (voice cracking, swallowing) "

What to say (goes in MOSS text field): Y entonces el tipo me dice, 'estás buenísima, ¿cómo es que estás sola?'

with_dialogue · no_ref
prompt-sim × invWER
best-of-16rew·ps-0.049invWER0.923WER0.077prompt-sim-0.053blend5.030genu2.016
best-of-8rew·ps-0.049invWER0.923WER0.077prompt-sim-0.053blend5.030genu2.016
best-of-6rew·ps-0.179invWER1.000WER0.000prompt-sim-0.179blend6.532genu2.033
best-of-4rew·ps-0.123invWER0.692WER0.308prompt-sim-0.177blend5.949genu2.254
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all1.634invWER1.000WER0.000prompt-sim-0.179blend6.532genu2.033
best-of-8rew·all1.514invWER1.000WER0.000prompt-sim-0.306blend7.340genu1.661
best-of-6rew·all1.514invWER1.000WER0.000prompt-sim-0.306blend7.340genu1.661
best-of-4rew·all1.514invWER1.000WER0.000prompt-sim-0.306blend7.340genu1.661
with_dialogue · emo_ref
prompt-sim × invWER
best-of-16rew·ps-0.018invWER0.077WER0.923prompt-sim-0.230blend1.581genu1.092
best-of-8rew·ps-0.070invWER0.538WER0.462prompt-sim-0.131blend1.639genu1.624
best-of-6rew·ps-0.018invWER0.077WER0.923prompt-sim-0.230blend1.581genu1.092
best-of-4rew·ps-0.069invWER0.231WER0.769prompt-sim-0.300blend1.193genu0.914
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all1.250invWER1.000WER0.000prompt-sim-0.287blend2.788genu3.058
best-of-8rew·all1.250invWER1.000WER0.000prompt-sim-0.287blend2.788genu3.058
best-of-6rew·all1.250invWER1.000WER0.000prompt-sim-0.287blend2.788genu3.058
best-of-4rew·all1.029invWER0.923WER0.077prompt-sim-0.255blend4.259genu0.899
no_dialogue · no_ref
prompt-sim × invWER
best-of-16rew·ps-0.056invWER0.769WER0.231prompt-sim-0.073blend6.242genu2.977
best-of-8rew·ps-0.056invWER0.769WER0.231prompt-sim-0.073blend6.242genu2.977
best-of-6rew·ps-0.056invWER0.769WER0.231prompt-sim-0.073blend6.242genu2.977
best-of-4rew·ps-0.056invWER0.769WER0.231prompt-sim-0.073blend6.242genu2.977
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all1.643invWER1.000WER0.000prompt-sim-0.306blend7.983genu2.026
best-of-8rew·all1.643invWER1.000WER0.000prompt-sim-0.306blend7.983genu2.026
best-of-6rew·all1.643invWER1.000WER0.000prompt-sim-0.306blend7.983genu2.026
best-of-4rew·all1.473invWER1.000WER0.000prompt-sim-0.087blend4.898genu1.456
no_dialogue · emo_ref
prompt-sim × invWER
best-of-16rew·ps-0.000invWER0.000WER1.154prompt-sim-0.434blend0.187genu1.841
best-of-8rew·ps-0.020invWER0.923WER0.077prompt-sim-0.022blend0.488genu2.498
best-of-6rew·ps-0.000invWER0.000WER1.000prompt-sim-0.229blend3.767genu4.577
best-of-4rew·ps-0.000invWER0.000WER1.154prompt-sim-0.434blend0.187genu1.841
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all1.264invWER1.000WER0.000prompt-sim-0.458blend5.339genu2.645
best-of-8rew·all1.213invWER1.000WER0.000prompt-sim-0.415blend6.225genu1.365
best-of-6rew·all1.264invWER1.000WER0.000prompt-sim-0.458blend5.339genu2.645
best-of-4rew·all1.130invWER0.923WER0.077prompt-sim-0.022blend0.488genu2.498
NONCCcc2c_archetype_4265_noncc cc2c_archetype
SAY: I still scan every window. Every shadow.
original DramaBox prompt & direction text

Full DramaBox prompt (how to say — with the "quoted" dialogue):
A 30s male with a tightly controlled, gravelly tenor, delivering this high-quality studio voice recording with no background noise. The same voice is a watchful protector, sour with unresolved betrayal, prideful in his vigilance, and aching with longing for a lost partner. (breathing slow, jaw tight) "I still scan every window. Every shadow." (shifting weight, glancing) "She'd tell me to let it go. I can

Direction only (dialogue removed — this is what prompt-sim compares against):
A 30s male with a tightly controlled, gravelly tenor, delivering this high-quality studio voice recording with no background noise. The same voice is a watchful protector, sour with unresolved betrayal, prideful in his vigilance, and aching with longing for a lost partner. (breathing slow, jaw tight) (shifting weight, glancing) "She'd tell me to let it go. I can

What to say (goes in MOSS text field): I still scan every window. Every shadow.

with_dialogue · no_ref
prompt-sim × invWER
best-of-16rew·ps-0.000invWER0.000WER1.143prompt-sim-0.265blend4.663genu0.993
best-of-8rew·ps-0.000invWER0.000WER1.143prompt-sim-0.265blend4.663genu0.993
best-of-6rew·ps-0.000invWER0.000WER1.143prompt-sim-0.265blend4.663genu0.993
best-of-4rew·ps-0.096invWER0.714WER0.286prompt-sim-0.135blend5.665genu1.110
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all1.649invWER1.000WER0.000prompt-sim-0.190blend7.365genu1.623
best-of-8rew·all1.566invWER0.857WER0.143prompt-sim-0.007blend6.403genu2.040
best-of-6rew·all1.649invWER1.000WER0.000prompt-sim-0.190blend7.365genu1.623
best-of-4rew·all1.642invWER1.000WER0.000prompt-sim-0.183blend7.352genu1.533
with_dialogue · emo_ref
prompt-sim × invWER
best-of-16rew·ps-0.000invWER0.000WER3.571prompt-sim-0.293blend0.370genu2.221
best-of-8rew·ps-0.000invWER0.000WER1.000prompt-sim-0.119blend0.502genu0.680
best-of-6rew·ps-0.000invWER0.000WER1.143prompt-sim-0.125blend3.280genu1.968
best-of-4rew·ps-0.000invWER0.000WER3.714prompt-sim-0.272blend0.000genu3.034
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all1.081invWER1.000WER0.000prompt-sim-0.277blend3.015genu1.746
best-of-8rew·all1.050invWER1.000WER0.000prompt-sim-0.301blend2.402genu2.161
best-of-6rew·all1.081invWER1.000WER0.000prompt-sim-0.277blend3.015genu1.746
best-of-4rew·all0.733invWER0.714WER0.286prompt-sim-0.261blend2.620genu1.546
no_dialogue · no_ref
prompt-sim × invWER
best-of-16rew·ps-0.000invWER0.000WER1.429prompt-sim-0.032blend3.152genu1.244
best-of-8rew·ps-0.000invWER0.000WER2.714prompt-sim-0.230blend4.432genu2.293
best-of-6rew·ps-0.000invWER0.000WER1.571prompt-sim-0.160blend4.876genu1.351
best-of-4rew·ps-0.000invWER0.000WER1.000prompt-sim-0.185blend6.584genu1.679
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all1.634invWER1.000WER0.000prompt-sim-0.005blend5.751genu1.255
best-of-8rew·all1.330invWER1.000WER0.000prompt-sim-0.078blend4.709genu0.606
best-of-6rew·all1.330invWER1.000WER0.000prompt-sim-0.078blend4.709genu0.606
best-of-4rew·all1.634invWER1.000WER0.000prompt-sim-0.005blend5.751genu1.255
no_dialogue · emo_ref
prompt-sim × invWER
best-of-16rew·ps-0.000invWER0.000WER2.000prompt-sim-0.271blend0.000genu1.249
best-of-8rew·ps-0.000invWER0.000WER2.000prompt-sim-0.271blend0.000genu1.249
best-of-6rew·ps-0.000invWER0.000WER1.286prompt-sim-0.237blend0.309genu0.704
best-of-4rew·ps-0.000invWER0.000WER2.000prompt-sim-0.271blend0.000genu1.249
invWER × (norm prompt-sim + blend + genu)
best-of-16rew·all1.642invWER1.000WER0.000prompt-sim-0.239blend5.185genu3.497
best-of-8rew·all1.510invWER1.000WER0.000prompt-sim-0.225blend6.607genu1.538
best-of-6rew·all1.642invWER1.000WER0.000prompt-sim-0.239blend5.185genu3.497
best-of-4rew·all1.302invWER0.857WER0.143prompt-sim-0.103blend4.578genu2.105