Each embedded DramaBox clip is reinterpreted by MOSS-TTS-4.55B voice-acting-v2 (the base checkpoint for our LoRAs): the original audio is fed back as the reference together with its own GENERAL/SCRIPT prompt, and the model regenerates the same line as a batched group of 8 candidates. Candidates are ranked by emotional similarity to the original × inverse WER; the top 3 are shown next to the original. Regenerating and reward-ranking cleans up disfluencies and mistakes while staying faithful to the original emotion.
A feminine voice, voice at peak biological vigor. Timbre: the treble frequencies are significantly; standard human baseline; standard. Delivery: whisper-talk, casual, monologue. Emotion: confusion, emotional numbness, te
● ORIGINAL · 2.54s
the embedded DramaBox clip
✦ TOP 1
reward 0.699 · emo-sim 0.699 · WER 0.000 · 3.84s
“Part of me. Don't know my name, Hank.”
✦ TOP 2
reward 0.525 · emo-sim 0.525 · WER 0.000 · 3.76s
“Part of me don't know my name Hank.”
✦ TOP 3
reward 0.000 · emo-sim 0.581 · WER 1.000 · 2.64s
“Part of me don't know my name Hank. Part of me don't know my name Hank.”
#30 · “Oh, isn't it just the funniest thing that the absolute absurdity gone? The absolute absurdity is gone. I- isn't at all.”
A feminine voice, the acoustic signature reflects a fully. Timbre: the high frequencies are distinctly; standard human baseline; standard. Delivery: casual, playful, conversational. Emotion: amusement, astonishment surpr
● ORIGINAL · 7.49s
the embedded DramaBox clip
✦ TOP 1
reward 0.352 · emo-sim 0.622 · WER 0.435 · 10.24s
“Oh, isn't it just the funniest thing that the absolute absurdity gone? The absolute absur”
✦ TOP 2
reward 0.304 · emo-sim 0.304 · WER 0.000 · 10.0s
“Oh! Isn't it just the funniest thing that the absolute absurdity gone? The absolute absurd”
✦ TOP 3
reward 0.250 · emo-sim 0.411 · WER 0.391 · 10.88s
“Oh, isn't it just the funniest thing that the absolute absurdity is gone?”
#31 · “I mean, think about it, a cow quake! Whoever”
A the acoustic profile features, clear. Timbre: treble frequencies are heavily emphasized; standard human baseline; standard. Delivery: casual, storytelling, conversational. Emotion: interest, amusement, teasing, astonis
● ORIGINAL · 3.06s
the embedded DramaBox clip
✦ TOP 1
reward 0.000 · emo-sim 0.860 · WER 1.000 · 3.84s
“I mean, think about it, a cow quake, whoever. I mean, think about it, a cow quake, whoeve”
✦ TOP 2
reward 0.000 · emo-sim 0.891 · WER 1.000 · 4.48s
“I mean, think about it. A cow quake. Whoever. I mean, think about it. A cow quake. Wh”
✦ TOP 3
reward 0.000 · emo-sim 0.876 · WER 1.000 · 4.4s
“I mean, think about it, a cow quake. Whoever. I mean, think about it, a cow quake. Whoe”
#32 · “heard of such a thing? Start,”
A feminine voice, voice at peak biological vigor. Timbre: perfect; standard human baseline; standard. Delivery: casual, playful, dramatic. Emotion: interest, concentration, disgust, elation, contempt. Genuineness 2.252/6
● ORIGINAL · 22.84s
the embedded DramaBox clip
✦ TOP 1
reward 0.045 · emo-sim 0.272 · WER 0.833 · 2.8s
“Heard of such a thing? Heard of such a thing?”
✦ TOP 2
reward 0.000 · emo-sim 0.249 · WER 1.000 · 5.2s
“Heard of such a thing. Start. Heard of such a thing. Start.”
✦ TOP 3
reward -0.000 · emo-sim -0.354 · WER 1.000 · 6.4s
“Heard of such a thing? Start Heard of such a thing? Start”
#33 · “though I do miss my teapot, but really isn't life just wonderfully unpredictable?”
A the audio delivers a, the acoustic signature reflects a fully. Timbre: perfect; standard human baseline; standard. Delivery: playful, conversational, casual. Emotion: amusement, interest, astonishment surprise, teasing
● ORIGINAL · 6.32s
the embedded DramaBox clip
✦ TOP 1
reward 0.809 · emo-sim 0.809 · WER 0.000 · 6.08s
“Though I do miss my teapot, but really isn't life just wonderfully unpredictable?”
✦ TOP 2
reward 0.763 · emo-sim 0.763 · WER 0.000 · 6.64s
“Though I do miss my teapot, but really isn't life just wonderfully unpredictable?”
✦ TOP 3
reward 0.759 · emo-sim 0.759 · WER 0.000 · 6.16s
“Though I do miss my teapot, but really isn't life just wonderfully unpredictable?”
#34 · “And the colors afterwards, the sky was the most vibrant shade of lavender I've ever seen.”
A the audio delivers a, the acoustic signature reflects a fully. Timbre: perfect; standard human baseline; standard. Delivery: narrator, monologue, storytelling. Emotion: interest, awe, hope enthusiasm optimism, amusemen
● ORIGINAL · 5.24s
the embedded DramaBox clip
✦ TOP 1
reward 0.000 · emo-sim 0.858 · WER 1.000 · 6.24s
“And the colors afterwards, the sky was the most vibrant shade of lavender I've ever seen. ”
✦ TOP 2
reward 0.000 · emo-sim 0.605 · WER 1.000 · 8.0s
“And the colors afterwards, the sky was the most vibrant shade of lavender I've ever seen. ”
✦ TOP 3
reward 0.000 · emo-sim 0.921 · WER 1.000 · 7.28s
“And the colors afterwards, the sky was the most vibrant shade of lavender I've ever seen. ”
#35 · “It's almost beautiful in a terribly disorienting sort of way almost.”
A feminine voice, the acoustic signature reflects a fully. Timbre: perfect; highly pleasant; standard. Delivery: monologue, narrator, asmr. Emotion: contemplation, awe, sadness, emotional numbness, disappointment. Genuin
● ORIGINAL · 6.0s
the embedded DramaBox clip
✦ TOP 1
reward 0.558 · emo-sim 0.558 · WER 0.000 · 6.96s
“It's almost beautiful in a terribly disorienting sort of way, almost.”
✦ TOP 2
reward 0.266 · emo-sim 0.266 · WER 0.000 · 6.56s
“It's almost beautiful in a terribly disorienting sort of way almost.”
✦ TOP 3
reward 0.000 · emo-sim 0.311 · WER 1.000 · 7.12s
“It's almost beautiful in a terribly disorienting sort of way, almost. It's almost beautif”
#37 · “The the application process, quite lengthy, was it. I s- quite a long wait personally. I've spent an incredible amount o”
A the audio delivers a, the acoustic signature reflects a fully. Timbre: the treble frequencies are significantly; standard human baseline; a distinct. Delivery: monologue, cartoonish, narrator. Emotion: interest, concen
● ORIGINAL · 30.23s
the embedded DramaBox clip
✦ TOP 1
reward 0.085 · emo-sim 0.256 · WER 0.667 · 31.92s
“Did the application process quite lengthy, was it? I sssss... quite a long wait personall”
✦ TOP 2
reward 0.039 · emo-sim 0.331 · WER 0.881 · 13.92s
“The application process quite lengthy was it. The application process quite lengthy was i”
✦ TOP 3
reward 0.034 · emo-sim 0.579 · WER 0.941 · 36.72s
“the application process quite lengthy was it quite a long wait personally. I've spent an ”
#38 · “And then the email arrived. It you always know I had a little impression of shock because I I it stated I know congratul”
A the audio delivers a, the acoustic signature reflects a fully. Timbre: the treble frequencies are significantly; standard human baseline; a distinct. Delivery: casual, conversational, monologue. Emotion: interest, hope
● ORIGINAL · 29.28s
the embedded DramaBox clip
✦ TOP 1
reward 0.068 · emo-sim 0.648 · WER 0.895 · 31.68s
“and then the email arrived. You always know I had a little impression of shock because, a”
✦ TOP 2
reward 0.020 · emo-sim 0.683 · WER 0.970 · 31.04s
“and then the email arrived. You always know I had a little impression of shock because I,”
✦ TOP 3
reward 0.000 · emo-sim 0.592 · WER 1.015 · 36.48s
“And then the email arrived. You always know I had a little impression of shock because I,”
#39 · “The the application process, quite lengthy, was it. I s- quite a long wait personally. I've spent an incredible”
A the audio delivers a, the acoustic signature reflects a fully. Timbre: high-frequency energy is present but; standard human baseline; standard. Delivery: whisper-talk, casual, conversational. Emotion: interest, concent
● ORIGINAL · 6.29s
the embedded DramaBox clip
✦ TOP 1
reward 0.331 · emo-sim 0.552 · WER 0.400 · 8.0s
“the application process. Quite lengthy was it? I've spent an incredible...”
✦ TOP 2
reward 0.206 · emo-sim 0.515 · WER 0.600 · 10.32s
“the application process quite lengthy, was it? I've spent an incredible... the applicatio”
✦ TOP 3
reward 0.107 · emo-sim 0.716 · WER 0.850 · 10.72s
“The application process quite lengthy was it? Quite a long wait personally. I've spent a”
#40 · “amount of time on my non-linear documentation”
A the audio delivers a, the acoustic signature reflects a fully. Timbre: high-frequency energy is present but; standard human baseline; standard. Delivery: formal, narrator, monologue. Emotion: interest, concentration, e
● ORIGINAL · 3.19s
the embedded DramaBox clip
✦ TOP 1
reward 0.733 · emo-sim 0.733 · WER 0.000 · 4.56s
“Amount of time on my non-linear documentation.”
✦ TOP 2
reward 0.511 · emo-sim 0.681 · WER 0.250 · 5.6s
“Amount of time on my nonlinear documentation.”
✦ TOP 3
reward 0.000 · emo-sim 0.826 · WER 1.000 · 4.88s
“amount of time on my nonlinear documentation. Amount of time on my nonlinear documentatio”
#41 · “it involved numerous forms and reports and replication steps, all quite immaculate outside our website.”
A the audio delivers a, the acoustic signature reflects a fully. Timbre: high-frequency energy is present but; standard human baseline; standard. Delivery: whisper-talk, narrator, monologue. Emotion: interest, concentrat
● ORIGINAL · 7.28s
the embedded DramaBox clip
✦ TOP 1
reward 0.866 · emo-sim 0.866 · WER 0.000 · 9.28s
“It involved numerous forms and reports and replication steps, all quite immaculate outside”
✦ TOP 2
reward 0.809 · emo-sim 0.809 · WER 0.000 · 9.92s
“It involved numerous forms and reports and replication steps, all quite immaculate outside”
✦ TOP 3
reward 0.777 · emo-sim 0.777 · WER 0.000 · 9.68s
“It involved numerous forms and reports and replication steps, all quite immaculate outside”
#42 · “I did check the fe- February deadline several times, of course, to ensure I wasn't missing anything.”
A the audio delivers a, the acoustic signature reflects a fully. Timbre: perfect; standard human baseline; standard. Delivery: narrator, monologue, formal. Emotion: disappointment, emotional numbness, interest, concentra
● ORIGINAL · 6.45s
the embedded DramaBox clip
✦ TOP 1
reward 0.762 · emo-sim 0.807 · WER 0.056 · 5.68s
“I did check the FIP February deadline several times, of course, to ensure I wasn't missing”
✦ TOP 2
reward 0.761 · emo-sim 0.806 · WER 0.056 · 7.6s
“I did check the February deadline several times of course to ensure I wasn't missing anyth”
✦ TOP 3
reward 0.605 · emo-sim 0.640 · WER 0.056 · 8.08s
“I did check the February deadline several times, of course, to ensure I wasn't missing any”
#43 · “The Harvard recommendation letters I said required quite a bit of coordination with former professors, which took some e”
A the audio delivers a, the acoustic signature reflects a fully. Timbre: perfect; standard human baseline; standard. Delivery: formal, monologue, narrator. Emotion: interest, concentration, amusement, hope enthusiasm opt
● ORIGINAL · 7.02s
the embedded DramaBox clip
✦ TOP 1
reward 0.774 · emo-sim 0.774 · WER 0.000 · 9.28s
“The Harvard recommendation letters I said required quite a bit of coordination with former”
✦ TOP 2
reward 0.673 · emo-sim 0.673 · WER 0.000 · 8.08s
“The Harvard recommendation letters I said required quite a bit of coordination with former”
✦ TOP 3
reward 0.113 · emo-sim 0.867 · WER 0.870 · 7.36s
“The Harvard recommendation letters I said required quite a bit of coordination with former”
#44 · “And then the email arrived. It you always know I had a little impression of shock because I I it stated I know congratul”
A the audio delivers a, the acoustic signature reflects a fully. Timbre: the treble frequencies are significantly; standard human baseline; a distinct. Delivery: casual, monologue, conversational. Emotion: interest, reli
● ORIGINAL · 15.31s
the embedded DramaBox clip
✦ TOP 1
reward 0.069 · emo-sim 0.602 · WER 0.886 · 20.64s
“and then the email arrived. You always know I had a little impression of shock because it”
✦ TOP 2
reward 0.044 · emo-sim 0.517 · WER 0.914 · 14.8s
“And then the email arrived. You always know I had a little impression of shock because it”
✦ TOP 3
reward 0.027 · emo-sim 0.472 · WER 0.943 · 20.4s
“and then the email arrived. You always know I had a little impression of shock because I,”
#45 · “I reread it three times before I fully processed the information a rather unusual occurrence for me”
A the audio delivers a, the voice begins to display the. Timbre: high-frequency energy is present but; standard human baseline; standard. Delivery: monologue, teacher/didactic, whisper-talk. Emotion: interest, concentrat
● ORIGINAL · 8.57s
the embedded DramaBox clip
✦ TOP 1
reward 0.473 · emo-sim 0.536 · WER 0.118 · 9.76s
“I re-read it three times before I fully processed the information. A rather unusual occur”
✦ TOP 2
reward 0.000 · emo-sim 0.708 · WER 1.177 · 8.56s
“I re-read it three times before I fully processed the information. A rather unusual occur”
✦ TOP 3
reward 0.000 · emo-sim 0.495 · WER 1.059 · 7.76s
“I reread it three times before I fully process the information. A rather unusual occurren”
#46 · “there was a small celebratory dance, a very quiet one, naturally, but it happened nonetheless.”
A the audio delivers a, the acoustic signature reflects a fully. Timbre: perfect; standard human baseline; standard. Delivery: narrator, monologue, storytelling. Emotion: interest, concentration, contentment, contemplati
● ORIGINAL · 5.4s
the embedded DramaBox clip
✦ TOP 1
reward 0.856 · emo-sim 0.856 · WER 0.000 · 6.88s
“There was a small celebratory dance, a very quiet one, naturally, but it happened nonethel”
✦ TOP 2
reward 0.837 · emo-sim 0.837 · WER 0.000 · 7.6s
“There was a small celebratory dance, a very quiet one, naturally, but it happened nonethel”
✦ TOP 3
reward 0.813 · emo-sim 0.813 · WER 0.000 · 7.68s
“There was a small celebratory dance, a very quiet one, naturally, but it happened nonethel”
#47 · “es, wie still es hier ist, wie ich dein Herz nicht mehr lesen kann. Bitte, sag mir, dass es nicht vorbei ist, dass es no”
A feminine voice, voice at peak biological vigor. Timbre: perfect; standard human baseline; standard. Delivery: casual, monologue, dramatic. Emotion: distress, helplessness, disappointment, fear, longing. Genuineness 1.9
● ORIGINAL · 28.06s
the embedded DramaBox clip
✦ TOP 1
reward 0.170 · emo-sim 0.551 · WER 0.691 · 19.12s
“Es wie still es hier ist, wie ich dein Herz nicht mehr lesen kann. Nisamme, es wie still ”
✦ TOP 2
reward 0.000 · emo-sim 0.819 · WER 1.218 · 32.32s
“es wie still es hier ist, wie ich dein Herz nicht mehr lesen kann. Bitte, sag mir, dass e”
✦ TOP 3
reward 0.000 · emo-sim 0.810 · WER 1.236 · 34.88s
“Es wie still es hier ist, wie ich dein Herz nicht mehr lesen kann. Bitte, sag mir, dass e”
#48 · “es, wie still es hier ist, wie ich dein Herz nicht mehr lesen kann.”
A feminine voice, the acoustic signature reflects a fully. Timbre: perfect; standard human baseline; standard. Delivery: monologue, casual, dramatic. Emotion: sadness, longing, distress, disappointment, helplessness. Gen
● ORIGINAL · 7.23s
the embedded DramaBox clip
✦ TOP 1
reward 0.850 · emo-sim 0.850 · WER 0.000 · 6.72s
“Es wie still es hier ist, wie ich dein Herz nicht mehr lesen kann.”
✦ TOP 2
reward 0.827 · emo-sim 0.827 · WER 0.000 · 6.08s
“Es wie still es hier ist, wie ich dein Herz nicht mehr lesen kann.”
✦ TOP 3
reward 0.819 · emo-sim 0.819 · WER 0.000 · 8.0s
“Es, wie still es hier ist, wie ich dein Herz nicht mehr lesen kann.”
#49 · “Bitte, sag mir, dass es nicht vorbei ist, dass es noch einen Weg gibt, ich bin so mutverdecklt, dieser Angst, die ist is”
A feminine voice, voice at peak biological vigor. Timbre: perfect; standard human baseline; standard. Delivery: casual, monologue, dramatic. Emotion: distress, helplessness, fear, sadness, disappointment. Genuineness 1.8
● ORIGINAL · 20.83s
the embedded DramaBox clip
✦ TOP 1
reward 0.268 · emo-sim 0.687 · WER 0.610 · 13.76s
“Bitte, sag mir, dass es nicht vorbei ist, dass es noch einen Weg gibt. Ich bin so mutverd”
✦ TOP 2
reward 0.000 · emo-sim 0.777 · WER 1.268 · 26.16s
“Bitte, sag mir, dass es nicht vorbei ist. Dass es noch einen Weg gibt, ich bin so mutverd”
✦ TOP 3
reward 0.000 · emo-sim 0.785 · WER 1.122 · 22.0s
“bitte sag mir, dass es nicht vorbei ist, dass es noch einen Weg gibt. Ich bin so mutverde”
#50 · “es, wie still es hier ist,”
A feminine voice, the acoustic signature reflects a fully. Timbre: perfect; standard human baseline; standard. Delivery: monologue, whisper-talk, formal. Emotion: longing, interest, emotional numbness, infatuation, sadne
● ORIGINAL · 1.47s
the embedded DramaBox clip
✦ TOP 1
reward 0.861 · emo-sim 0.861 · WER 0.000 · 2.72s
“Es wie still es hier ist.”
✦ TOP 2
reward 0.840 · emo-sim 0.840 · WER 0.000 · 2.88s
“Es wie still es hier ist.”
✦ TOP 3
reward 0.700 · emo-sim 0.700 · WER 0.000 · 2.96s
“Es, wie still es hier ist.”
#51 · “wie ich dein Herz nicht mehr lesen kann.”
A feminine voice, voice at peak biological vigor. Timbre: perfect; standard human baseline; standard. Delivery: casual, dramatic, conversational. Emotion: sadness, longing, distress, disappointment, helplessness. Genuine
● ORIGINAL · 5.76s
the embedded DramaBox clip
✦ TOP 1
reward 0.636 · emo-sim 0.636 · WER 0.000 · 4.24s
“wie ich dein Herz nicht mehr lesen kann.”
✦ TOP 2
reward 0.416 · emo-sim 0.416 · WER 0.000 · 3.28s
“wie ich dein Herz nicht mehr lesen kann.”
✦ TOP 3
reward 0.389 · emo-sim 0.389 · WER 0.000 · 3.92s
“wie ich dein Herz nicht mehr lesen kann.”
#52 · “Bitte, sag mir, dass es nicht vorbei ist,”
A feminine voice, voice at peak biological vigor. Timbre: perfect; standard human baseline; standard. Delivery: casual, conversational, whisper-talk. Emotion: sadness, helplessness, distress, disappointment, longing. Gen
● ORIGINAL · 3.38s
the embedded DramaBox clip
✦ TOP 1
reward 0.866 · emo-sim 0.866 · WER 0.000 · 4.32s
“Bitte, sag mir, dass es nicht vorbei ist.”
✦ TOP 2
reward 0.837 · emo-sim 0.956 · WER 0.125 · 3.2s
“Titte, sag mir, dass es nicht vorbei ist.”
✦ TOP 3
reward 0.000 · emo-sim 0.948 · WER 1.000 · 3.36s
“Please tell me that it is not over.”
#53 · “dass es noch einen Weg gibt, ich bin so mutverdecklt, dieser Angst, die ist ist unentreglich, es nennet, hinduebobend, a”
A feminine voice, voice at peak biological vigor. Timbre: perfect; standard human baseline; standard. Delivery: monologue, casual, dramatic. Emotion: fear, distress, sadness, helplessness, disappointment. Genuineness 2.1
● ORIGINAL · 11.47s
the embedded DramaBox clip
✦ TOP 1
reward 0.317 · emo-sim 0.387 · WER 0.182 · 13.68s
“dass es noch einen Weg gibt, ich bin so mutverdeckelt, dieser Angst, die ist, ist unenträg”
✦ TOP 2
reward 0.021 · emo-sim 0.463 · WER 0.955 · 17.68s
“dass es noch einen Weg gibt. Ich bin so mutverdeckelt, dieser Angst, die ist, ist unenträ”
✦ TOP 3
reward 0.000 · emo-sim 0.460 · WER 1.136 · 10.8s
“that there is still a way. I am so covered in fear. This fear is incessant, it is called ”
#54 · “sie ist nur, es gahin, glimemf, mein Angst, Ich liebe dich.”
A feminine voice, voice at peak biological vigor. Timbre: perfect; standard human baseline; standard. Delivery: dramatic, casual, conversational. Emotion: affection, distress, fear, longing, sadness. Genuineness 2.293/6,
● ORIGINAL · 5.98s
the embedded DramaBox clip
✦ TOP 1
reward 0.458 · emo-sim 0.630 · WER 0.273 · 7.76s
“She is nur, es gahin glimmimpf, mein angst, ich liebe dich.”
✦ TOP 2
reward 0.453 · emo-sim 0.713 · WER 0.364 · 7.52s
“Sie ist nur, es gar hin, glimm' empf mein Angst, ich liebe dich.”
✦ TOP 3
reward 0.342 · emo-sim 0.537 · WER 0.364 · 7.76s
“Sie ist nur, es gar hin glimm'mf mein Angst. Ich liebe dich.”