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: perfect; standard human baseline; standard. Delivery: formal, playful, monologue. Emotion: emotional numbness, embarrassment, pleasure ecstasy, sadness, fatigue e
● ORIGINAL · 0.55s
the embedded DramaBox clip
✦ TOP 1
reward 0.000 · emo-sim 0.781 · WER 1.000 · 1.76s
“And so, and so.”
✦ TOP 2
reward 0.000 · emo-sim 0.987 · WER 1.000 · 1.44s
“And so... And so...”
✦ TOP 3
reward 0.000 · emo-sim 0.985 · WER 1.000 · 1.2s
“and so and so”
#83 · “and in the chapter that's right here. Oh”
A feminine voice, voice at peak biological vigor. Timbre: the treble frequencies are significantly; highly functional but distinctly neutral-cool; lmost completely obliterated by violent. Delivery: casual, dramatic, mono
● ORIGINAL · 20.32s
the embedded DramaBox clip
✦ TOP 1
reward -0.000 · emo-sim -0.349 · WER 1.000 · 6.48s
“And in the chapter, that's right here. Oh. And in the chapter, that's right here. Oh.”
✦ TOP 2
reward -0.000 · emo-sim -0.144 · WER 1.111 · 19.2s
“And in the chapter... That's right here. Oh... And in the chapter... That's right here”
✦ TOP 3
reward -0.019 · emo-sim -0.170 · WER 0.889 · 7.2s
“And in the chapter, that's right here. And in the chapter, that's right here.”
#84 · “and in the chapter that's right here. Oh”
A feminine voice, voice at peak biological vigor. Timbre: the treble frequencies are significantly; highly functional but distinctly neutral-cool; lmost completely obliterated by violent. Delivery: casual, dramatic, mono
● ORIGINAL · 20.32s
the embedded DramaBox clip
✦ TOP 1
reward 0.001 · emo-sim 0.010 · WER 0.889 · 7.36s
“And in the chapter that's right here. And in the chapter that's right here.”
✦ TOP 2
reward -0.000 · emo-sim -0.387 · WER 1.000 · 5.04s
“And in the chapter, that's right here. Oh, and in the chapter, that's right here. Oh.”
✦ TOP 3
reward -0.000 · emo-sim -0.417 · WER 1.000 · 5.84s
“And in the chapter that's right here. Oh, and in the chapter that's right here. Oh.”
#85 · “and in the chapter that's right here. Oh”
A feminine voice, voice at peak biological vigor. Timbre: the treble frequencies are significantly; highly functional but distinctly neutral-cool; lmost completely obliterated by violent. Delivery: casual, dramatic, mono
● ORIGINAL · 20.32s
the embedded DramaBox clip
✦ TOP 1
reward -0.000 · emo-sim -0.387 · WER 1.444 · 8.56s
“And in the ch-ch-chapter, that's right here. Oh! And in the ch-ch-chapter, that's right ”
✦ TOP 2
reward -0.000 · emo-sim -0.325 · WER 1.444 · 29.12s
“And in the chapter, that's right here. And in the chapter, that's right here. Dirk, that”
✦ TOP 3
reward -0.000 · emo-sim -0.312 · WER 1.000 · 6.72s
“And in chapter that's right here. Ho. And in chapter that's right here. Ho.”
#86 · “Oh, don't be shy, sweetheart. I've climbed higher than this and danced all night after. The air is so clear up here as i”
A the audio delivers a, the acoustic signature reflects a fully. Timbre: the high frequencies are distinctly; standard human baseline; standard. Delivery: conversational, dramatic, playful. Emotion: interest, hope enthus
● ORIGINAL · 6.65s
the embedded DramaBox clip
✦ TOP 1
reward 0.113 · emo-sim 0.482 · WER 0.767 · 12.72s
“Oh, don't be shy sweetheart. I've climbed higher than this and danced all night after. T”
✦ TOP 2
reward 0.000 · emo-sim 0.649 · WER 1.000 · 10.56s
“Oh, don't be shy, sweetheart. I've climbed higher than this and danced all night after. ”
✦ TOP 3
reward 0.000 · emo-sim 0.732 · WER 1.000 · 9.84s
“Oh, don't be shy sweetheart. I've climbed higher than this and danced all night after. The”
#87 · “Oh, don't be shy, sweetheart. I've climbed higher than this and danced all night after.”
A the audio delivers a, voice at peak biological vigor. Timbre: perfect; standard human baseline; standard. Delivery: conversational, playful, storytelling. Emotion: hope enthusiasm optimism, interest, amusement, affecti
● ORIGINAL · 4.02s
the embedded DramaBox clip
✦ TOP 1
reward 0.885 · emo-sim 0.885 · WER 0.000 · 6.4s
“Oh, don't be shy, sweetheart. I've climbed higher than this and danced all night after.”
✦ TOP 2
reward 0.871 · emo-sim 0.871 · WER 0.000 · 7.04s
“Oh, don't be shy, sweetheart. I've climbed higher than this and danced all night after.”
✦ TOP 3
reward 0.807 · emo-sim 0.807 · WER 0.000 · 6.32s
“Oh, don't be shy, sweetheart. I've climbed higher than this and danced all night after.”
#88 · “The air is so clear up here as it makes a body feel”
A the audio delivers a, voice at peak biological vigor. Timbre: the high frequencies are distinctly; standard human baseline; standard. Delivery: casual, storytelling, playful. Emotion: interest, contemplation, pleasure
● ORIGINAL · 2.63s
the embedded DramaBox clip
✦ TOP 1
reward 0.870 · emo-sim 0.870 · WER 0.000 · 4.0s
“The air is so clear up here as it makes a body feel.”
✦ TOP 2
reward 0.797 · emo-sim 0.797 · WER 0.000 · 4.56s
“The air is so clear up here as it makes a body feel.”
✦ TOP 3
reward 0.706 · emo-sim 0.706 · WER 0.000 · 4.64s
“The air is so clear up here as it makes a body feel.”
#89 · “give me water now! Water, please. I can't”
A the audio delivers a, voice at peak biological vigor. Timbre: the high frequencies are distinctly; distinctly tinny and highly top-heavy; ggressively harsh and distinctly growling. Delivery: cartoonish, casual, dramati
● ORIGINAL · 4.56s
the embedded DramaBox clip
✦ TOP 1
reward 0.249 · emo-sim 0.748 · WER 0.667 · 5.28s
“Give me water now! Water, please! Give me water now! Water, please!”
✦ TOP 2
reward 0.000 · emo-sim 0.957 · WER 1.111 · 4.56s
“Give me water, no! Water, please! I can't! Give me water, no! Water, please! I can't!”
✦ TOP 3
reward 0.000 · emo-sim 0.952 · WER 1.000 · 4.88s
“Give me water now! Water! Please! I can't give me water now! Water! Please! I can't-”
#90 · “give me water now! Water, please. I can't”
A the audio delivers a, voice at peak biological vigor. Timbre: the high frequencies are distinctly; distinctly tinny and highly top-heavy; ggressively harsh and distinctly growling. Delivery: cartoonish, casual, dramati
● ORIGINAL · 4.56s
the embedded DramaBox clip
✦ TOP 1
reward 0.770 · emo-sim 0.770 · WER 0.000 · 5.2s
“Give me water now! Water, please! I can't!”
✦ TOP 2
reward 0.403 · emo-sim 0.906 · WER 0.556 · 10.24s
“Give me water now! Give me water now! WHA-”
✦ TOP 3
reward 0.280 · emo-sim 0.841 · WER 0.667 · 10.24s
“Give me water now! Water, please! Give me water now! Water, please!”
#91 · “give me water now! Water, please. I can't”
A the audio delivers a, voice at peak biological vigor. Timbre: the high frequencies are distinctly; distinctly tinny and highly top-heavy; ggressively harsh and distinctly growling. Delivery: cartoonish, casual, dramati
● ORIGINAL · 4.56s
the embedded DramaBox clip
✦ TOP 1
reward 0.083 · emo-sim 0.748 · WER 0.889 · 10.24s
“Shhh. Give me water now! Water please. Shhh. Give me water now! Water please.”
✦ TOP 2
reward 0.000 · emo-sim 0.943 · WER 1.000 · 6.08s
“Give me water now! Water! Please! I can't! Give me water now! Water! Please! I can't!”
✦ TOP 3
reward 0.000 · emo-sim 0.970 · WER 1.000 · 3.76s
“Give me water now! Water please! I can't! Give me water now! Water please! I can't!”
#94 · “The energy in here is just incredible it's funny, isn't it, how you can feel so disconnected in your own life and then t”
A feminine voice, the voice begins to display the. Timbre: the high frequencies are distinctly; highly pleasant; a distinct. Delivery: conversational, asmr, narrator. Emotion: hope enthusiasm optimism, interest, contentm
● ORIGINAL · 18.3s
the embedded DramaBox clip
✦ TOP 1
reward 0.322 · emo-sim 0.901 · WER 0.643 · 12.72s
“The energy in here is just incredible. It's funny, isn't it? How you can feel so disconn”
✦ TOP 2
reward 0.046 · emo-sim 0.977 · WER 0.952 · 21.12s
“The energy in here is just incredible. It's funny, isn't it, how you can feel so disconne”
✦ TOP 3
reward 0.000 · emo-sim 0.906 · WER 1.000 · 26.64s
“The energy in here is just incredible. It's funny, isn't it? How you can feel so disconn”
#95 · “Oy, that is so great. S- Right there is right here in my wiener chest, right next to my thic- that is that”
A feminine voice, voice at peak biological vigor. Timbre: the high frequencies are distinctly; standard human baseline; standard. Delivery: casual, conversational, playful. Emotion: interest, astonishment surprise, disgu
● ORIGINAL · 5.94s
the embedded DramaBox clip
✦ TOP 1
reward 0.011 · emo-sim 0.262 · WER 0.957 · 8.64s
“Boy, that is right. There is right here in my wiener chest right next to my thick. That ”
✦ TOP 2
reward 0.000 · emo-sim 0.658 · WER 1.044 · 8.64s
“That is so great Right there is right here in my wiener chest right next to my thick that”
✦ TOP 3
reward 0.000 · emo-sim 0.761 · WER 1.044 · 8.8s
“Oh, that is so great. Right there is right here in my wiener chest, right next to my thi”
#96 · “is the best. That's a good part of Yeah, right there is that's just I w- I can't believe someone”
A masculine voice, voice at peak biological vigor. Timbre: the acoustic signal is completely; highly functional but distinctly neutral-cool; ggressively harsh and distinctly growling. Delivery: casual, dramatic, playful.
● ORIGINAL · 6.91s
the embedded DramaBox clip
✦ TOP 1
reward 0.058 · emo-sim 0.447 · WER 0.870 · 10.32s
“is the best. That's a good part of... Yeah, right there is. That's just... I can't belie”
✦ TOP 2
reward 0.043 · emo-sim 0.330 · WER 0.870 · 12.64s
“is the best. That's a good part of... Yeah, right there is. That's just... I can't believe”
✦ TOP 3
reward 0.038 · emo-sim 0.079 · WER 0.522 · 5.6s
“is the best. That's a good part of... is the best. That's a good part of...”
#97 · “someone next to my feet. The bass is so loud, but”
A feminine voice, clear. Timbre: the high frequencies are distinctly; standard human baseline; standard. Delivery: casual, dramatic, conversational. Emotion: astonishment surprise, impatience and irritability, disgust, i
● ORIGINAL · 4.24s
the embedded DramaBox clip
✦ TOP 1
reward 0.547 · emo-sim 0.547 · WER 0.000 · 3.84s
“someone next to my feet. The bass is so loud, but...”
✦ TOP 2
reward 0.000 · emo-sim 0.438 · WER 1.000 · 6.16s
“Someone next to my feet. The bass is so loud, but... Someone next to my feet. The bass is”
✦ TOP 3
reward 0.000 · emo-sim 0.274 · WER 1.000 · 6.0s
“Someone next to my feet! The bass is so loud! But... Someone next to my feet! The bass is”
#98 · “seriously it's just a lot, so much going on. OK, OK, deep”
A feminine voice, voice at peak biological vigor. Timbre: the high frequencies are distinctly; standard human baseline; standard. Delivery: casual, conversational, playful. Emotion: fatigue exhaustion, relief, impatience
● ORIGINAL · 5.27s
the embedded DramaBox clip
✦ TOP 1
reward 0.194 · emo-sim 0.419 · WER 0.538 · 4.24s
“Seriously, it's just a lot. Seriously, it's just a lot.”
✦ TOP 2
reward 0.131 · emo-sim 0.569 · WER 0.769 · 11.12s
“Seriously, it's just a lot, so much going on! Seriously, it's just a lot, so much going o”
✦ TOP 3
reward 0.000 · emo-sim 0.670 · WER 1.154 · 9.6s
“Seriously, it's just a lot, so much going on. Okay, okay, deep? Seriously, it's just a l”
#99 · “deep breaths. Just gotta keep moving.”
A feminine voice, clear. Timbre: the high frequencies are distinctly; standard human baseline; standard. Delivery: casual, storytelling, monologue. Emotion: interest, hope enthusiasm optimism, contentment, teasing, conce
● ORIGINAL · 2.49s
the embedded DramaBox clip
✦ TOP 1
reward 0.089 · emo-sim 0.533 · WER 0.833 · 2.48s
“Deep breaths. Just cut deep breaths. Just cut...”
✦ TOP 2
reward 0.000 · emo-sim 0.201 · WER 1.000 · 8.0s
“Deep breaths. Just gotta keep moving. Deep breaths. Just gotta keep moving.”
✦ TOP 3
reward 0.000 · emo-sim 0.367 · WER 1.000 · 4.48s
“Deep breaths just gotta keep moving deep breaths Just gotta keep moving”
#100 · “But hey, grab my arm! Oh, thank you!”
A the acoustic profile features, clear. Timbre: the high frequencies are distinctly; distinctly tinny and highly top-heavy; ggressively harsh and distinctly growling. Delivery: cartoonish, dramatic, casual. Emotion: than
● ORIGINAL · 3.78s
the embedded DramaBox clip
✦ TOP 1
reward 0.000 · emo-sim 0.856 · WER 1.000 · 3.92s
“But hey, grab my arm. Oh, thank you. But hey, grab my arm. Oh, thank you”
✦ TOP 2
reward 0.000 · emo-sim 0.807 · WER 1.000 · 5.52s
“But hey, grab my arm! Oh, thank you! But hey, grab my arm! Oh, thank you!”
✦ TOP 3
reward 0.000 · emo-sim 0.889 · WER 1.000 · 4.0s
“But hey, grab my arm! Oh! Thank you! But hey, grab my arm! Oh! Thank you!”
#101 · “Seriously, thank you! I love you. You know that?”
A feminine voice, clear. Timbre: the high frequencies are distinctly; standard human baseline; standard. Delivery: conversational, casual, storytelling. Emotion: thankfulness gratitude, relief, affection, hope enthusiasm
● ORIGINAL · 3.11s
the embedded DramaBox clip
✦ TOP 1
reward 0.000 · emo-sim 0.858 · WER 1.000 · 4.64s
“Seriously, thank you! I love you! You know that? Seriously, thank you! I love you! You kn”
✦ TOP 2
reward 0.000 · emo-sim 0.893 · WER 1.000 · 3.76s
“Seriously, thank you. I love you. You know that? Seriously, thank you. I love you. You kno”
✦ TOP 3
reward 0.000 · emo-sim 0.806 · WER 1.000 · 4.8s
“Seriously, thank you, I love you. You know that? Seriously, thank you, I love you. You kno”
#102 · “Thank you for being here.”
A feminine voice, voice at peak biological vigor. Timbre: the high frequencies are distinctly; standard human baseline; standard. Delivery: casual, conversational, playful. Emotion: interest, hope enthusiasm optimism, re
● ORIGINAL · 18.5s
the embedded DramaBox clip
✦ TOP 1
reward 0.556 · emo-sim 0.556 · WER 0.000 · 2.64s
“Thank you for being here.”
✦ TOP 2
reward 0.513 · emo-sim 0.513 · WER 0.000 · 3.04s
“Thank you for being here.”
✦ TOP 3
reward 0.458 · emo-sim 0.458 · WER 0.000 · 4.16s
“Thank you for being here.”
#103 · “The energy in here is just incredible it's funny, isn't it,”
A feminine voice, the acoustic signature reflects a fully. Timbre: perfect; highly pleasant; standard. Delivery: monologue, whisper-talk, narrator. Emotion: interest, hope enthusiasm optimism, elation, awe, pleasure ecst
● ORIGINAL · 5.78s
the embedded DramaBox clip
✦ TOP 1
reward 0.965 · emo-sim 0.965 · WER 0.000 · 7.2s
“The energy in here is just incredible. It's funny, isn't it?”
✦ TOP 2
reward 0.945 · emo-sim 0.945 · WER 0.000 · 6.32s
“The energy in here is just incredible. It's funny, isn't it?”
✦ TOP 3
reward 0.856 · emo-sim 0.856 · WER 0.000 · 6.4s
“The energy in here is just incredible. It's funny. Isn't it?”
#104 · “how you can feel so disconnected in your own life and then”
A feminine voice, clear. Timbre: perfect; standard human baseline; standard. Delivery: storytelling, conversational, casual. Emotion: contemplation, relief, interest, helplessness, sadness. Genuineness 0.903/6, vocal-bur
● ORIGINAL · 3.84s
the embedded DramaBox clip
✦ TOP 1
reward 0.689 · emo-sim 0.689 · WER 0.000 · 4.56s
“How you can feel so disconnected in your own life and then...”
✦ TOP 2
reward 0.000 · emo-sim 0.542 · WER 1.000 · 3.92s
“How you can feel so disconnected in your own life and then... How you can feel so disconn”
✦ TOP 3
reward 0.000 · emo-sim 0.649 · WER 1.000 · 4.32s
“How you can feel so disconnected in your own life. And then, how you can feel so disconne”
#105 · “this just pure unadulterated feeling. I'm actually really happy right now. Yeah, really happy, worth it”
A feminine voice, the acoustic signature reflects a fully. Timbre: the high frequencies are distinctly; standard human baseline; standard. Delivery: conversational, casual, playful. Emotion: relief, elation, contentment,
● ORIGINAL · 8.68s
the embedded DramaBox clip
✦ TOP 1
reward 0.000 · emo-sim 0.935 · WER 1.000 · 10.8s
“This just pure unadulterated feeling. I'm actually really happy right now. Yeah, really ha”
✦ TOP 2
reward 0.000 · emo-sim 0.955 · WER 1.000 · 11.92s
“This just pure unadulterated feeling. I'm actually really happy right now. Yeah, really h”
✦ TOP 3
reward 0.000 · emo-sim 0.937 · WER 1.000 · 10.96s
“This just pure unadulterated feeling. I'm actually really happy right now. Yeah, really ”
#106 · “God, what have you done? This wasn't supposed to happen! I failed! No no no!”
A the audio delivers a, voice at peak biological vigor. Timbre: treble frequencies are heavily emphasized; distinctly tinny and highly top-heavy; ggressively harsh and distinctly growling. Delivery: ranting/angry, cartoo
● ORIGINAL · 6.29s
the embedded DramaBox clip
✦ TOP 1
reward 0.737 · emo-sim 0.907 · WER 0.188 · 12.32s
“God, what have you done? This wasn't supposed to happen. I failed! I failed!”
✦ TOP 2
reward 0.000 · emo-sim 0.699 · WER 1.000 · 9.04s
“God, what have you done? This wasn't supposed to happen! I failed. No, no, no. God, what”
✦ TOP 3
reward 0.000 · emo-sim 0.921 · WER 1.000 · 11.28s
“God! What have you done? This wasn't supposed to happen! I failed! No, no, no! God, what h”
#107 · “God, what have you done? This wasn't supposed to happen! I failed! No no no!”
A the audio delivers a, voice at peak biological vigor. Timbre: treble frequencies are heavily emphasized; distinctly tinny and highly top-heavy; ggressively harsh and distinctly growling. Delivery: ranting/angry, cartoo
● ORIGINAL · 6.29s
the embedded DramaBox clip
✦ TOP 1
reward 0.057 · emo-sim 0.910 · WER 0.938 · 7.6s
“What have you done? This wasn't supposed to happen! I failed! No, no, no! What have yo”
✦ TOP 2
reward 0.000 · emo-sim 0.956 · WER 1.000 · 5.92s
“God, what have you done? This wasn't supposed to happen! I failed! No, no, no! God, what ”
✦ TOP 3
reward 0.000 · emo-sim 0.946 · WER 1.125 · 6.48s
“God what have you done? This wasn't supposed to happen. I failed. No no no no God what ha”
#108 · “God, what have you done? This wasn't supposed to happen! I failed! No no no!”
A the audio delivers a, voice at peak biological vigor. Timbre: treble frequencies are heavily emphasized; distinctly tinny and highly top-heavy; ggressively harsh and distinctly growling. Delivery: ranting/angry, cartoo
● ORIGINAL · 6.29s
the embedded DramaBox clip
✦ TOP 1
reward 0.175 · emo-sim 0.934 · WER 0.812 · 9.12s
“God, what have you done? This wasn't supposed to happen! I failed! God, what have you d”
✦ TOP 2
reward 0.173 · emo-sim 0.922 · WER 0.812 · 4.48s
“God, what have you done? This wasn't supposed to happen! I failed! God, what have you don”
✦ TOP 3
reward 0.107 · emo-sim 0.858 · WER 0.875 · 8.32s
“Cod what have you done? This wasn't supposed to happen. I failed Cod what have you done t”