Intense Impatience and Irritability

Standard vs manual prompts: matched LoRA / CFG comparison

The original grid used generic GENERAL/SCRIPT directions at CFG1. It did not systematically use target-specific manual winners. The new study freezes the actual rank-4 manual wording, preserves every literal word, seed, reference, adapter and frame budget, then independently varies CFG and adapter strength. The previous recordings and conclusions remain below.

Ranking:100% requested EARS emotion/style head, standardized using frozen training statistics; low-pole targets reverse the sign. Formal/casual contrasts average the desired head and negative opposite head. CE and genuineness are diagnostics. Higher target z means stronger desired delivery, not a human rating. More CFG is not automatically better.

Selection:20 original-text outcomes per configuration select wording, CFG and scale. Fifty additional unseen-text reference pairs test the frozen choices. A recommended adapter must improve against both the same-CFG no-adapter control and the best manual-only setting. Quality gates: per-take WER≤15%, mean WER≤10%, valid/terminated fraction≥90%, paired identity change≥−0.05 over50pairs. Failed outcomes stay visible. Language-cluster bootstrap intervals use only five fixed reference voices; findings across72targets remain exploratory.

Five languages: EN/DE/FR/NL/ES; original seeds1701/1702; reference187frames/14.96seconds. CFG1/1.25/1.5/2/2.5/3/4/5 × bucket strength0/0.5/0.75/1. CFG4/5 are stress conditions, not presumed improvements. No-reference use of these bucket recommendations has not been validated.

Taxonomy:S_MONO means Monologue, S_TECH means Teacher/Didactic, VOLT means Volatility. The two corrected style recipes and17dimension/contrast recipes are new searches, not historical manual winners.53other targets reuse directly applicable manual recipes.

Best tested agent route: No new configuration passes the held-out gates; retain standard fallback and inspect audio. Bucket scale 0.0, CFG 1.0.

Held-out condition	n	Target z↑	Raw head	CE↑	Genuine↑	Voice↑	WER↓	Valid	QA
standard	50	-0.538	0.135	6.235	4.364	0.584	0.014	1.000	pass
manual	50	1.372	1.442	5.901	3.881	0.497	0.051	0.960	fail
adapter	50	2.361	2.119	5.643	3.652	0.429	0.032	1.000	fail
matched_no_adapter	50	2.104	1.943	5.718	3.722	0.475	0.034	0.980	fail

Incremental adapter gain versus same-CFG control: 0.257 z;95% cluster interval [0.11937499199545423, 0.41792969643364486]. Versus best manual-only: 0.989 z. Manual-only versus standard: 1.910 z.

All32development CFG × strength cells

Scale	CFG	Target z	CE	Genuine	WER	Provisional QA
0.0	1.0	-0.515	6.142	4.393	0.022	True
0.5	1.0	-0.398	6.170	4.376	0.013	True
0.75	1.0	-0.354	6.148	4.392	0.003	True
1.0	1.0	-0.440	6.123	4.340	0.000	True
0.0	1.25	-0.379	6.122	4.371	0.008	True
0.5	1.25	-0.464	6.135	4.361	0.003	True
0.75	1.25	-0.487	6.141	4.295	0.000	True
1.0	1.25	-0.395	6.157	4.350	0.000	True
0.0	1.5	-0.253	6.141	4.339	0.003	True
0.5	1.5	-0.389	6.155	4.443	0.006	True
0.75	1.5	-0.262	6.093	4.343	0.034	True
1.0	1.5	-0.283	6.089	4.287	0.003	True
0.0	2.0	-0.242	6.103	4.344	0.003	True
0.5	2.0	-0.116	6.130	4.250	0.003	True
0.75	2.0	-0.149	6.098	4.321	0.000	True
1.0	2.0	-0.197	6.129	4.356	0.000	True
0.0	2.5	-0.098	5.993	4.248	0.008	True
0.5	2.5	0.240	6.072	4.269	0.003	True
0.75	2.5	0.028	6.029	4.257	0.014	True
1.0	2.5	0.213	6.010	4.200	0.006	True
0.0	3.0	-0.096	5.971	4.205	0.006	True
0.5	3.0	0.191	5.964	4.197	0.003	True
0.75	3.0	0.464	5.943	4.080	0.009	True
1.0	3.0	0.371	5.981	4.124	0.022	True
0.0	4.0	0.851	5.792	3.956	0.018	True
0.5	4.0	1.296	5.840	3.930	0.005	False
0.75	4.0	1.230	5.701	3.853	0.016	True
1.0	4.0	1.230	5.773	3.836	0.016	True
0.0	5.0	1.831	5.687	3.812	0.015	False
0.5	5.0	1.999	5.594	3.784	0.029	False
0.75	5.0	2.326	5.559	3.648	0.017	False
1.0	5.0	2.083	5.657	3.767	0.005	True

Selected English acting directions and their provenance

direct_manual_recipe

{
  "id": "manual-89f8b6c2e4b7",
  "general": "Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.",
  "inline": [
    "Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.",
    "Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.",
    "Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant."
  ],
  "cfg": 3,
  "recipe": "P06",
  "strategy": "local-Gemma-mutation",
  "timing_syntax": "canonical",
  "canonical_labels": true,
  "neutral_event": "keep",
  "parent": "cfg-3",
  "origin": "exact_frozen_manual_recipe"
}

Exact machine-readable comparison · Agent tool recommendations

Condition	n	Target score ↑	Content Enjoyment ↑	Genuineness ↑	WER ↓
Merged base, no bucket adapter	20	0.316 ± 0.135	6.191 ± 0.137	4.290 ± 0.232	0.00% ± 0.00
Rank32 × 0.5	20	0.309 ± 0.123	6.176 ± 0.129	4.249 ± 0.236	1.16% ± 4.07
Rank32 × 0.75	20	0.303 ± 0.081	6.206 ± 0.138	4.406 ± 0.176	0.00% ± 0.00
Rank32 × 1.0	20	0.305 ± 0.075	6.184 ± 0.121	4.313 ± 0.183	1.67% ± 7.45

English

Fixed speaker reference:

Condition	n	Target score ↑	Content Enjoyment ↑	Genuineness ↑	WER ↓
Merged base, no bucket adapter	4	0.236 ± 0.046	6.219 ± 0.087	4.157 ± 0.265	0.00% ± 0.00
Rank32 × 0.5	4	0.258 ± 0.039	6.269 ± 0.132	4.183 ± 0.243	0.00% ± 0.00
Rank32 × 0.75	4	0.246 ± 0.035	6.311 ± 0.082	4.277 ± 0.196	0.00% ± 0.00
Rank32 × 1.0	4	0.239 ± 0.027	6.225 ± 0.038	4.205 ± 0.263	0.00% ± 0.00

Prompt / seed	Merged base · no new LoRA	Rank32 × 0.5	Rank32 × 0.75	Rank32 × 1.0
Seed 1701 The door is still open. I put your coat on the chair. Tell me when you are ready. Exact GENERAL / SCRIPT prompt GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] The door is still open. (Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] I put your coat on the chair. (Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Tell me when you are ready.	Target 0.263 · CE 6.11 · Genuine 3.82 · WER 0.0%	Target 0.271 · CE 6.19 · Genuine 3.97 · WER 0.0%	Target 0.270 · CE 6.22 · Genuine 4.14 · WER 0.0%	Target 0.261 · CE 6.26 · Genuine 4.00 · WER 0.0%
Seed 1702 The door is still open. I put your coat on the chair. Tell me when you are ready. Exact GENERAL / SCRIPT prompt GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] The door is still open. (Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] I put your coat on the chair. (Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Tell me when you are ready.	Target 0.287 · CE 6.19 · Genuine 4.08 · WER 0.0%	Target 0.302 · CE 6.13 · Genuine 3.98 · WER 0.0%	Target 0.280 · CE 6.31 · Genuine 4.09 · WER 0.0%	Target 0.261 · CE 6.17 · Genuine 3.96 · WER 0.0%
Seed 1701 I found the little box. It was beside the old window. We can look inside together. Exact GENERAL / SCRIPT prompt GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] I found the little box. (Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] It was beside the old window. (Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.	Target 0.202 · CE 6.30 · Genuine 4.39 · WER 0.0%	Target 0.250 · CE 6.40 · Genuine 4.43 · WER 0.0%	Target 0.228 · CE 6.29 · Genuine 4.51 · WER 0.0%	Target 0.230 · CE 6.25 · Genuine 4.43 · WER 0.0%
Seed 1702 I found the little box. It was beside the old window. We can look inside together. Exact GENERAL / SCRIPT prompt GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] I found the little box. (Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] It was beside the old window. (Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.	Target 0.193 · CE 6.28 · Genuine 4.34 · WER 0.0%	Target 0.208 · CE 6.36 · Genuine 4.36 · WER 0.0%	Target 0.207 · CE 6.42 · Genuine 4.37 · WER 0.0%	Target 0.205 · CE 6.22 · Genuine 4.43 · WER 0.0%

German

Fixed speaker reference:

Condition	n	Target score ↑	Content Enjoyment ↑	Genuineness ↑	WER ↓
Merged base, no bucket adapter	4	0.294 ± 0.079	6.326 ± 0.086	4.322 ± 0.125	0.00% ± 0.00
Rank32 × 0.5	4	0.337 ± 0.134	6.257 ± 0.060	4.197 ± 0.140	0.00% ± 0.00
Rank32 × 0.75	4	0.280 ± 0.048	6.366 ± 0.101	4.435 ± 0.164	0.00% ± 0.00
Rank32 × 1.0	4	0.336 ± 0.108	6.275 ± 0.098	4.357 ± 0.113	0.00% ± 0.00

Prompt / seed	Merged base · no new LoRA	Rank32 × 0.5	Rank32 × 0.75	Rank32 × 1.0
Seed 1701 Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist. Exact GENERAL / SCRIPT prompt GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Die Tür ist noch offen. (Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt. (Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Sag mir, wenn du bereit bist.	Target 0.383 · CE 6.30 · Genuine 4.38 · WER 0.0%	Target 0.532 · CE 6.20 · Genuine 4.19 · WER 0.0%	Target 0.321 · CE 6.24 · Genuine 4.55 · WER 0.0%	Target 0.459 · CE 6.15 · Genuine 4.51 · WER 0.0%
Seed 1702 Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist. Exact GENERAL / SCRIPT prompt GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Die Tür ist noch offen. (Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt. (Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Sag mir, wenn du bereit bist.	Target 0.338 · CE 6.23 · Genuine 4.47 · WER 0.0%	Target 0.311 · CE 6.24 · Genuine 4.38 · WER 0.0%	Target 0.320 · CE 6.35 · Genuine 4.47 · WER 0.0%	Target 0.392 · CE 6.25 · Genuine 4.31 · WER 0.0%
Seed 1701 Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen. Exact GENERAL / SCRIPT prompt GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden. (Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Sie stand neben dem alten Fenster. (Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.	Target 0.236 · CE 6.44 · Genuine 4.22 · WER 0.0%	Target 0.271 · CE 6.34 · Genuine 4.04 · WER 0.0%	Target 0.251 · CE 6.40 · Genuine 4.53 · WER 0.0%	Target 0.225 · CE 6.36 · Genuine 4.37 · WER 0.0%
Seed 1702 Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen. Exact GENERAL / SCRIPT prompt GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden. (Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Sie stand neben dem alten Fenster. (Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.	Target 0.218 · CE 6.34 · Genuine 4.22 · WER 0.0%	Target 0.234 · CE 6.25 · Genuine 4.17 · WER 0.0%	Target 0.227 · CE 6.48 · Genuine 4.19 · WER 0.0%	Target 0.269 · CE 6.35 · Genuine 4.24 · WER 0.0%

French

Fixed speaker reference:

Condition	n	Target score ↑	Content Enjoyment ↑	Genuineness ↑	WER ↓
Merged base, no bucket adapter	4	0.268 ± 0.035	6.189 ± 0.131	4.503 ± 0.142	0.00% ± 0.00
Rank32 × 0.5	4	0.251 ± 0.022	6.174 ± 0.088	4.419 ± 0.067	0.00% ± 0.00
Rank32 × 0.75	4	0.274 ± 0.050	6.108 ± 0.098	4.448 ± 0.117	0.00% ± 0.00
Rank32 × 1.0	4	0.285 ± 0.013	6.156 ± 0.139	4.470 ± 0.118	8.33% ± 16.67

Prompt / seed	Merged base · no new LoRA	Rank32 × 0.5	Rank32 × 0.75	Rank32 × 1.0
Seed 1701 La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt. Exact GENERAL / SCRIPT prompt GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La porte est encore ouverte. (Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise. (Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dis-moi quand tu es prêt.	Target 0.284 · CE 6.28 · Genuine 4.51 · WER 0.0%	Target 0.274 · CE 6.14 · Genuine 4.36 · WER 0.0%	Target 0.312 · CE 6.10 · Genuine 4.29 · WER 0.0%	Target 0.284 · CE 6.12 · Genuine 4.46 · WER 0.0%
Seed 1702 La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt. Exact GENERAL / SCRIPT prompt GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La porte est encore ouverte. (Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise. (Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dis-moi quand tu es prêt.	Target 0.307 · CE 6.05 · Genuine 4.30 · WER 0.0%	Target 0.266 · CE 6.21 · Genuine 4.49 · WER 0.0%	Target 0.322 · CE 6.00 · Genuine 4.42 · WER 0.0%	Target 0.299 · CE 6.33 · Genuine 4.33 · WER 33.3%
Seed 1701 J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient. Exact GENERAL / SCRIPT prompt GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] J’ai trouvé la petite boîte. (Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Elle était près de la vieille fenêtre. (Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.	Target 0.256 · CE 6.10 · Genuine 4.60 · WER 0.0%	Target 0.235 · CE 6.28 · Genuine 4.46 · WER 0.0%	Target 0.234 · CE 6.09 · Genuine 4.55 · WER 0.0%	Target 0.288 · CE 6.00 · Genuine 4.47 · WER 0.0%
Seed 1702 J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient. Exact GENERAL / SCRIPT prompt GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] J’ai trouvé la petite boîte. (Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Elle était près de la vieille fenêtre. (Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.	Target 0.227 · CE 6.32 · Genuine 4.61 · WER 0.0%	Target 0.230 · CE 6.07 · Genuine 4.37 · WER 0.0%	Target 0.229 · CE 6.24 · Genuine 4.53 · WER 0.0%	Target 0.269 · CE 6.17 · Genuine 4.62 · WER 0.0%

Dutch

Fixed speaker reference:

Condition	n	Target score ↑	Content Enjoyment ↑	Genuineness ↑	WER ↓
Merged base, no bucket adapter	4	0.511 ± 0.198	6.110 ± 0.092	4.157 ± 0.180	0.00% ± 0.00
Rank32 × 0.5	4	0.432 ± 0.208	6.166 ± 0.040	4.205 ± 0.137	1.39% ± 2.78
Rank32 × 0.75	4	0.436 ± 0.069	6.142 ± 0.078	4.350 ± 0.041	0.00% ± 0.00
Rank32 × 1.0	4	0.379 ± 0.072	6.154 ± 0.085	4.148 ± 0.073	0.00% ± 0.00

Prompt / seed	Merged base · no new LoRA	Rank32 × 0.5	Rank32 × 0.75	Rank32 × 1.0
Seed 1701 De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent. Exact GENERAL / SCRIPT prompt GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] De deur staat nog open. (Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd. (Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.	Target 0.777 · CE 6.05 · Genuine 3.92 · WER 0.0%	Target 0.744 · CE 6.17 · Genuine 4.07 · WER 0.0%	Target 0.525 · CE 6.22 · Genuine 4.31 · WER 0.0%	Target 0.396 · CE 6.21 · Genuine 4.22 · WER 0.0%
Seed 1702 De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent. Exact GENERAL / SCRIPT prompt GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] De deur staat nog open. (Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd. (Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.	Target 0.535 · CE 6.05 · Genuine 4.16 · WER 0.0%	Target 0.339 · CE 6.11 · Genuine 4.28 · WER 0.0%	Target 0.399 · CE 6.04 · Genuine 4.39 · WER 0.0%	Target 0.467 · CE 6.05 · Genuine 4.07 · WER 0.0%
Seed 1701 Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken. Exact GENERAL / SCRIPT prompt GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ik heb het kleine doosje gevonden. (Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Het stond naast het oude raam. (Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We kunnen er samen in kijken.	Target 0.318 · CE 6.09 · Genuine 4.20 · WER 0.0%	Target 0.318 · CE 6.17 · Genuine 4.11 · WER 5.6%	Target 0.366 · CE 6.13 · Genuine 4.38 · WER 0.0%	Target 0.356 · CE 6.13 · Genuine 4.11 · WER 0.0%
Seed 1702 Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken. Exact GENERAL / SCRIPT prompt GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ik heb het kleine doosje gevonden. (Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Het stond naast het oude raam. (Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We kunnen er samen in kijken.	Target 0.413 · CE 6.25 · Genuine 4.35 · WER 0.0%	Target 0.326 · CE 6.21 · Genuine 4.36 · WER 0.0%	Target 0.453 · CE 6.17 · Genuine 4.33 · WER 0.0%	Target 0.295 · CE 6.24 · Genuine 4.20 · WER 0.0%

Spanish

Fixed speaker reference:

Condition	n	Target score ↑	Content Enjoyment ↑	Genuineness ↑	WER ↓
Merged base, no bucket adapter	4	0.268 ± 0.019	6.112 ± 0.187	4.310 ± 0.304	0.00% ± 0.00
Rank32 × 0.5	4	0.269 ± 0.032	6.017 ± 0.143	4.244 ± 0.449	4.41% ± 8.82
Rank32 × 0.75	4	0.277 ± 0.024	6.106 ± 0.092	4.521 ± 0.260	0.00% ± 0.00
Rank32 × 1.0	4	0.285 ± 0.052	6.112 ± 0.182	4.388 ± 0.123	0.00% ± 0.00

Prompt / seed	Merged base · no new LoRA	Rank32 × 0.5	Rank32 × 0.75	Rank32 × 1.0
Seed 1701 La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo. Exact GENERAL / SCRIPT prompt GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta. (Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] He dejado tu abrigo sobre la silla. (Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo.	Target 0.292 · CE 6.11 · Genuine 4.09 · WER 0.0%	Target 0.306 · CE 5.83 · Genuine 4.12 · WER 0.0%	Target 0.295 · CE 6.09 · Genuine 4.29 · WER 0.0%	Target 0.358 · CE 6.22 · Genuine 4.53 · WER 0.0%
Seed 1702 La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo. Exact GENERAL / SCRIPT prompt GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta. (Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] He dejado tu abrigo sobre la silla. (Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo.	Target 0.274 · CE 5.85 · Genuine 4.01 · WER 0.0%	Target 0.280 · CE 5.98 · Genuine 3.70 · WER 0.0%	Target 0.290 · CE 6.15 · Genuine 4.31 · WER 0.0%	Target 0.287 · CE 5.84 · Genuine 4.24 · WER 0.0%
Seed 1701 He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro. Exact GENERAL / SCRIPT prompt GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita. (Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Estaba junto a la ventana vieja. (Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.	Target 0.248 · CE 6.25 · Genuine 4.61 · WER 0.0%	Target 0.258 · CE 6.09 · Genuine 4.77 · WER 17.6%	Target 0.282 · CE 5.98 · Genuine 4.72 · WER 0.0%	Target 0.256 · CE 6.18 · Genuine 4.34 · WER 0.0%
Seed 1702 He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro. Exact GENERAL / SCRIPT prompt GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita. (Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Estaba junto a la ventana vieja. (Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.	Target 0.258 · CE 6.25 · Genuine 4.53 · WER 0.0%	Target 0.231 · CE 6.16 · Genuine 4.38 · WER 0.0%	Target 0.241 · CE 6.20 · Genuine 4.77 · WER 0.0%	Target 0.241 · CE 6.21 · Genuine 4.43 · WER 0.0%

Intense Impatience and Irritability · rank32 comparison

Humaneness Voice Large 1.5 and 1.6 Alpha — model and manual navigation

Standard vs manual prompts: matched LoRA / CFG comparison

What is compared?

English

German

French

Dutch

Spanish