← all dimensions · markdown (agent skill) · manual home
Head Resonance VoiceNet dimension guide
Resonance Placementcode vn_R_HEADslot 80
This dimension measures resonance originating from the head cavity. Below: the merge-scaling dose-response for the __high and __low LoRA (laion/moss-voicenet-dimension-loras) at 25/50/75/100/125%, the measured target value at each dose, the top-3 ± correlated EmoNet emotions and VoiceNet dimensions, three audio samples per dose, and a grounded prompting tip. Costs are shifts vs. the 24-sample neutral baseline in genuineness, vocal-burst blend and speech quality.
Head Resonance controls resonance originating from the head cavity. The __high LoRA shifts it +0.42 at 125% (worst cost: burst-blend -0.41); the __low LoRA shifts it -0.02 at 25% (worst cost: burst-blend -0.06). The __high direction is the stronger, more reliable knob here.
▲ HIGH — Head Resonance __high
Dose-response
| dose | target | Δtarget | Δgenu | Δblend | Δqual |
|---|
| baseline (0%) | 0.048 | — | — | — | — |
| 25% | 0.040 | -0.01 | -0.03 | -0.13 | -0.02 |
| 50% | 0.206 | +0.16 | -0.06 | -0.19 | +0.05 |
| 75% | 0.304 | +0.26 | -0.05 | -0.26 | +0.01 |
| 100% | 0.436 | +0.39 | -0.12 | -0.39 | +0.08 |
| 125% ★ | 0.470 | +0.42 | -0.13 | -0.41 | +0.03 |
EmoNet emotion correlation
Concentration+0.26
Embarrassment+0.26
Elation+0.26
Longing-0.61
Fear-0.53
Awe-0.51
VoiceNet dimension correlation
Brightness+0.88
Mask Resonance+0.88
Nasal Resonance+0.85
Vocal-burst blend-0.71
Genuineness-0.67
Cognitive Load-0.63
Listen — 3 samples per dose
25%measured target: 0.00 · 0.05 · 0.00
50%measured target: 0.19 · 0.01 · 0.05
75%measured target: 0.00 · 0.07 · 0.40
100%measured target: 0.24 · 0.63 · 0.46
125% ★measured target: 0.33 · 0.45 · 0.44
Merging Head Resonance __high pushes the dimension: at the recommended 125% dose the measured Head Resonance score moves from a 0.05 baseline to 0.47 (a +0.42 shift). The dose-response is clean and monotonic — each step pushes the dimension further. That reach is a steep cost — the biggest hit is to burst-blend (-0.41); across the board genuineness -0.13, burst-blend -0.41, speech quality +0.03. Emotionally it reads as Concentration (r 0.26), Embarrassment (0.26) and Elation (0.26), and it moves away from Longing, Fear and Awe. On other voice dimensions it co-moves most with Brightness (0.88), Mask Resonance (0.88) and Nasal Resonance (0.85), while pulling down Vocal-burst blend, Genuineness and Cognitive Load. Practical call: merge __high at 100–125%; expect Concentration and Brightness to rise and burst-blend to fall. If you don’t want Concentration bleeding in, offset it with a prompt cue toward Longing to keep the head resonance shift without the side-effect.
▼ LOW — Head Resonance __low
Dose-response
| dose | target | Δtarget | Δgenu | Δblend | Δqual |
|---|
| baseline (0%) | 0.048 | — | — | — | — |
| 25% ★ | 0.031 | -0.02 | -0.03 | -0.06 | -0.02 |
| 50% | 0.163 | +0.12 | -0.02 | -0.11 | +0.01 |
| 75% | 0.141 | +0.09 | +0.01 | -0.10 | -0.14 |
| 100% | 0.119 | +0.07 | -0.06 | -0.11 | +0.02 |
| 125% | 0.131 | +0.08 | -0.06 | -0.04 | +0.04 |
EmoNet emotion correlation
Disgust+0.30
Sourness+0.29
Impatience and Irritability+0.28
Fear-0.36
Relief-0.35
Fatigue/Exhaustion-0.30
VoiceNet dimension correlation
Nasal Resonance+0.78
Brightness+0.76
Mask Resonance+0.74
Cognitive Load-0.61
Disfluency-0.49
Genuineness-0.44
Listen — 3 samples per dose
25% ★measured target: 0.05 · 0.06 · 0.01
50%measured target: 0.00 · 0.19 · 0.18
75%measured target: 0.00 · 0.00 · 0.40
100%measured target: 0.18 · 0.08 · 0.18
125%measured target: 0.36 · 0.11 · 0.00
Merging Head Resonance __low dials back the dimension: at the recommended 25% dose the measured Head Resonance score moves from a 0.05 baseline to 0.03 (a -0.02 shift). The dose-response is mostly ordered but noisy between doses. That reach is nearly free — the biggest hit is to burst-blend (-0.06); across the board genuineness -0.03, burst-blend -0.06, speech quality -0.02. Emotionally it reads as Disgust (r 0.30), Sourness (0.29) and Impatience and Irritability (0.28), and it moves away from Fear, Relief and Fatigue/Exhaustion. On other voice dimensions it co-moves most with Nasal Resonance (0.78), Brightness (0.76) and Mask Resonance (0.74), while pulling down Cognitive Load, Disfluency and Genuineness. Practical call: merge __low at a light 25–50%; expect Disgust and Nasal Resonance to rise and burst-blend to fall. If you don’t want Disgust bleeding in, offset it with a prompt cue toward Fear to keep the head resonance shift without the side-effect.