docs(zonos-gateway): dials-first emotion spec (operator ruling)

Canonical direction: emotion set by twisting raw dials per-utterance, not preset
selection. Presets demoted to optional examples. Spec covers the dial vocabulary
+ ranges, the emotion_cfg_scale 'deaf by 1.5' rule (NO cap — documented ceiling,
explicit over implicit), measured RTF cost, starting-point dial-sets, an LLM
client system-prompt snippet, and clone reference guidance (~15-24s, no
transcript). Follow-ups flagged: align dials.py cfg help/metadata, trim in-code
PRESETS pending usage check, stand up vh/zonos-gateway for version control.
This commit is contained in:
2026-07-17 18:33:26 -07:00
parent ba0ec64ac3
commit 0a9fb85a52
2 changed files with 151 additions and 1 deletions
+140
View File
@@ -0,0 +1,140 @@
# Zonos Emotion Control — Dials-First Spec
**Status:** canonical direction (operator ruling 2026-07-17). **Applies to:**
`zonos-gateway` (`:8890`) + its consumers (asset-engine, gateway-chat, any
future client). **Supersedes:** the preset-centric usage pattern.
## 1. Philosophy — twist the dials, don't pick a mood
Emotion is set **per-utterance by twisting the raw dials**, not by choosing from
a fixed menu of named presets. The dials ARE the engine's canonical interface
(Zyphra/ZONOS2 exposes exactly these; presets were a PFI-only convenience layer,
not upstream). Rationale:
- **Expressiveness.** A scene needs "wry, tired, a little fond" — not `sad`. An
LLM client picks fine-grained affect per line far better than N fixed moods.
- **Explicit over implicit.** A dial-set states the actual emotion in the call;
a preset name hides it behind an opaque label we alone define.
- **No curation burden.** Presets are a layer we'd have to keep tuning; they
already drifted overwrought (`excited`/`intense` cfg 1.61.8 chipmunked with
nobody re-tuning them). Dials have no drift and no maintenance surface.
**Presets are demoted to optional copy-and-tweak examples** (see §5), not the
primary interface and not a maintained product.
## 2. The dials (`POST /v1/audio/speech`)
All emotion dials require `emotion_enabled: true` — it is the master switch;
without it every `emotion_*` field is inert.
| Dial | Range | Default | What it does | Guidance |
|---|---|---|---|---|
| `emotion_enabled` | bool | `false` | Master switch for emotion conditioning. | Set `true` to use any dial below. |
| `emotion_sliders` | `{happy\|sad\|angry\|surprised: w}` | `null` | Per-emotion weights (the 4 named directions). Blend by setting several. | Weights ~`0.40.8`. **`surprised` raises pitch — the chipmunk driver; use sparingly or omit.** |
| `emotion_valence` | `1.0 … +1.0` | `0.0` | Pleasant ↔ unpleasant axis. | Continuous affect for states between the 4 named emotions. |
| `emotion_arousal` | `1.0 … +1.0` | `0.0` | Calm ↔ energized axis. | `+` = excited/anxious, `` = tired/subdued. High arousal + `surprised` = chipmunk. |
| `emotion_strength` | float | `1.0` | Multiplier on the **per-speaker-calibrated** direction. `1.0` = calibrated; `>1` exaggerates. | Keep `~0.71.1`. Above `~1.3` strains the voice. |
| `emotion_cfg_scale` | `≥ 1.0` | `1.0` | Classifier-free guidance on emotion. `1.0` = off. `>1` amplifies. | **See §3 — the "deaf by 1.5" dial.** |
| `accurate_mode` | bool | `true` | `true` = faithful to the reference voice; `false` = looser / more expressive. | Leave `true` for identity-preserving; flip `false` only when you want the voice to bend. |
| `speaking_rate_enabled` | bool | `false` | Master switch for rate conditioning. | Needed for `speaking_rate` / `speaking_rate_bucket` / `speed` to bite. |
| `speaking_rate_bucket` | int `07` | `null` | Exact rate bucket (`0`=slowest … `7`=fastest; wps bands from `/tts/capabilities`). | Fast = excited/anxious; slow = sad/tired. Pair with the emotion, don't overdrive. |
Discovery is live: `GET /v1/dials` self-describes emotions, axes, rate buckets,
and per-dial ranges.
## 3. `emotion_cfg_scale` — the knob goes to 30, but you're deaf by 1.5
**There is deliberately NO enforced cap.** The dial will take large values — set
it to 30 if you want. You will regret it. Emotional realism tops out around
**1.5**; past ~1.4 the voice is overwrought and distorted, and by 1.5 you're
"deaf" — pushing harder only adds artifact, not feeling.
- **Usable range: `1.0``1.5`.** Recommended ceiling **`1.4`**. **Never above 1.5.**
- `1.0` = off: the additive emotion directions alone (already calibrated). Plenty
expressive for most lines.
- `~1.251.4` = the sweet spot when you want a line to land harder.
- `> 1.5` = do not. It's the amp that goes to 11 — the number is bigger, the
sound is worse.
This is documented, not clamped, on purpose (explicit over implicit): the client
owns the choice; the spec owns the warning.
## 4. Cost / real-time — a second reason to stay ≤ 1.5
Measured on the 3090 (irv-ml1):
| `emotion_cfg_scale` | RTF | Note |
|---|---|---|
| `1.0` (off) | ~0.52 | **free** — same as neutral; additive vectors, no extra forward pass |
| `1.5` | ~0.625 | ~+20% wall (CFG doubles the *decode* pass), still comfortably real-time |
| `> 1.5` | worse | more compute AND worse sound — strictly dominated |
So cfg above 1.5 costs more *and* sounds worse. Stay ≤ 1.4.
## 5. Starting-point dial-sets (examples — copy and tweak, not presets)
Tuned by ear on BritishFemale. Treat these as departure points, not a menu.
```jsonc
// warm — friendly, unhurried
{ "emotion_enabled": true, "emotion_sliders": {"happy": 0.4},
"emotion_valence": 0.4, "emotion_strength": 0.8, "emotion_cfg_scale": 1.3 }
// excited — bright, brisk (NO 'surprised' — that chipmunks it)
{ "emotion_enabled": true, "emotion_sliders": {"happy": 0.55},
"emotion_valence": 0.5, "emotion_arousal": 0.35, "emotion_strength": 0.75,
"emotion_cfg_scale": 1.25, "speaking_rate_enabled": true, "speaking_rate_bucket": 4 }
// sad — slow, quiet
{ "emotion_enabled": true, "emotion_sliders": {"sad": 0.8},
"emotion_valence": -0.6, "emotion_arousal": -0.5, "emotion_strength": 1.0,
"emotion_cfg_scale": 1.4, "speaking_rate_enabled": true, "speaking_rate_bucket": 1 }
// intense — emphatic, tense (angry only; no 'surprised')
{ "emotion_enabled": true, "emotion_sliders": {"angry": 0.55},
"emotion_valence": -0.25, "emotion_arousal": 0.45, "emotion_strength": 0.85,
"emotion_cfg_scale": 1.3 }
// whisper — hushed, breathy
{ "emotion_enabled": true, "emotion_sliders": {"sad": 0.2},
"emotion_arousal": -0.7, "emotion_strength": 0.9, "emotion_cfg_scale": 1.4,
"speaking_rate_enabled": true, "speaking_rate_bucket": 2 }
```
## 6. LLM client system-prompt snippet (the real deliverable)
Paste into an LLM client that drives TTS, so it emits a dial-set per utterance:
> You control speech emotion by emitting a JSON dial-set alongside each line.
> Set `emotion_enabled: true`, then shape the delivery:
> - `emotion_sliders`: weights (00.8) over `happy` / `sad` / `angry` /
> `surprised`. Blend them. **Avoid `surprised` unless you truly want a gasp —
> it pitches the voice up unnaturally.**
> - `emotion_valence` (1..+1): unpleasant → pleasant. `emotion_arousal`
> (1..+1): calm → energized. Use these for nuance between the four emotions.
> - `emotion_strength` (~0.71.1): how hard to push. `emotion_cfg_scale`
> (**1.01.4, never above 1.5**): amplification — 1.0 is already expressive;
> 1.251.4 lands a line harder; above 1.5 is distorted garbage, do not.
> - `speaking_rate_enabled: true` + `speaking_rate_bucket` (0 slow … 7 fast) for
> pacing: fast when excited/anxious, slow when sad/weary.
> Match the dial-set to the line's actual feeling — subtle by default, bold only
> when the moment earns it.
## 7. Voice cloning (reference audio)
Cloning is text-independent (Qwen3 speaker embedding) — **no transcript needed.**
Give it **~1524s of clean, single-speaker audio** (Zyphra's own default voices
run 8.723.9s). Shorter clips (≤5s) under-condition the embedding and audibly
degrade, worse under emotion steering. Register a reusable voice via
`POST /tts/speakers` (caches the embedding; reference by `speaker_embedding_id`).
## 8. Follow-ups (not done here)
- **Gateway code:** align `dials.py` `emotion_cfg_scale` help/`max` metadata with
§3 (carry the "deaf by 1.5" warning; no clamp added — no cap by ruling). Trim
the in-code `PRESETS` to a couple of examples (or drop) once current `preset:`
usage in asset-engine / gateway-chat is confirmed.
- **Version control:** the gateway source lives only on irv-ml1 (`~/zonos-gateway`,
not in gitea) — stand up `vh/zonos-gateway` so this spec + the code are tracked
together. This spec currently lives in the eshpfi mirror as the version-controlled
home until then.
+11 -1
View File
@@ -41,7 +41,17 @@ one-line alias repoint, invisible to every consumer. This repo stays
Zonos-specific (voice registry, correct native defaults, presets); the swap
point is the alias, not the code.
## Emotion control — the simple caller path (presets)
## Emotion control
> **Direction (operator ruling 2026-07-17): dials-first.** Emotion is set by
> twisting the raw dials per-utterance; presets are demoted to optional
> copy-and-tweak examples, not the primary interface. See
> [`EMOTION-DIALS-SPEC.md`](EMOTION-DIALS-SPEC.md) for the dial vocabulary, the
> `emotion_cfg_scale` "deaf by 1.5" rule (no cap, documented ceiling), the
> LLM-client system-prompt snippet, and reference-voice guidance. The
> preset-centric description below is retained as background.
### (background) the preset path
Emotion is exposed as **named presets** that bundle the engine's steering knobs
(`emotion_sliders` / `emotion_valence` / `emotion_arousal` / `emotion_strength`