higgsfield-audio

# Higgsfield Audio Prompting Guide

## QUICK FACTS
*Routing aids — read the linked sections for the full rules.*
- Native-joint audio models: Kling 3.0, Seedance 2.0 / 1.5 Pro, Veo 3/3.1, Grok — all others add audio in post [→](#which-models-support-audio)
- Four layers to consider per prompt: Dialogue / SFX / Ambient / BGM [→](#the-four-audio-layers)
- Lip-sync is the most failure-prone feature: 3–8s clips, MCU framing, one speaking face, locked camera, no head-motion tokens; per-language sync-word budgets are FIELD-reported [→](#lip-sync-rules)
- **Seedance 2.0 `@Audio1` is a conditioning INPUT** — beat sync, the `[AUDIO: Xs]` script block, and the first-15s extraction trap [→](#audio-as-a-conditioning-input-seedance-20-audio1)
- Scope an audio reference like an image one: name the property that rides, the property that must NOT, and where the excluded one comes from instead [→](#scope-an-audio-reference-say-which-property-rides)
- Multi-clip assembly: one master track · cuts land on musical punctuation, never inside a sung vowel (ECU mouth-match is the one exception) · unified grain + LUT masks batch color drift [→](#cutting-to-music-assembling-separately-generated-clips-on-one-track)
- Cinema Studio 3.0 native joint audio (SCELA): describe audio as a separate section; specific foley beats generic moods [→](#cinema-studio-30-audio-businessteam-plan)
- **Seed Audio 1.0** (`seed_audio`, standalone) = whole-scene audio in ONE pass — multi-speaker dialogue + music + SFX + ambience mixed [→](#scene-audio-generation-seed-audio-10)
- Standalone Audio catalog (2026-08-01 snapshot): `seed_audio`, `qwen_audio_tts` (NEW — Qwen 3.0 TTS Flash, expressive instructions + cloned voices), `text2speech_v2` (5 engines incl. cozy_voice), plus 3 game-pipeline-only tools — distinct from in-video joint audio [→](#standalone-audio-tab-tool-catalog-2026-08-01-snapshot)

## Which Models Support Audio?

| Model | Audio type | Dialogue | SFX | Ambient | BGM | Lip-sync |
|-------|-----------|----------|-----|---------|-----|----------|
| Kling 3.0 / Omni | Native joint | ✅ | ✅ | ✅ | ✅ | ✅ Multi-language |
| Seedance 2.0 | Native joint | ✅ | ✅ | ✅ | ✅ | ✅ Multi-language |
| Seedance 1.5 Pro | Native joint | ✅ | ✅ | ✅ | ✅ | ✅ Best lip-sync |
| Veo 3 / 3.1 | Native joint | ✅ | ✅ | ✅ | ✅ | ✅ English best |
| Grok Imagine Video | Native joint | ✅ | ✅ | ✅ | ✅ | ✅ |
| All other models | ❌ | — | — | — | — | — |

**"Native joint"** means audio and video are generated simultaneously in one pass —
not layered on after. This produces natural synchronization without post-production.

Models without native audio: add audio in post with Lipsync Studio or external tools.

---

## The Four Audio Layers

Every audio-capable prompt should consider four layers. You don't need all four
in every prompt, but knowing which to include gives the model clear direction.

### 1. Dialogue — What characters say

Put dialogue in quotes. Be explicit about who speaks, their tone, and language.

```
She says: "We need to leave. Now."
He whispers: "Not yet."
```

**Best practices:**
- Keep dialogue short — 1-2 sentences per character per shot
- Specify emotional tone: "says urgently", "whispers", "shouts across the room"
- For non-English: specify language and dialect → `She speaks in Cantonese: "走啦"`
- For Seedance 1.5 Pro: supports English, Chinese (incl. Sichuanese, Cantonese,
  Taiwanese Mandarin, Shanghainese), Japanese, Korean, Spanish, Indonesian

### 2. SFX — Specific sound events tied to action

Describe SFX at the point they happen. Tie them to visible actions.

```
The glass shatters on the floor — sharp crack, then settling tinkle.
Footsteps on wet concrete — splashing, rhythmic.
A door slams shut — heavy metal, echoing.
```

**Best practices:**
- One SFX description per action beat
- Use onomatopoeia sparingly — descriptive phrases work better than "BANG" or "CRASH"
- Tie timing to action: "as she sets the cup down" not "cup sound at 4 seconds"

### 3. Ambient — Background soundscape

Set the acoustic environment. This is the continuous sound bed.

```
Ambient: quiet café murmur, espresso machine, rain against windows.
Ambient: forest at night — crickets, distant owl, gentle wind through leaves.
Ambient: busy intersection — traffic, horns, construction in the distance.
```

**Best practices:**
- 2-3 ambient elements maximum — more gets muddy
- Describe the *space* acoustics: "reverberant church hall", "tight car interior"
- Contrast silence with sound for impact: "Dead silence. Then — a single footstep."

### 4. BGM — Background music mood

Don't name songs or artists (content filter). Describe the musical texture.

```
BGM: slow piano, minor key, melancholic.
BGM: tense orchestral build — low strings, rising.
BGM: lo-fi hip-hop beat, warm vinyl crackle, relaxed.
```

**Best practices:**
- Describe instrumentation, tempo, mood — not genre labels alone
- "Tense strings, building" works better than "suspenseful music"
- Specify when music enters/exits: "Piano enters at the midpoint, builds to the end"
- For beat-sync content: "Cuts match the downbeat" or "Movement peaks on the drop"

### Suppressing music — `NO BGM` is a spec, `no music` is a preference

`[DEMO — Joey cinema-director-v3, 2026-08-16]` `[UNPROVEN HERE]` When a piece must
carry no score, the phrase matters. **`no music` reads as a weak stylistic preference**
and loses to the model's strong prior that generated video wants a bed under it.
**`NO BGM` reads as a production term** — a hard spec — and is the form to write.
Expand it once on first use so the abbreviation is unambiguous, then let it carry.

**Lead positive, then negate.** Name what the audio *is* before naming what it is not —
diegetic sources tied to surfaces and materials, plus room tone. A suppression clause
with nothing positive in it leaves the model to decide what "silence" sounds like, and
it decides in favour of a pad.

```
Audio: diegetic sound only — footsteps on wet stone, fabric shift, breath, room to