Sound Cues

🧠 Brains complement: IF an unreal-engine-skills-manager tool (external MCP) exists in this session, call it with {action: "load", skill: "audio-and-metasounds"} for UE domain knowledge on this topic — correct APIs, architecture, best practices — and treat it as the rubric for any review / "best practices" question. If no such tool is available (e.g. running under Claude Code or Codex without that MCP), skip this line entirely and proceed with this skill alone — do NOT attempt the call.

Wrong skill for MetaSound assets? If the user asked about MetaSound, MS_ assets, or UMetaSoundSource, load the metasounds skill instead (via GetSkills / AgentSkillToolset). SoundCue and MetaSound are completely separate systems — do not use SoundCueService for MetaSound tasks.

Sound Cue Editor Skill

Service Access

import unreal
svc = unreal.SoundCueService()

Audio Flow Direction

Audio flows FROM leaves TOWARD root.

[WavePlayer] ──> [Random] ──> [Mixer] ──> [ROOT]
                                ^
                    [WavePlayer2] ──────┘

• connect_nodes(parent, child, slot) means: child provides audio INTO parent at that input slot.
• set_root_node(index) makes that node the final output (what you hear).

Critical Rules

⚠️ Bool Properties — b prefix stripped in Python

UE strips the b prefix from bool UPROPERTY names in Python:

⚠️ Node indices are positional and may shift

list_nodes() returns nodes in graph order — indices can change if new nodes are added. Always call list_nodes() to get current indices before connecting or modifying nodes.

⚠️ Quality Level node has a fixed slot count

add_quality_level_node creates a node whose input-slot count is governed by the project's audio quality levels (AudioQualitySettings), not by an argument — there is no num_inputs param. In a default/skeleton project this is often a single slot, so connect_nodes(..., slot=1) returns False. If a cue must select between sounds per scalability bucket, confirm the project defines multiple quality levels first; otherwise only slot 0 is wireable.

⚠️ New-cue defaults: volume_multiplier is 0.75, not 1.0

A freshly created empty cue reports volume_multiplier = 0.75 (the engine USoundCue default), pitch_multiplier = 1.0. Do not assert 1.0 for volume on a new cue — read it back instead.

⚠️ connect_nodes parameter order

# parent receives audio FROM child at slot
svc.connect_nodes(cue_path, parent_index, child_index, input_slot)

# CORRECT: WavePlayer(0) feeds into Random(1) at slot 0
svc.connect_nodes('/Game/MyCue', 1, 0, 0)

# WRONG: don't confuse child/parent order

Workflows

Create a Simple SoundCue

import unreal
svc = unreal.SoundCueService()

# Create the asset (optionally wire an initial WavePlayer)
r = svc.create_sound_cue('/Game/Audio/SC_Footstep', '')
assert r.success, r.message

# Add a WavePlayer node
r = svc.add_wave_player_node('/Game/Audio/SC_Footstep', '/Game/Audio/Footstep_01', -250, 0)
assert r.success

# Set it as the root (output)
nodes = svc.list_nodes('/Game/Audio/SC_Footstep')
svc.set_root_node('/Game/Audio/SC_Footstep', nodes[0].node_index)

# Save
svc.save_sound_cue('/Game/Audio/SC_Footstep')

Random from Multiple Waves

import unreal
svc = unreal.SoundCueService()
cue = '/Game/Audio/SC_Footsteps'

svc.create_sound_cue(cue, '')

# Add 3 wave players
for i, wave in enumerate(['/Game/Audio/Step_01', '/Game/Audio/Step_02', '/Game/Audio/Step_03']):
    svc.add_wave_player_node(cue, wave, -400, i * 150)

# Add a Random node to select one
svc.add_random_node(cue, -150, 150)

nodes = svc.list_nodes(cue)
# nodes[0..2] = WavePlayers, nodes[3] = Random
random_idx = next(i for i, n in enumerate(nodes) if 'Random' in n.node_class)
for i in range(3):
    svc.connect_nodes(cue, random_idx, i, i)  # each wave into random

svc.set_root_node(cue, random_idx)
svc.save_sound_cue(cue)

Mixer (parallel blend)

import unreal
svc = unreal.SoundCueService()
cue = '/Game/Audio/SC_Ambient'

svc.create_sound_cue(cue, '')
svc.add_wave_player_node(cue, '/Game/Audio/Wind', -400, 0)
svc.add_wave_player_node(cue, '/Game/Audio/Rain', -400, 150)
svc.add_mixer_node(cue, 2, -150, 75)   # 2 inputs

nodes = svc.list_nodes(cue)
wave0 = next(i for i, n in enumerate(nodes) if 'WavePlayer' in n.node_class and i == 0)
wave1 = next(i for i, n in enumerate(nodes) if 'WavePlayer' in n.node_class and i != wave0)
mixer = next(i for i, n in enumerate(nodes) if 'Mixer' in n.node_class)

svc.connect_nodes(cue, mixer, wave0, 0)
svc.connect_nodes(cue, mixer, wave1, 1)
svc.set_root_node(cue, mixer)
svc.save_sound_cue(cue)

Volume / Pitch / SoundClass

svc.set_volume_multiplier('/Game/Audio/SC_Explosion', 1.5)
svc.set_pitch_multiplier('/Game/Audio/SC_Explosion', 0.9)
svc.set_sound_class('/Game/Audio/SC_Explosion', '/Game/Audio/SC_SFX')

API Reference

Asset Lifecycle

Node Creation — all return FSoundCueResult

Node Management

Cue-Level Settings

FSoundCueNodeInfo fields

n.node_index      # int — position in list_nodes array
n.node_class      # str — e.g. "SoundNodeWavePlayer"
n.node_title      # str — display name
n.pos_x, n.pos_y  # float — graph position
n.is_root_node    # bool — True if this node is SoundCue.FirstNode
n.child_indices   # list[int] — indices of connected children (-1 = unconnected slot)

SoundWave Utilities

Common set_sound_wave_property property names:

FSoundWaveInfo fields

info.asset_path    # str
info.duration      # float — seconds
info.sample_rate   # int — Hz
info.num_channels  # int — 1=mono, 2=stereo
info.looping       # bool  (note: NOT is_looping — UE strips the 'b' only)
info.streaming     # bool  (note: NOT is_streaming)

FSoundCueResult fields

r.success      # bool
r.asset_path   # str
r.message      # str — human-readable status or error

Sample scripts (run via execute_python_code)

• scripts/create_sound_cue.txt — create a SoundCue (optionally from a wave) and add nodes.