Eve library

ISIS v2 Voice Line Pack Baseline Workflow Graph

Guide

Revision 1

On this page

Generated: 2026-03-03T11:20:46.630Z Checklist: MXA-0542 (ISIS2-00740) Asset Family: voice-line-pack Phase: Phase 4 | Milestone: M3 Launch (2026-07-27 to 2026-10-30)

Objective#

Provide a deterministic baseline workflow graph for voice-line-pack generation with locked model/synthesis defaults, reproducible seed policy, and delivery-ready mastered dialogue output topology.

Deterministic Defaults#

Setting Value
modelName xtts_v2_voiceset_a.safetensors
seed 2026073102
durationSeconds 8
speakingRate 1
pitchShiftSemitones 0
conditioningStrength 0.62
voiceStability 0.72
sampleRateHz 48000
targetLufs -18
outputFormat wav
outputChannels 1
outputBitDepth 24

Input Contract#

Input Type Required Default
cue_id string yes VOICE_LINE_M3_BASELINE_01
script_text string yes Commander, reroute auxiliary power to deck three and hold for extraction.
speaker_id enum yes narrator_f
language_locale enum yes en-US
emotion enum yes confident
speaking_rate float yes 1
pitch_shift_semitones float yes 0
duration_seconds integer yes 8
conditioning_strength float yes 0.62
voice_stability float yes 0.72
sample_rate_hz integer yes 48000
target_lufs float yes -18
output_format enum yes wav
seed integer yes 2026073102

Graph Nodes#

Node ID Class Role Output Count
n1 VoiceLinePromptComposer prompt-construction 1
n2 VoiceLineModelLoader model-load 1
n3 VoiceLineSynthesisNode audio-generation 1
n4 VoiceLineCleanupDenoise audio-post 1
n5 AudioLoudnessNormalize audio-post 1
n6 SaveAudio artifact-output 0

Graph Edges#

Edge ID From To
e1 n1:0 n3.prompt
e2 n2:0 n3.model
e3 n3:0 n4.audio
e4 n4:0 n5.audio
e5 n5:0 n6.audio

Topological Node Order#

n1 -> n2 -> n3 -> n4 -> n5 -> n6

Research Alignment#

Workflow Path Node Classes
SFX Sound Designer libs/isis/workflows/src/workflows/audio/sfx-sound-designer.json AudioLoudnessNormalize, SaveAudio, StableAudioNode, StableAudioOpenModelLoader, StableAudioPromptComposer
Music Cue Composer libs/isis/workflows/src/workflows/audio/music-cue-composer.json ACEModelLoader, ACEStepAudioGenerator, ACEStepPromptBuilder, AudioLimiter, SaveAudio
Voice Performance Synthesis libs/isis/workflows/src/workflows/audio/voice-performance-synthesis.json AudioDeesser, KokoroModelLoader, KokoroPromptBuilder, KokoroTextToSpeech, SaveAudio

Acceptance Criteria#

  • Graph is acyclic and topologically sortable.
  • All deterministic defaults are explicitly set (seed, model, duration, loudness target, and export format).
  • Node class inventory covers baseline voice-line synthesis path from script conditioning to persisted mastered dialogue artifact.
  • Output contract aligns to MXA-0541 required output classes.

Traceability#

  • Checklist item: MXA-0542
  • Ticket key: ISIS2-00740
  • Source references:
    • docs/domains/isis/remediation-v2/ISIS_REMEDIATION_V2_TICKETS.json
    • docs/domains/isis/remediation-v2/ISIS_V2_VOICE_LINE_PACK_REQUIREMENTS_BRIEF.json
    • libs/isis/workflows/src/workflows/audio/sfx-sound-designer.json
    • libs/isis/workflows/src/workflows/audio/music-cue-composer.json
    • libs/isis/workflows/src/workflows/audio/voice-performance-synthesis.json
    • docs/domains/isis/remediation-v2/ISIS_V2_CONTROL_TAXONOMY.json
    • docs/domains/isis/remediation-v2/ISIS_V2_OUTPUT_PACKAGE_TAXONOMY.json
    • ISIS_TODOS_2.md