Eve library

ISIS v2 WS08-004: Voice Consistency Profiles

Guide

Revision 1

On this page

Scope#

WS08-004 implements first-class voice consistency profile contracts for audio voice workflows, including speaker embedding controls, pronunciation lexicon controls, and style token controls with provider-capability-aware runtime application.

Research and Existing Implementation Alignment#

Before implementation, existing ISIS patterns were reviewed in:

  • Existing provider fields and API contracts:
    • libs/isis/ai-providers/src/types/tts.types.ts
    • libs/isis/ai-providers/src/providers/tts/elevenlabs-provider.ts
  • Existing voice profile and pronunciation system primitives:
    • libs/isis/audio-generation/src/voice/elevenlabs-client.ts
    • libs/isis/ai-providers/src/providers/conversational-ai/pronunciation-dictionary
  • Existing generation-api normalization/capability-guard patterns:
    • apps/isis/generation-api/src/workflows/executor.ts
    • apps/isis/generation-api/src/schemas/job.schema.ts

These references were used to align new contracts with current ISIS naming and provider behavior (voice IDs, pronunciation dictionary locators, and consistency-related voice controls).

Deliverables#

  1. Typed API and SDK contracts
  • Added voiceConsistency / voice_consistency request contracts across:
    • apps/isis/generation-api/src/types.ts
    • libs/isis/client/src/types.ts
  • Added typed fields for:
    • profile identifiers and voice/speaker IDs
    • speaker embedding ID/URL/vector and reference audio URLs
    • pronunciation lexicon IDs and dictionary locators
    • style tokens and consistency strength
    • provider capability mode and prompt-preservation policy
  1. Validation support in generation API
  • Added JobVoiceConsistencyRequestSchema in apps/isis/generation-api/src/schemas/job.schema.ts.
  • Added strict validation for URL fields, embedding vector bounds, enum values, and numeric ranges.
  • Added schema regression tests for valid and invalid payloads.
  1. Workflow capability exposure
  • Extended voice-performance-synthesis workflow inputs with explicit voice consistency controls:
    • voice_consistency_profile_id, voice_id
    • speaker_embedding_id, speaker_embedding_url, speaker_embedding_vector, speaker_reference_audio_urls
    • pronunciation_lexicon_ids, pronunciation_dictionary_locators
    • style_tokens, voice_consistency_strength, voice_consistency_provider_mode
  1. Runtime normalization, mapping, and diagnostics
  • Added canonical request normalization for voiceConsistency payloads.
  • Added capability-aware input mapping to workflow inputs.
  • Added provider capability guard behavior:
    • providerCapabilityMode: "required" blocks application when workflow does not expose voice consistency inputs.
  • Added execution diagnostics at output.metadata.voiceConsistency with:
    • support/blocking status
    • requested embedding/lexicon/style token counts
    • supported and used workflow input keys
  1. Regression coverage
  • Added executor regression coverage validating voice consistency contract application and diagnostics for voice-performance-synthesis workflow runs.

Verification Commands#

bash
pnpm --filter @isis/workflows exec vitest run src/workflows.spec.ts --reporter=dot
pnpm --filter @isis/generation-api exec vitest run src/schemas/job.schema.spec.ts src/workflows/executor.spec.ts --reporter=dot

Result#

WS08-004 is now implemented as a typed, validated, and runtime-enforced voice consistency profile system, with first-class support for speaker embeddings, pronunciation lexicons, and style token controls in ISIS audio voice workflows.