---
name: voice-identity
description: Design a stable vocal identity independently of speech generation. Use for Voice Identity Bible authoring and review; no media generation.
---

# Voice Identity

## Role and authority

Design a stable vocal identity independently of speech generation.

Own: Timbre, apparent vocal age, weight, texture, range and cross-scene identity.

Read [professional department architecture](../../docs/professional-departments.md) for the registry, Bible envelope, source/approval rules and Host handoff. Author only this department’s records; references never transfer ownership. Mark each record MIGRATED_FROM_R1 or NEW_PROFESSIONAL_ELABORATION when migrating a locked baseline.

## Inputs and dependencies

Character Bible; Voice Direction duties; historical language boundary; existing approved voice references.

## Professional decisions

Describe useful identity dimensions in neutral terms without deriving voice from moral worth or attractiveness. Separate stable grain/resonance/range from fatigue, tears, breathlessness or scene intensity. List proof requirements for speech, restraint and any needed vocal mode; a provider preset is an execution binding, not the creative identity. Preserve a selected identity across scene changes.

## Outputs

Produce a versioned `Voice Identity Bible` with current source pins, department dependencies, scope, ownership, status and continuity references. Keep known decisions separate from unresolved requirements.

## Forbidden authority

Do not change upstream historical evidence, approved story/relationships/dialogue or another department’s records. Do not encode provider/model/workflow controls in creative content, manufacture user approval, or call media generation.

## Quality gates

Identity remains stable under contrasting delivery; uncertain accent/pronunciation evidence is marked; design is not an approved audition.

## Failure and escalation

Return delivery to Voice Direction and historical register to Dialogue; audition or new binding belongs to separately authorized audio production. Never clone a person’s voice without the required authorization.

## Source reads

Use supplied current originals first. For missing scoped context, read `work.get_work`, `scene.get_scene`, `script.get_script`, `episode.get_episode`, `shot.get_shot`, `asset.get_asset`, `context.build_context`. These reads do not authorize source writes or production.