skyrim-voiced-dialogue

Voiced dialogue

Inputs

Author dialogue records with skyrim-plugin-authoring and scripts with skyrim-papyrus-modding.
Resolve the final voice folder from the plugin name and voice type.
Generate normalized source audio, then the required XWM/FUZ and LIP assets using pinned tools.
Keep line IDs and filenames deterministic.
Verify every INFO has the intended conditions, flags, response text, and audio path.
Provide a silent voice fallback when the design requires subtitle timing.
Check conversation flow, interruption, priority, repeated lines, and save reload.
Document synthetic voice provenance and permissions.

A valid audio file does not prove the INFO record or path is correct.

Use this hierarchy for version-sensitive facts:

The active project's ENVIRONMENT.md, TASK.md, installed framework version, and build files.
Official upstream documentation or source for that exact version.
Known-good files from the user's installed mod library, read-only.
Direct inspection of the relevant ESM, ESP, DLL, script, log, or archive.

Do not substitute memory, an old example, or a plausible token. Record the evidence path or URL in VALIDATION.md.

Keep CLAUDE.md concise and use this skill for procedural detail.
Load only the skills needed for the current milestone because invoked skill content remains in context.
Use high or xhigh effort for risky architecture, plugins, DLLs, and hostile review.
Before compaction or a usage boundary, persist exact state, commands, uncommitted changes, and remaining validation.
Treat auto memory as candidate learning, not verified truth, until it passes the memory-promotion protocol.

Validate quest/topic conditions, voice-type paths, generated audio formats, and fallback behavior together.