# Canonical voice corpus registry. One row per voice; the canonical clip + its
# full transcript are the source of truth, engine-agnostic. derive.py reads this
# together with engines.yaml to produce per-engine reference sets.

voices:
  donut:
    canonical: canonical/donut.wav
    transcript: transcripts/donut.txt
    source_sr: 44100
    duration_s: 16.3
    character: "sassy fairy-charm kid"
    provenance: "cloned from the 65-frost Booth bundle (2026-08)"

  glados:
    canonical: canonical/glados.wav
    transcript: transcripts/glados.txt
    source_sr: 16000
    duration_s: 25.0
    character: "GLaDOS — flat, deliberate, menacing-cheerful"
    provenance: "Portal GLaDOS lines"
    warning: "LOW-SR source (16kHz) — upgrade the canonical clip if a cleaner GLaDOS source surfaces"

  emmie:
    canonical: canonical/emmie.wav
    transcript: transcripts/emmie.txt
    source_sr: 24000
    duration_s: 19.3
    provenance: "Zonos clone added 2026-07-17; origin unrecorded"

  miranda:
    canonical: canonical/miranda.wav
    transcript: transcripts/miranda.txt
    source_sr: 24000
    duration_s: 16.3
    provenance: "Zonos clone added 2026-07-17; origin unrecorded"