# Per-engine reference requirements. derive.py reads this to turn a canonical
# source + transcript into an engine-ready reference set under derived/<engine>/.
#
# Fields:
#   sample_rate          native SR the engine wants
#   resample             true = derive.py should resample to sample_rate
#                        (NOTE: resample is a follow-up — see the resample TODO
#                         in derive.py; dots resamples internally so it's false there)
#   needs_transcript     engine requires a per-reference transcript file
#   ref_max_seconds      cap on derived reference length (null = uncapped)
#   ref_sentence_bounded transcript/clip must end on a sentence boundary (. ! ?)
#                        — set for engines that leak reference content otherwise

engines:
  dots:
    description: "dots.tts (rednote-hilab) — continuous-AR 48kHz zero-shot clone"
    sample_rate: 48000
    resample: false          # runtime auto-resamples at load; keep source SR
    needs_transcript: true   # REQUIRED and must be accurate + sentence-bounded
    ref_max_seconds: 10
    ref_sentence_bounded: true
    notes: >
      Transcript accuracy AND sentence-boundary are load-bearing: a mismatched or
      mid-clause transcript makes dots regurgitate reference audio into the output.

  chatterbox:
    description: "chatterbox-fast (Turbo) — streaming 24kHz clone"
    sample_rate: 24000
    resample: true
    needs_transcript: false  # audio-only clone; server globs its refs dir live
    ref_max_seconds: null
    ref_sentence_bounded: false

  zonos:
    description: "Zonos2 — expressive 44.1kHz clone + emotion dials"
    sample_rate: 44100
    resample: true
    needs_transcript: false
    ref_max_seconds: null
    ref_sentence_bounded: false