witnessbox/script.py

"""Scripted, pre-generated beats.

These lines are fixed, so their audio is generated *once* (in parallel via
Modal `.map()` at deploy/warm time — see modal_app.py) and cached on a Volume.
That keeps the dramatic moments — especially the witness's **voice crack** —
off the per-turn latency path and lets us pick the best take of the climax.

The break line has several takes precisely because VoxCPM2's expressive style
varies run-to-run; we generate many and keep the one that cracks best (PRD §10).
"""
from __future__ import annotations

from witnessbox.witness import WITNESS_NAME

# Spoken by the court / framing narration (composed neutral voice or on-screen text).
INTRO_NARRATION = (
    "The witness is sworn. Marcus Reid, Chief Financial Officer of Halcyon "
    "Dynamics. Twelve million dollars left the company for a vendor named "
    "Meridian Atlantic. You have the floor, counselor. Mind how you say it — "
    "he listens for doubt."
)

# The witness's opening line, composed style.
WITNESS_OPENING = (
    "Counselor. I've answered these questions for the auditors, the board, and "
    "two regulators. Ask what you like — I have nothing to hide."
)

# The climax. Generated in many takes; the best (most broken) take is cached and
# played when the third contradiction lands. Style forced to the 'breaking' tag.
BREAK_LINE = (
    "No— that's… that isn't… I signed it. I knew them. I knew the dates. "
    "I signed it."
)
BREAK_LINE_TAKES = 32  # generate this many; keep the best (PRD §10)

# Played after the break, composed court voice, as the win sting.
WIN_EPILOGUE = (
    "The witness is excused. The record will reflect the contradictions: the "
    "timeline, the authorization, the relationship. Well examined, counselor."
)

# Played if the player runs out of credibility with the bench (lose).
LOSE_LINE = (
    "The bench has heard enough speculation, counselor. The witness is excused — "
    "and so are you. Mr. Reid keeps his composure, and his story."
)


def scripted_beats() -> dict[str, dict]:
    """All fixed lines + the voice style each should be rendered in.

    Returned as a plain dict so modal_app.py can fan it out over `.map()`.
    """
    return {
        "intro": {"text": INTRO_NARRATION, "style": "calm, formal, courtroom narrator", "takes": 1},
        "opening": {"text": WITNESS_OPENING, "style": "calm, composed, faintly condescending", "takes": 1},
        "break": {"text": BREAK_LINE, "style": "voice unsteady and cracking, composure gone", "takes": BREAK_LINE_TAKES},
        "win": {"text": WIN_EPILOGUE, "style": "calm, formal, courtroom narrator", "takes": 1},
        "lose": {"text": LOSE_LINE, "style": "calm, formal, courtroom narrator", "takes": 1},
    }


__all__ = [
    "INTRO_NARRATION",
    "WITNESS_OPENING",
    "BREAK_LINE",
    "BREAK_LINE_TAKES",
    "WIN_EPILOGUE",
    "LOSE_LINE",
    "scripted_beats",
    "WITNESS_NAME",
]