"""VoxCPM2 TTS — uses the exact API from openbmb/VoxCPM2 model card.
Voice design is achieved by prefixing text with '(voice description) actual text'.
"""
import os, uuid, numpy as np, soundfile as sf
from pathlib import Path
from ..config import AUDIO_CACHE

_ENG = None


def _voice_clause(vd: dict) -> str:
    pace = vd.get("pace", "moderate")
    tone = vd.get("tone", "calm_grounded").replace("_", " ")
    vid  = vd.get("voice_id", "")
    # heuristic: feminine/masculine hint based on voice_id name
    gender = "female" if "guardian" in vid or "weaver" in vid or "presenter" in vid else \
             "male"   if "builder"  in vid or "fetcher" in vid else "neutral"
    return f"({gender} voice, {tone} tone, {pace} pace)"


def _lazy():
    global _ENG
    if _ENG is not None:
        return _ENG
    try:
        from voxcpm import VoxCPM
        _ENG = VoxCPM.from_pretrained("openbmb/VoxCPM2", load_denoiser=False)
        print("[voxcpm] loaded")
    except Exception as e:
        print(f"[voxcpm] load failed ({e}) — using silent fallback")
        _ENG = "SILENT"
    return _ENG


def synthesize(text: str, voice_design: dict) -> str:
    eng = _lazy()
    out = AUDIO_CACHE / f"{uuid.uuid4().hex}.wav"
    if not text.strip():
        sf.write(out, np.zeros(int(48000 * 0.3), dtype=np.float32), 48000)
        return str(out)
    if eng == "SILENT" or eng is None:
        sf.write(out, np.zeros(int(48000 * 0.6), dtype=np.float32), 48000)
        return str(out)
    prefix = _voice_clause(voice_design or {})
    full_text = f"{prefix}{text}"
    try:
        wav = eng.generate(text=full_text, cfg_value=2.0, inference_timesteps=10)
        sr  = eng.tts_model.sample_rate
        sf.write(out, wav, sr)
    except Exception as e:
        print(f"[voxcpm] generation failed: {e}")
        sf.write(out, np.zeros(int(48000 * 0.6), dtype=np.float32), 48000)
    return str(out)