core/tts.py

# core/tts.py
"""Story text → grandmother-voice audio (EN/BN).

EN → VoxCPM2 Voice Design persona (Build Order step 5 — still stubbed).
BN → get_config().tts_bn_backend ('indic_parler' or 'indic_tts'), synthesised on
     Modal via Indic Parler-TTS. The grandmother persona is controlled by the
     caption below — tune it for warmth and storytelling pace (CLAUDE.md §9).
Returns (None, label) if TTS unavailable or failed. Never raises.
"""

import tempfile
from pathlib import Path

from core.model_config import UI_MOCK, get_config
from core.modal_infra import synthesize_bengali_remote, synthesize_english_remote

# A pre-generated sample clip for RUPKOTHA_MOCK=1, so the audio player has something
# to show during local UI dev (no Modal/GPU). None if the sample isn't present.
_MOCK_WAV = next(
    (str(p) for p in [
        Path("finetune/data/sample/demo_story_ai4bharat.wav"),
        Path("finetune/data/sample/demo_story_output_sampled.wav"),
    ] if p.exists()),
    None,
)

# Grandmother voice caption — controls the Indic Parler-TTS speaker persona.
# Tune for warmth and pace; run 5–10 samples and keep the best (CLAUDE.md §9).
GRANDMOTHER_CAPTION_BN = (
    "Aditi speaks in the warm, tender voice of a loving elderly Bengali "
    "grandmother telling a bedtime story to her beloved grandchild. Her pace is "
    "very slow, gentle, and unhurried, pausing softly at every sentence. Her "
    "delivery is affectionate and expressive, rising and falling with the natural "
    "soothing melody of Bengali storytelling, full of warmth and calm. The "
    "recording is very clear, close, and intimate, with no background noise."
)

# Grandmother Voice Design persona for VoxCPM2 (English). This is prefixed to the
# story text in parentheses by core/modal_infra.py — keep it short and concrete.
# Tune for warmth and a slow, storytelling pace (CLAUDE.md §11, build step 5).
GRANDMOTHER_VOICE_EN = (
    "a warm, loving elderly grandmother reading a bedtime story, "
    "slow and gentle pace, soft and soothing tone"
)


def _write_wav(audio_bytes: bytes) -> str:
    """Persist WAV bytes to a temp file and return its path."""
    tmp = tempfile.NamedTemporaryFile(suffix=".wav", delete=False)
    try:
        tmp.write(audio_bytes)
    finally:
        tmp.close()
    return tmp.name


def speak(
    text: str,
    language: str,            # 'en' or 'bn'
    voice: str = "grandmother",
) -> tuple[str | None, str]:
    """Returns (wav_path_or_None, tts_model_label). Never raises."""
    cfg = get_config()

    if UI_MOCK:  # local UI dev — sample clip, no Modal/GPU
        return _MOCK_WAV, "UI-mock"

    if language == "bn":
        label = cfg.tts_bn_backend
        if not (text or "").strip():
            return None, label
        try:
            audio_bytes = synthesize_bengali_remote(text, GRANDMOTHER_CAPTION_BN)
            if not audio_bytes:
                return None, label
            return _write_wav(audio_bytes), label
        except Exception as e:  # noqa: BLE001 — never raise to the UI
            print(f"[tts.py] Bengali TTS failed: {e}")
            return None, label

    # English path: VoxCPM2 Voice Design.
    label = cfg.tts_en_backend
    if not (text or "").strip():
        return None, label
    try:
        audio_bytes = synthesize_english_remote(text, GRANDMOTHER_VOICE_EN)
        if not audio_bytes:
            return None, label
        return _write_wav(audio_bytes), label
    except Exception as e:  # noqa: BLE001 — never raise to the UI
        print(f"[tts.py] English TTS failed: {e}")
        return None, label