"""Contrato HTTP v1 do serviço de voz do CenaForge (herdado do dropsz_voice; campos em camelCase).""" from __future__ import annotations import re import unicodedata from typing import Literal from pydantic import BaseModel, ConfigDict, Field, field_validator # Limite duro do schema; o limite efetivo (VOICE_MAX_TEXT_CHARS) é aplicado no serviço. HARD_TEXT_LIMIT = 5000 REQUEST_ID_PATTERN = r"^[A-Za-z0-9_-]{8,64}$" VOICE_ID_PATTERN = r"^[a-z0-9][a-z0-9-]{1,47}$" _CONTROL = re.compile(r"[\x00-\x08\x0b\x0c\x0e-\x1f\x7f]") _SPACES = re.compile(r"\s+") def normalize_text(text: str) -> str: """NFC, sem caracteres de controle, espaços colapsados. É o texto que vira chave de cache.""" text = unicodedata.normalize("NFC", text) text = _CONTROL.sub(" ", text) return _SPACES.sub(" ", text).strip() class SynthesisParams(BaseModel): model_config = ConfigDict(extra="forbid") speed: float = Field(1.0, ge=0.5, le=2.0, description="1.0 = normal; 2.0 = duas vezes mais rápido") # wav = para o render (FFmpeg mistura sem perda); ogg_opus = leve, para ouvir no painel. format: str = Field("ogg_opus", pattern=r"^(ogg_opus|wav)$") class SynthesizeRequest(BaseModel): model_config = ConfigDict(extra="forbid") requestId: str = Field(..., pattern=REQUEST_ID_PATTERN) text: str = Field(..., min_length=1, max_length=HARD_TEXT_LIMIT) voiceId: str = Field(..., pattern=VOICE_ID_PATTERN) params: SynthesisParams = Field(default_factory=SynthesisParams) @field_validator("text") @classmethod def _normalize(cls, value: str) -> str: value = normalize_text(value) if not value: raise ValueError("texto vazio") return value class VoiceDescriptor(BaseModel): """Descritor público de voz (ADR 0025 §2.3). Sem caminho de arquivo, URL ou origem interna.""" id: str name: str languages: list[str] revision: str engine: Literal["tts", "tts+rvc"] default: bool # Campos do CenaForge: motor base, voz base (vozes de personagem) e se veio do painel. provider: Literal["piper", "edge", "kokoro", "google", "azure", "clone", "fake"] | None = None baseVoice: str | None = None user: bool = False offline: bool | None = None rvc: dict | None = None description: str | None = None gender: Literal["female", "male", "neutral"] | None = None ageRange: Literal["child", "young", "adult", "senior"] | None = None accent: str | None = None class VoicesPage(BaseModel): items: list[VoiceDescriptor] nextCursor: str | None