xiaoxia-saas/apps/api/app/schemas/tts.py

"""TTS 合成 API Schema。"""

from __future__ import annotations

from datetime import datetime
from typing import Any, Optional

from pydantic import BaseModel, Field


class TTSSynthesizeRequest(BaseModel):
    """TTS 合成请求。"""

    text: str = Field(..., min_length=1, max_length=10000, description="合成文本")
    voice_id: str = Field("", description="音色 ID")
    output_name: str = Field("", description="输出文件名")
    language: str = Field("zh-CN", description="语言")
    speed: float = Field(1.0, ge=0.5, le=2.0, description="语速")
    style: Optional[str] = Field(
        None,
        description="语气风格（natural/sweet/excited/professional/news/livestream），可选；优先级高于 emotion",
    )
    volume: Optional[int] = Field(None, ge=0, le=100, description="音量（0-100），默认 50")
    pitch: Optional[float] = Field(None, ge=0.5, le=2.0, description="音调（0.5-2.0），默认 1.0")
    emotion: str = Field(
        "",
        description="[deprecated] 旧情绪参数，内部映射为 style；新接入请使用 style",
    )
    voice_model: str = Field("", description="语音模型名称")
    voice_clone_profile_id: str = Field("", description="关联的音色克隆档案 ID")
    format: str = Field("mp3", description="输出格式（mp3/wav/pcm）")
    metadata_: Optional[dict[str, Any]] = Field(default=None, alias="metadata", description="额外元数据")

    class Config:
        populate_by_name = True


class TTSJobResponse(BaseModel):
    """TTS 任务响应。"""

    id: str
    user_id: str
    input_text: str
    voice_id: str = ""
    voice_model: str = ""
    project_id: str = ""
    voice_clone_profile_id: str = ""
    status: str
    output_audio_url: str = ""
    output_audio_key: str = ""
    duration: float = 0.0
    file_size: int = 0
    sample_rate: int = 22050
    format: str = "mp3"
    error_message: str = ""
    retry_count: int = 0
    max_retries: int = 3
    metadata_: Optional[dict[str, Any]] = Field(default=None, alias="metadata", description="额外元数据")
    started_at: Optional[datetime] = None
    completed_at: Optional[datetime] = None
    created_at: datetime
    updated_at: datetime

    class Config:
        populate_by_name = True


class TTSStatusResponse(BaseModel):
    """TTS 任务状态响应（用于轮询）。"""

    id: str
    status: str
    output_audio_url: str = ""
    error_message: str = ""
    duration: float = 0.0
    retry_count: int = 0
    created_at: datetime
    updated_at: datetime


class TTSSynthesizeResponse(BaseModel):
    """TTS 合成创建响应。"""

    job_id: str
    status: str
    message: str = "合成任务已创建"


class ListTTSJobResponse(BaseModel):
    """TTS 任务列表响应。"""

    items: list[TTSJobResponse]
    total: int
    page: int
    page_size: int


class SaveToLibraryRequest(BaseModel):
    """保存到配音库请求。"""

    name: Optional[str] = Field(None, description="配音素材名称，留空则自动生成")


class SaveToLibraryResponse(BaseModel):
    """保存到配音库响应。"""

    id: str
    name: str
    audio_url: str
    duration: float
    voice_id: str
    voice_name: str
    status: str


class TTSPreviewRequest(BaseModel):
    """TTS 预览（试听）请求。"""

    text: str = Field(..., min_length=1, max_length=200, description="合成文本，限制 200 字")
    voice_id: str = Field(..., min_length=1, description="音色 ID")
    speed: float = Field(1.0, ge=0.5, le=2.0, description="语速")
    style: Optional[str] = Field(
        None,
        description="语气风格（natural/sweet/excited/professional/news/livestream），可选；优先级高于 emotion",
    )
    volume: Optional[int] = Field(None, ge=0, le=100, description="音量（0-100），默认 50")
    emotion: str = Field("", description="[deprecated] 旧情绪参数，内部映射为 style")
    language: str = Field("zh-CN", description="语言（zh-CN/en-US 等）")
    pitch: float = Field(1.0, ge=0.5, le=2.0, description="音调（0.5-2.0），默认 1.0")


class TTSPreviewResponse(BaseModel):
    """TTS 预览（试听）响应。"""

    audio_url: str = Field(..., description="合成音频 URL")
    duration: Optional[float] = Field(default=None, description="音频时长（秒）")