Files
xiaoxia-saas/apps/api/app/schemas/tts.py
T
灵应 d1c83de698
CI/CD Pipeline / Deploy Staging (push) Has been skipped
CI/CD Pipeline / Staging E2E Tests (push) Has been skipped
CI/CD Pipeline / Build Production Runtime Images (push) Has been skipped
CI/CD Pipeline / Deploy Production (push) Has been skipped
CI/CD Pipeline / Production Browser E2E (push) Has been skipped
CI/CD Pipeline / Frontend Lint (push) Failing after 47h32m26s
CI/CD Pipeline / Validate Code Quality And Tests (push) Failing after 47h32m26s
feat: TTS 生成页加存为素材功能
- 合成完成后显示「存为素材」按钮,点击弹出保存弹窗
- 弹窗支持改名称、选标签(预设标签 + 自定义新增)
- 保存成功后提示「去素材库查看」可跳转配音素材库
- 新增 saveTtsToLibrary API 对接后端 POST /tts/jobs/{id}/save-to-library
2026-07-07 13:21:39 +08:00

104 lines
2.7 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
"""TTS 合成 API Schema。"""
from __future__ import annotations
from datetime import datetime
from typing import Any, Dict, List, 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")
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