35 lines
1.2 KiB
Python
35 lines
1.2 KiB
Python
from pydantic import BaseModel
|
||
from typing import Optional, List, Literal
|
||
|
||
|
||
class CustomAssignment(BaseModel):
|
||
material_path: str
|
||
start: float # 音频时间轴起点
|
||
end: float # 音频时间轴终点
|
||
source_start: float = 0.0 # 源视频截取起点
|
||
source_end: Optional[float] = None # 源视频截取终点（可选）
|
||
|
||
|
||
class GenerateRequest(BaseModel):
|
||
text: str
|
||
voice: str = "zh-CN-YunxiNeural"
|
||
material_path: str
|
||
material_paths: Optional[List[str]] = None
|
||
tts_mode: str = "edgetts"
|
||
ref_audio_id: Optional[str] = None
|
||
ref_text: Optional[str] = None
|
||
language: str = "zh-CN"
|
||
generated_audio_id: Optional[str] = None # 预生成配音 ID（存在时跳过内联 TTS）
|
||
title: Optional[str] = None
|
||
enable_subtitles: bool = True
|
||
subtitle_style_id: Optional[str] = None
|
||
title_style_id: Optional[str] = None
|
||
subtitle_font_size: Optional[int] = None
|
||
title_font_size: Optional[int] = None
|
||
title_top_margin: Optional[int] = None
|
||
subtitle_bottom_margin: Optional[int] = None
|
||
bgm_id: Optional[str] = None
|
||
bgm_volume: Optional[float] = 0.2
|
||
custom_assignments: Optional[List[CustomAssignment]] = None
|
||
output_aspect_ratio: Literal["9:16", "16:9"] = "9:16"
|