42 lines
1.2 KiB
Python
42 lines
1.2 KiB
Python
"""
|
|
TTS API schemas
|
|
"""
|
|
|
|
from typing import Optional
|
|
from pydantic import BaseModel, Field
|
|
|
|
|
|
class TTSSynthesizeRequest(BaseModel):
|
|
"""TTS synthesis request"""
|
|
text: str = Field(..., description="Text to synthesize")
|
|
workflow: Optional[str] = Field(
|
|
None,
|
|
description="TTS workflow key (e.g., 'runninghub/tts_edge.json' or 'selfhost/tts_edge.json'). If not specified, uses default workflow from config."
|
|
)
|
|
ref_audio: Optional[str] = Field(
|
|
None,
|
|
description="Reference audio path for voice cloning (optional). Can be a local file path or URL."
|
|
)
|
|
voice_id: Optional[str] = Field(
|
|
None,
|
|
description="Voice ID (deprecated, use workflow instead)"
|
|
)
|
|
|
|
class Config:
|
|
json_schema_extra = {
|
|
"example": {
|
|
"text": "Hello, welcome to Pixelle-Video!",
|
|
"workflow": "runninghub/tts_edge.json",
|
|
"ref_audio": None
|
|
}
|
|
}
|
|
|
|
|
|
class TTSSynthesizeResponse(BaseModel):
|
|
"""TTS synthesis response"""
|
|
success: bool = True
|
|
message: str = "Success"
|
|
audio_path: str = Field(..., description="Path to generated audio file")
|
|
duration: float = Field(..., description="Audio duration in seconds")
|
|
|