modules/video_creator/schemas.py

from pydantic import BaseModel, Field
from typing import List, Optional, Literal
from enum import Enum


class VoiceEnum(str, Enum):
    """Available TTS voices"""
    af_heart = "af_heart"
    af_alloy = "af_alloy"
    af_aoede = "af_aoede"
    af_bella = "af_bella"
    af_jessica = "af_jessica"
    af_kore = "af_kore"
    af_nicole = "af_nicole"
    af_nova = "af_nova"
    af_river = "af_river"
    af_sarah = "af_sarah"
    af_sky = "af_sky"
    am_adam = "am_adam"
    am_echo = "am_echo"
    am_eric = "am_eric"
    am_fenrir = "am_fenrir"
    am_liam = "am_liam"
    am_michael = "am_michael"
    am_onyx = "am_onyx"
    am_puck = "am_puck"
    am_santa = "am_santa"
    bf_emma = "bf_emma"
    bf_isabella = "bf_isabella"
    bm_george = "bm_george"
    bm_lewis = "bm_lewis"
    bf_alice = "bf_alice"
    bf_lily = "bf_lily"
    bm_daniel = "bm_daniel"
    bm_fable = "bm_fable"


class MusicMoodEnum(str, Enum):
    """Available music moods"""
    sad = "sad"
    melancholic = "melancholic"
    happy = "happy"
    euphoric = "euphoric/high"
    excited = "excited"
    chill = "chill"
    uneasy = "uneasy"
    angry = "angry"
    dark = "dark"
    hopeful = "hopeful"
    contemplative = "contemplative"
    funny = "funny/quirky"


class OrientationEnum(str, Enum):
    """Video orientation"""
    portrait = "portrait"
    landscape = "landscape"


class CaptionPositionEnum(str, Enum):
    """Caption position on video"""
    top = "top"
    center = "center"
    bottom = "bottom"


class MusicVolumeEnum(str, Enum):
    """Music volume level"""
    low = "low"
    medium = "medium"
    high = "high"
    muted = "muted"


class VideoStatus(str, Enum):
    """Video processing status"""
    processing = "processing"
    ready = "ready"
    failed = "failed"


class SceneInput(BaseModel):
    """Input for a single scene in the video"""
    text: str = Field(..., description="Text to be narrated in this scene")
    searchTerms: List[str] = Field(..., description="Keywords for finding background video", alias="searchTerms")
    
    class Config:
        populate_by_name = True


class RenderConfig(BaseModel):
    """Configuration for video rendering"""
    paddingBack: Optional[int] = Field(0, description="End screen duration in milliseconds")
    music: Optional[MusicMoodEnum] = Field(None, description="Background music mood")
    captionPosition: CaptionPositionEnum = Field(CaptionPositionEnum.bottom, description="Caption position")
    captionBackgroundColor: str = Field("blue", description="Caption background color")
    voice: VoiceEnum = Field(VoiceEnum.af_heart, description="TTS voice")
    orientation: OrientationEnum = Field(OrientationEnum.portrait, description="Video orientation")
    musicVolume: MusicVolumeEnum = Field(MusicVolumeEnum.high, description="Background music volume")
    
    class Config:
        populate_by_name = True


class CreateVideoRequest(BaseModel):
    """Request to create a short video"""
    scenes: List[SceneInput] = Field(..., min_length=1, description="List of scenes for the video")
    config: Optional[RenderConfig] = Field(default_factory=RenderConfig, description="Render configuration")


class CreateVideoResponse(BaseModel):
    """Response after creating a video"""
    videoId: str = Field(..., description="Unique ID for the created video")


class VideoStatusResponse(BaseModel):
    """Response for video status check"""
    status: VideoStatus = Field(..., description="Current status of the video")


class VideoListItem(BaseModel):
    """Single video in the list"""
    id: str
    status: VideoStatus


class VideoListResponse(BaseModel):
    """Response for listing all videos"""
    videos: List[VideoListItem]


class Caption(BaseModel):
    """Caption with timing information"""
    text: str
    startMs: int
    endMs: int


class Scene(BaseModel):
    """Processed scene with all media"""
    captions: List[Caption]
    video: str  # Path to video file
    audio: dict  # Audio info with 'url' and 'duration'