865fcdc246
- Add model selection (flash vs pro) for quality control - Add speed slider (0.5x - 2.0x) for pacing adjustment - Add style presets (neutral, calm, energetic, professional, warm, documentary) - Add custom style prompt option for advanced customization - New /tts/options endpoint returns available TTS options - Voice preview now tests all settings so users hear exact output - Backward compatible: all new fields have sensible defaults 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
119 lines
3.9 KiB
Python
119 lines
3.9 KiB
Python
from datetime import datetime
|
|
from enum import Enum
|
|
from typing import Any, Literal, Optional
|
|
|
|
from pydantic import BaseModel, Field, constr
|
|
|
|
|
|
class JobStatus(str, Enum):
|
|
CREATED = "created"
|
|
INGESTING = "ingesting"
|
|
AI_PROCESSING = "ai_processing"
|
|
PENDING_QC = "pending_qc"
|
|
APPROVED_ENGLISH = "approved_english" # For English source videos
|
|
APPROVED_SOURCE = "approved_source" # For non-English source videos
|
|
REJECTED = "rejected"
|
|
QC_FEEDBACK = "qc_feedback"
|
|
TRANSLATING = "translating"
|
|
TTS_GENERATING = "tts_generating"
|
|
PENDING_FINAL_REVIEW = "pending_final_review"
|
|
COMPLETED = "completed"
|
|
|
|
@classmethod
|
|
def is_approved(cls, status: str) -> bool:
|
|
"""Check if status indicates source approval (any language)"""
|
|
return status in [cls.APPROVED_ENGLISH.value, cls.APPROVED_SOURCE.value]
|
|
|
|
|
|
class Source(BaseModel):
|
|
filename: str
|
|
original_filename: Optional[str] = None
|
|
gcs_uri: str
|
|
duration_s: Optional[float] = None
|
|
language: constr(min_length=2, max_length=10) = "en" # Final source language (from detection or explicit)
|
|
language_hint: Optional[str] = None # User-provided hint for non-English videos
|
|
detected_language: Optional[str] = None # AI-detected language from Gemini
|
|
|
|
|
|
class TTSPreferences(BaseModel):
|
|
"""TTS voice preferences for audio description generation"""
|
|
provider: Literal["gemini", "google", "elevenlabs"] = "gemini"
|
|
default_voice: str = "Kore" # Default Gemini voice
|
|
voices_per_language: dict[str, str] = {} # {"en": "Kore", "es": "Aoede"}
|
|
# TTS quality and style settings
|
|
model: Literal["flash", "pro"] = "flash" # flash = fast/cheap, pro = higher quality
|
|
speed: float = Field(default=1.0, ge=0.5, le=2.0) # Speech rate multiplier
|
|
style_preset: Literal[
|
|
"neutral", "calm", "energetic", "professional", "warm", "documentary", "custom"
|
|
] = "neutral"
|
|
custom_style_prompt: Optional[str] = None # Used when style_preset is "custom"
|
|
|
|
|
|
class RequestedOutputs(BaseModel):
|
|
captions_vtt: bool = True
|
|
audio_description_vtt: bool = True
|
|
audio_description_mp3: bool = True
|
|
languages: list[str] = []
|
|
transcreation: list[str] = []
|
|
tts_preferences: Optional[TTSPreferences] = None
|
|
|
|
|
|
class LangOutput(BaseModel):
|
|
captions_vtt_gcs: Optional[str] = None
|
|
ad_vtt_gcs: Optional[str] = None
|
|
ad_mp3_gcs: Optional[str] = None
|
|
origin: Optional[Literal["translate", "transcreate"]] = None
|
|
qa_notes: Optional[str] = None
|
|
|
|
|
|
class ReviewHistoryItem(BaseModel):
|
|
at: datetime
|
|
status: str
|
|
by: Optional[str] = None
|
|
notes: Optional[str] = None
|
|
|
|
|
|
class Review(BaseModel):
|
|
notes: Optional[str] = ""
|
|
reviewer_id: Optional[str] = None
|
|
history: list[ReviewHistoryItem] = []
|
|
|
|
|
|
class AISection(BaseModel):
|
|
ingestion_json: Optional[dict[str, Any]] = None
|
|
confidence: Optional[float] = None
|
|
|
|
|
|
class Job(BaseModel):
|
|
id: Optional[str] = Field(None, alias="_id")
|
|
client_id: str
|
|
title: str
|
|
source: Source
|
|
requested_outputs: RequestedOutputs
|
|
status: JobStatus = JobStatus.CREATED
|
|
review: Review = Review()
|
|
outputs: Optional[dict[str, LangOutput]] = None
|
|
ai: Optional[AISection] = None
|
|
error: Optional[dict[str, Any]] = None
|
|
created_at: Optional[datetime] = None
|
|
updated_at: Optional[datetime] = None
|
|
|
|
class Config:
|
|
populate_by_name = True
|
|
use_enum_values = True
|
|
|
|
|
|
class JobCreate(BaseModel):
|
|
title: str
|
|
source_is_english: bool = True # True = English source, False = other language (auto-detect)
|
|
language_hint: Optional[str] = None # Optional hint when source_is_english=False
|
|
requested_outputs: RequestedOutputs
|
|
|
|
|
|
class JobUpdate(BaseModel):
|
|
title: Optional[str] = None
|
|
status: Optional[JobStatus] = None
|
|
review: Optional[Review] = None
|
|
outputs: Optional[dict[str, LangOutput]] = None
|
|
ai: Optional[AISection] = None
|
|
error: Optional[dict[str, Any]] = None
|