Files
xiaoxia-saas/apps/api/app/schemas/lipsync.py
T
frontend-dev 938ef0b8cc
CI/CD Pipeline / Dedup Check - skip PR tests when covered by push pipeline (push) Successful in 2s
CI/CD Pipeline / Check push changed paths (push) Successful in 4s
CI/CD Pipeline / Build Staging API Image (push) Successful in 21s
CI/CD Pipeline / Build Staging Worker Image (push) Successful in 24s
CI/CD Pipeline / Build Staging Web Image (push) Successful in 51s
CI/CD Pipeline / Integration Tests (push) Successful in 3m26s
CI/CD Pipeline / Validate - Python (mypy + alembic) (push) Successful in 3m37s
CI/CD Pipeline / Validate - Style (push) Successful in 4m6s
CI/CD Pipeline / Frontend Unit Tests (push) Successful in 4m29s
CI/CD Pipeline / Validate - Security (push) Successful in 8m25s
CI/CD Pipeline / Unit Tests (push) Successful in 8m59s
CI/CD Pipeline / Production Browser E2E (push) Has been skipped
CI/CD Pipeline / Deploy Staging (Watchtower auto-deploy) (push) Successful in 18m30s
CI/CD Pipeline / ACR Image Cleanup (push) Successful in 1m43s
CI/CD Pipeline / Staging E2E Tests (push) Failing after 3m7s
CI/CD Pipeline / Staging API Integration Tests (push) Successful in 3m42s
CI/CD Pipeline / CI Gate (push) Failing after 108h33m30s
CI/CD Pipeline / Build Production API Image (push) Failing after 108h33m30s
CI/CD Pipeline / Retag skipped Staging API Image (push) Failing after 108h41m37s
CI/CD Pipeline / PR Build Web Image (push) Failing after 108h42m36s
CI/CD Pipeline / Build Production Worker Image (push) Failing after 108h33m12s
CI/CD Pipeline / PR Build Worker Image (push) Failing after 108h42m18s
CI/CD Pipeline / PR Build API Image (push) Failing after 108h42m18s
CI/CD Pipeline / Retag skipped Staging Worker Image (push) Failing after 108h41m19s
CI/CD Pipeline / Retag skipped Staging Web Image (push) Failing after 108h41m19s
CI/CD Pipeline / Canary Release to Production (push) Failing after 108h18m59s
CI/CD Pipeline / Deploy Production (push) Failing after 108h33m9s
CI/CD Pipeline / Build Production Web Image (push) Failing after 108h33m12s
CI/CD Pipeline / Frontend Lint (push) Failing after 108h42m14s
CI/CD Pipeline / Check if frontend-only change (push) Failing after 108h42m19s
fix(ai-avatar): 端到端一致性修复(标题/封面/B-roll位置/B-roll时长) (#1869)
Co-authored-by: frontend-dev <frontend-dev@xiaoxiajianji.com>
Co-committed-by: frontend-dev <frontend-dev@xiaoxiajianji.com>
2026-09-12 02:41:11 +08:00

102 lines
3.8 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.
"""对口型 API Schema 定义 — #1796 / #1809 / #1822.
支持两种输入模式(二选一):
1. TTS 直生模式(推荐):传 voice_id + script_text(+ speed/emotion),
后端内部先调 CosyVoice 合成音频,再提交 MediaKit 对口型。
2. 直接音频模式:传 video_url + audio_url(音频已由调用方准备好)。
"""
from __future__ import annotations
from datetime import datetime
from typing import Optional
from pydantic import BaseModel, Field, model_validator
class LipsyncJobResponse(BaseModel):
"""对口型任务响应."""
id: str
user_id: str
project_id: str
video_url: str
audio_url: str
enable_video_loop: bool
voice_id: str = ""
script_text: str = ""
speed: float = 1.0
emotion: str = ""
mediakit_task_id: str
status: str
output_video_url: str
output_duration: float
error_message: str
error_code: str
sentence_timings: Optional[list] = None
submitted_at: Optional[datetime] = None
completed_at: Optional[datetime] = None
created_at: datetime
updated_at: datetime
class Config:
from_attributes = True
class CreateLipsyncJobRequest(BaseModel):
"""创建对口型任务请求.
两种模式(二选一):
- TTS 直生:voice_id + script_text 必填(+ 可选 speed/emotion);audio_url 留空。
- 直接音频:video_url + audio_url 必填。
"""
video_url: str = Field(..., description="人物视频 URL(MP4,≤30min,单人真人)")
# 模式 2:直接音频
audio_url: str = Field("", description="驱动音频 URL(mp3/aac/wav/m4a/flac);直生模式留空")
# 模式 1:TTS 直生
voice_id: str = Field("", description="音色 ID(预置音色或克隆音色 profile UUID)")
script_text: str = Field("", description="要合成的文案(直生模式必填,最长 5000 字符)")
speed: float = Field(1.0, ge=0.5, le=2.0, description="语速(0.5-2.0),默认 1.0")
emotion: str = Field("", description="情绪(natural/excited/calm/friendly 或中文 自然/兴奋/沉稳/亲切)")
enable_video_loop: bool = Field(False, description="音频长于视频时是否循环画面")
project_id: str = Field("", description="项目 ID(可选)")
@model_validator(mode="after")
def _validate_input_mode(self) -> "CreateLipsyncJobRequest":
video = (self.video_url or "").strip()
if not video:
raise ValueError("video_url 不能为空")
if not video.startswith(("http://", "https://")):
raise ValueError("video_url 必须是 HTTP/HTTPS URL")
lower = video.lower().split("?")[0]
if not lower.endswith(".mp4"):
raise ValueError("video_url 仅支持 MP4 格式")
has_audio = bool((self.audio_url or "").strip())
has_tts = bool((self.voice_id or "").strip()) and bool((self.script_text or "").strip())
if not has_audio and not has_tts:
raise ValueError(
"必须提供驱动音频:要么传 audio_url(直接音频模式),"
"要么同时传 voice_id + script_text(TTS 直生模式)"
)
if has_tts and len(self.script_text) > 5000:
raise ValueError("script_text 最长 5000 字符")
if has_audio:
au = self.audio_url.strip()
if not au.startswith(("http://", "https://")):
raise ValueError("audio_url 必须是 HTTP/HTTPS URL")
au_lower = au.lower().split("?")[0]
allowed = (".mp3", ".aac", ".wav", ".m4a", ".flac")
if not any(au_lower.endswith(ext) for ext in allowed):
raise ValueError(f"audio_url 格式不支持,仅支持: {', '.join(allowed)}")
self.audio_url = au
return self