feat: improve subject generation workflow

This commit is contained in:
2026-05-18 17:44:52 +08:00
parent 78bd294d57
commit 1f600ae436
12 changed files with 682 additions and 372 deletions

View File

@@ -17,7 +17,9 @@ LOCAL_ASR_BIN=/opt/homebrew/bin/mlx_whisper
LOCAL_ASR_MODEL=mlx-community/whisper-tiny
LOCAL_ASR_TIMEOUT_SECONDS=180
TRANSLATE_MODEL=gemini-2.5-flash
REWRITE_MODEL=gemini-2.5-pro
GPT_TEXT_MODEL=gpt-4o
REWRITE_MODEL=gpt-4o
VISION_MODEL=gpt-4o
PRODUCT_VIEW_MODEL=gpt-image-2
IMAGE_BASE_URL=https://ai.skg.com/ezlink/v1
IMAGE_API_KEY=
@@ -27,6 +29,8 @@ SUBJECT_ASSET_IMAGE_MODEL=gpt-image-2
SUBJECT_ASSET_IMAGE_MODELS=gpt-image-2
# 可选:本地网络需要代理访问 ai.skg.com 时配置launchd 不一定继承 shell 代理变量。
AI_HTTP_PROXY=
YTDLP_COOKIES_FILE=
YTDLP_COOKIES_FROM_BROWSER=
VIDEO_MODEL=seedance
VIDEO_MODEL_SEEDANCE=seedance-2-fast
VIDEO_MODEL_KLING=kling-omni
@@ -35,6 +39,7 @@ VIDEO_MODEL_VEO3=veo-3.1-fast
# 音频文案改写 + Azure OpenAI 配音
AUDIO_REWRITE_MODEL=gemini-2.5-pro
AUDIO_PRODUCT_BRIEF="SKG 智能按摩产品,主打日常肩颈、腰背、眼部、膝盖或足部放松;广告表达要高级、干净、可信,不做医疗疗效承诺。"
# 语音通道服务端固定为 Azure OpenAI。
VOICE_PROVIDER=azure_openai
AZURE_OPENAI_BASE_URL=https://ai.skg.com/azure
AZURE_OPENAI_API_KEY=
@@ -42,13 +47,7 @@ AZURE_TTS_MODEL=gpt-4o-mini-tts
AZURE_TTS_VOICE_ID=alloy
AZURE_TTS_VOICE_POOL=alloy,verse,shimmer
AZURE_TTS_PATH=/audio/speech
# MiniMax 旧配音通道,保留兼容;默认不走
MINIMAX_API_KEY=
MINIMAX_TTS_BASE_URL=https://api.minimax.io
MINIMAX_TTS_MODEL=speech-2.8-turbo
MINIMAX_TTS_VOICE_ID=English_expressive_narrator
MINIMAX_TTS_VOICE_POOL=English_magnetic_voiced_man,English_Upbeat_Woman,English_MaturePartner
AZURE_TTS_PATHS=/audio/speech,/v1/audio/speech
# Poe 视频 API优先用于 Seedance / Kling / Veo
POE_API_BASE_URL=https://api.poe.com/v1