Initial commit: YouTube Shorts maker application

Features:
- Video download from TikTok/Douyin using yt-dlp
- Audio transcription with OpenAI Whisper
- GPT-4 translation (direct/summarize/rewrite modes)
- Subtitle generation with ASS format
- Video trimming with frame-accurate preview
- BGM integration with volume control
- Intro text overlay support
- Thumbnail generation with text overlay

Tech stack:
- Backend: FastAPI, Python 3.11+
- Frontend: React, Vite, TailwindCSS
- Video processing: FFmpeg
- AI: OpenAI Whisper, GPT-4

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
This commit is contained in:
kihong.kim
2026-01-03 21:38:34 +09:00
commit c3795138da
64 changed files with 13059 additions and 0 deletions

27
.env.example Normal file
View File

@@ -0,0 +1,27 @@
# OpenAI API Key (필수)
OPENAI_API_KEY=your_openai_api_key_here
# OpenAI 모델 설정
OPENAI_MODEL=gpt-4o-mini # gpt-4o-mini (저렴), gpt-4o (고품질)
# 번역 모드: direct (직역), summarize (요약), rewrite (재구성)
TRANSLATION_MODE=rewrite
# 번역 최대 토큰 수 (비용 제어)
TRANSLATION_MAX_TOKENS=1000
# Pixabay API Key (선택 - BGM 검색용)
# https://pixabay.com/api/docs/ 에서 무료 발급
PIXABAY_API_KEY=
# Freesound API Key (선택 - 자동 BGM 검색/다운로드)
# https://freesound.org/apiv2/apply 에서 무료 발급
# 50만개+ CC 라이선스 사운드 검색 가능
FREESOUND_API_KEY=
# Whisper 모델 (small, medium, large)
# GPU 없으면 medium 권장
WHISPER_MODEL=medium
# 웹 서버 포트
PORT=3000