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>

backend/Dockerfile

@@ -0,0 +1,50 @@
+FROM python:3.11-slim
+
+WORKDIR /app
+
+# Install system dependencies
+RUN apt-get update && apt-get install -y \
+    ffmpeg \
+    fonts-nanum \
+    fonts-noto-cjk \
+    git \
+    curl \
+    unzip \
+    fontconfig \
+    && rm -rf /var/lib/apt/lists/*
+
+# Install additional Korean fonts for YouTube Shorts
+RUN mkdir -p /usr/share/fonts/truetype/korean && \
+    # Pretendard (가독성 최고)
+    curl -L -o /tmp/pretendard.zip "https://github.com/orioncactus/pretendard/releases/download/v1.3.9/Pretendard-1.3.9.zip" && \
+    unzip -j /tmp/pretendard.zip "*/Pretendard-Bold.otf" -d /usr/share/fonts/truetype/korean/ && \
+    unzip -j /tmp/pretendard.zip "*/Pretendard-Regular.otf" -d /usr/share/fonts/truetype/korean/ && \
+    # Black Han Sans (임팩트)
+    curl -L -o /usr/share/fonts/truetype/korean/BlackHanSans-Regular.ttf "https://github.com/AcDevelopers/Black-Han-Sans/raw/master/fonts/ttf/BlackHanSans-Regular.ttf" && \
+    # DoHyeon (귀여움)
+    curl -L -o /usr/share/fonts/truetype/korean/DoHyeon-Regular.ttf "https://github.com/nicholasrq/DoHyeon/raw/master/fonts/DoHyeon-Regular.ttf" && \
+    # Update font cache
+    fc-cache -fv && \
+    rm -rf /tmp/*.zip
+
+# Install yt-dlp
+RUN pip install --no-cache-dir yt-dlp
+
+# Install Python dependencies
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Download Whisper model (medium for CPU)
+RUN python -c "import whisper; whisper.load_model('medium')"
+
+# Copy application code
+COPY . .
+
+# Create data directories
+RUN mkdir -p data/downloads data/processed data/bgm
+
+# Expose port
+EXPOSE 8000
+
+# Run the application
+CMD ["uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "8000"]