- TimelineEditor, VideoStudio 컴포넌트 신규 추가
- 백엔드 transcriber, video_processor 서비스 개선
- 프론트엔드 HomePage 리팩토링 및 스타일 업데이트
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- 인트로(썸네일) 텍스트 제한을 10자에서 20자로 증가
- 비디오 URL에 updated_at 타임스탬프 추가하여 캐싱 문제 해결
- 재편집 후 영상이 이전 버전으로 보이는 문제 수정
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- 카테고리당 BGM 3개씩 다운로드 기능 추가
- 파일명에 카테고리 prefix 추가 (예: upbeat_trackname.mp3)
- 중복 BGM 자동 스킵 기능
- 프론트엔드에서 BGM을 카테고리별로 그룹화하여 표시
- 분류되지 않은 BGM은 '기타' 섹션에 표시
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Docker layer caching will now preserve the Whisper model download step,
avoiding 1.5GB download on every deployment.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Replace webhook-based deployment with Gitea Actions workflow.
On push to main, the workflow will:
- SSH into the server
- Pull latest code
- Rebuild and restart Docker containers
Required secrets in Gitea:
- SERVER_HOST
- SERVER_USER
- SERVER_SSH_KEY
- SERVER_PORT
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- deploy.sh: Script to pull code and restart Docker containers
- webhook-server.py: HTTP server to receive Gitea push events
- shorts-maker-webhook.service: Systemd service for webhook server
- setup-autodeploy.sh: Setup script for the server
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Intro text: Add 0.7s freeze frame effect before video plays
- Intro text: Auto-scale font size to prevent overflow
- Intro text: Split long text into 2 lines automatically
- BGM Page: Add free BGM download section with 6 categories
- BGM Page: Support individual and bulk download from Freesound.org
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
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>
