Automate YouTube Shorts creation locally — script generation, stock video search, TTS voiceover, subtitles, background music, and social media scheduling.

• AI Script Generation — uses g4f (free) or Gemini to generate video scripts
• Stock Video Search — auto-downloads matching clips from Pexels
• Multi-Voice TTS — Supertonic (local, 10 voices, 33 languages), TikTok TTS (fallback), KittenTTS
• Subtitle Templates — 10 presets (classic, modern_glow, bold_outline, minimal, cinematic, neon, social_viral, floating, news_ticker, karaoke_highlight)
• Background Music — auto-mix from your music library or extract from a video
• Image Stitching — upload multiple images to stitch at the start of the video with configurable duration per image (default 5s)
• Frame Extraction — extract a frame from any generated video for thumbnails
• Aspect Ratios — 9:16, 16:9, 1:1, 4:5, 21:9
• Multi-Business MagicSync — configure multiple API keys for different businesses; select which one to use when scheduling
• Social Media Scheduling — schedule posts to Instagram, TikTok, Facebook, LinkedIn, YouTube via MagicSync
• Hardware Acceleration — auto-detects GPU for faster ffmpeg encoding

YouTube or click on the image.

git clone https://github.com/leamsigc/ShortsGenerator.git
cd ShortsGenerator
cp .env.example .env
# Edit .env — at minimum set PEXELS_API_KEY and IMAGEMAGICK_BINARY
docker compose up -d

Open http://localhost:5000 or http://localhost:3000 for the frontend.

pip install -r requirements.txt
cp .env.example .env
# Fill in PEXELS_API_KEY, IMAGEMAGICK_BINARY, etc.
cd Backend
python main.py

cd UI
npm install
npm run dev

The frontend depends on the backend running on port 8080.

See EnvironmentVariables.md for the full list.

1. Generate a script — enter a video subject, select a script template, click Generate
2. Review & edit — modify the script, add search keywords, select subtitle template
3. Upload images (optional) — upload images that will be stitched at the start of the video; set duration per image
4. Select voice — choose TTS engine and voice style
5. Set aspect ratio — 9:16 (default), 16:9, 1:1, or 4:5
6. Generate video — downloads stock clips, generates TTS, combines everything with subtitles
7. Add music — pick from your music library or extract audio from a video
8. Schedule — in the Videos page, click "Schedule Upload", select a business and platforms, set date/time, and post via MagicSync

In the Generate page, click the Images section and upload one or more images. Each image becomes a video segment at the start of the final video. Adjust the global duration (default 5s) or set per-image duration. Images are scaled and cropped to match the selected aspect ratio.

In Settings → MagicSync Integration, add API keys for each business. Each business has its own MagicSync URL, API token, and video base URL. When scheduling a video, select which business to use — the correct credentials are sent automatically.

POST /api/extract-frame extracts a frame from any generated video at a given timestamp. Use this to generate custom thumbnails.

Backend/
├── main.py              # Flask app, all API routes
├── video.py             # Video processing, ffmpeg, subtitles, images
├── settings.py          # Global defaults
├── gpt.py               # AI script generation
├── search.py            # Pexels stock video search
├── tiktokvoice.py       # TikTok TTS
├── classes/
│   └── Shorts.py        # Core pipeline orchestrator
UI/
├── pages/
│   ├── generate/index.vue  # Video generation workspace
│   ├── videos/index.vue    # Gallery + scheduling
│   └── settings.vue        # Global settings + MagicSync
├── composables/
│   ├── useVideoSettings.ts # Video generation state
│   └── useGlobalSettings.ts # App-wide settings
└── stores/

Pull requests are welcome. For major changes, please open an issue first.

See LICENSE for details.