Input one idea → AI writes script, generates storyboard, video automatically
English | 简体中文
-
❌ No video editing software needed
-
❌ No complex prompts required
-
❌ No need to manually align subtitles/voiceovers
-
✅ Minimalist Workflow: Just enter a clear Idea. AI handles the script, storyboard, voiceover, and editing. Zero-barrier creation.
-
✅ Multi-Platform Access: Support for Web, Discord Bot, and Telegram Bot. Create anywhere, anytime.
-
✅ Lightning Fast: Average generation time is around 1 minute. Rapidly validate your content ideas.
-
🔓 Open Source — MIT License, fully self-hostable
-
🚀 One-click Generation — Idea → Script → Storyboard → Video
-
🧩 AI Storyboard — Scene-by-scene visual prompts
-
🔊 Audio Sync — TTS + BGM auto alignment
-
🌐 Multi-platform — Discord / Telegram / Web
-
🖌️ Styles — Anime / Realistic / 3D Render
You may have already tried:
- Using ChatGPT to write scripts
- Using Midjourney / Flux to generate images
- Using video editing software to assemble videos
SparkShort combines all these steps into a single input.
-
✅ Efficiency Seeker: You want to turn ideas into videos without wrestling with complex editing software.
-
✅ Solo Creator: You need a "one-click" tool to validate content concepts quickly.
-
✅ Early Adopter: You love exploring the boundaries of AI and growing with an evolving product.
-
❌ Perfectionist: You require absolute pixel-perfect control and cannot tolerate minor AI artifacts.
-
❌ Hands-Off Dreamer: You expect viral hits without providing a core, structured idea.
-
❌ Full Control Manualist: You want to manually tweak every transition and rendering parameter.
This project supports one-command startup using Docker Compose.
When running with Docker, FFmpeg is already included. No additional installation is needed on the host machine.
Prerequisites
-
Docker ≥ 20
-
Docker Compose v2
1️⃣ Clone the repository
git clone https://github.com/heyaohuo/SparkShort.git
cd SparkShort
2️⃣ Configure environment variables
- Backend: shorts_generation/.env (refer to .env.example if available)
3️⃣ Start the app
docker compose up -d
4️⃣ Access the app
-
Frontend: http://localhost:3000
-
Backend API: http://localhost:8000
Prerequisites
- Node.js 22.0+
- Python 3.10+
- FFmpeg
git clone https://github.com/heyaohuo/SparkShort.git
cd SparkShortWe recommend using a virtual environment:
cd shorts_generation
python -m venv venv
source venv/bin/activate # Windows: venv\Scripts\activate
pip install -r requirements.txtcd frontend
npm installCreate a .env file in the shorts_generation directory (refer to .env.example if available)
Start Backend:
fastapi dev app/main.pyStart Frontend:
npm run devInside Discord, you can:
- 🚀 Get early access to new video models & features
- 🧪 Join private beta tests before public release
- 🧠 Learn how creators are monetizing AI shorts
- 🗳 Vote on roadmap features (your vote matters)
Roadmap priorities are driven by community feedback.
🤝 Contributing Contributions are welcome! Please feel free to submit a Pull Request or open an Issue.
⭐ If SparkShort saves you time or inspires your workflow, consider giving it a Star — it really helps the project grow.