Skip to main content
ffmpeg must be installed and available on your PATH. Splyce uses ffmpeg for all video assembly and splicing operations. Video generation will fail without it.

​
Prerequisites

Before you start, make sure you have the following installed:
  • Python 3.10+ — check with python --version or python3 --version
  • pip — comes with Python; check with pip --version
  • ffmpeg — install via your system package manager (see below)
  • git — to clone the repository
brew install ffmpeg
Verify ffmpeg is on your PATH: 
ffmpeg -version

​
Installation

1

Clone the repository

git clone https://github.com/rushilkukreja/hoohacks.git
cd hoohacks
2

Create a virtual environment

python -m venv .venv
source .venv/bin/activate   # Windows: .venv\Scripts\activate
3

Install dependencies

pip install -r requirements.txt
4

Create your .env file

Create a .env file at the project root with at minimum your Gemini API key:
GEMINI_API_KEY=your_key_here

# Optional: required for voiceover generation
ELEVENLABS_API_KEY=your_key_here
Get a Gemini API key from Google AI Studio.For a full list of supported variables, see Environment variables.
5

Start the server

Run the server using the provided run.py launcher:
python run.py
This starts Uvicorn with --reload enabled on 127.0.0.1:8000. The process reads the PORT environment variable if you need a different port.Alternatively, invoke Uvicorn directly:
uvicorn app.main:app --reload --host 127.0.0.1 --port 8000
6

Verify the server is running

Send a request to the health endpoint:
curl http://127.0.0.1:8000/api/health
Expected response:
{
  "status": "ok",
  "service": "splyce-ad-personalization",
  "prompt_api": "product-prompt-v2-no-standard-ad",
  "gemini_configured": true,
  "elevenlabs_configured": false
}
gemini_configured is true when GEMINI_API_KEY is set. elevenlabs_configured is true when ELEVENLABS_API_KEY is set.

​
Production considerations

  • Disable reload — reload=True watches the filesystem for code changes. Remove it in production (--no-reload with Uvicorn, or edit run.py to pass reload=False).
  • Set a stable PORT — export PORT in your environment or process manager config so the port is predictable across restarts.
  • Use a reverse proxy — run Splyce behind nginx or a cloud load balancer to handle TLS termination, request buffering, and rate limiting.
  • Increase upload limits — the default MAX_VIDEO_UPLOAD_MB is 200. Adjust this to match your infrastructure limits and reverse proxy body-size settings.

Build docs developers (and LLMs) love

Get started for freeTalk to us