Develop AI Whiteboard Video Generator Tool

Job Title: AI Engineer Needed – Offline + Online Whiteboard Video Generator (Open Source Models)

Project Overview:
I want to build a clean and minimal tool similar to “Golpo AI” that generates complete whiteboard explainer videos from a single prompt or script.

I have zero programming knowledge, so I need an engineer who can build the full pipeline end-to-end and guide me.

Main Requirement:
I want to enter a prompt or full script → the tool automatically generates:
1) a whiteboard-style video (hand-drawn / animated drawing effect)
2) voice narration (AI voice)
3) final MP4 export (at least 4 minutes per video)

IMPORTANT:
I strongly prefer using open-source / free models for both video generation and voice generation so the tool can run offline. If fully open-source quality is not possible, use minimum-cost APIs (low-cost LLM like Grok or similar) while still keeping the system cost extremely low.

Key Features Needed:
- Simple clean UI (minimalistic)
- Prompt/script input box
- Generate video button
- Output: MP4 file (4+ minutes)
- Automatic scene/storyboard creation
- Auto-sync narration and visuals
- Options:
- voice selection (male/female)
- narration speed
- background music (optional)
- subtitles (optional)

Tech Requirements:
- Must support OFFLINE mode (local machine) using open-source models (preferred)
- Should also support ONLINE mode (server/cloud deployment)
- Efficient pipeline (render without crashing)
- Works on CPU + GPU if available (CUDA GPU preferred)

Preferred Implementation (engineer decides exact tools):
- Python backend (FastAPI preferred)
- Local model inference pipeline
- Video assembly using FFmpeg / MoviePy
- Open-source TTS narration (example: XTTS, Piper, Coqui TTS, etc.)
- Open-source image generation or whiteboard assets pipeline
- LLM for storyboard/script breakdown (open-source model OR cheapest API)

Deliverables:
1) Working tool/app that generates whiteboard videos automatically
2) Full source code
3) Installation guide (non-technical friendly)
4) Optionally: packaged desktop app (Windows/Mac) OR Docker setup for easy run

Nice to Have:
- Multi-language narration
- Ability to upload logo + brand font
- Multiple video templates/styles