SamurAIGPT/Text-To-Video-AI
A pipeline that generates videos from text prompts by combining video diffusion models with LLM-powered script generation and text-to-speech.

This tool creates AI-generated videos from text descriptions by combining multiple AI services. It uses video diffusion models to generate visuals, integrates with LLMs (OpenAI, Groq, Gemini) for script generation, text-to-speech systems (EdgeTTS, ElevenLabs) for voiceovers, and Whisper for caption synchronization. The pipeline also fetches B-roll footage from Pexels and supports multiple video orientations for platforms like YouTube Shorts, Instagram Reels, and TikTok.