AI Voiceover with GPT4V

Hugging Face Space

huggingface.co/spaces/martintomov/gpt4v-voiceover

Input Video

Input Video

Output Video

Output Video

Jupyter Notebook

gpt4v-video-voiceover/voiceover.ipynb

Workflow

1. Environment Setup: Load necessary API keys and configurations.
2. Video to Frames: Convert a video into individual frames suitable for processing.
3. AI-Generated Script: Use gpt4v to create a script based on the video frames.
4. Text to Speech: Convert the script to audio.
5. Video Finalization: Merge the audio back into the video, adjusting the video duration to match the audio if necessary.

Requirements

• Python 3.x
• python-dotenv
• moviepy
• opencv-python
• openai
• requests
• streamlit

Disclaimer

This project is only for demonstration and showcases purposes. Feel free to clone and modify the code to suit your needs.