Build a PoC in Python using Streamlit which takes a Video file and replace its audio with an AI Generated voice.
Original Video Taken for Testing :
GEN_AI_VIDEO.mp4
The Python code is designed to automate the process of extracting audio from a video, transcribing the audio using OpenAI's Whisper model, generating AI-based audio from the transcription, adjusting the duration of the generated audio to match the original video, and finally replacing the original audio with the new AI-generated audio in the video.
Final Output of the video after AI Generated voice :