This project provides a simple interface to transcribe audio from YouTube videos using the Whisper model and optionally through OpenAI's API.
- Transcribe audio from YouTube videos by providing the video URL.
- Alternatively, upload an audio file directly for transcription.
- Supports video input for transcription as well.
- moviepy
- gradio
- whisper
- pytube
- openai
- Run the script.
- Choose between providing a YouTube video URL, uploading an audio file, or providing a video file.
- Get the transcription output in text format.
- To use the OpenAI API for transcription, ensure you have appropriate account credentials and uncomment the relevant code section.
- You may need to install additional dependencies not listed here.