The OpenAI Whisper Transcription Tool is a Python application that leverages the OpenAI Whisper API to transcribe audio files. This tool allows you to specify the language, choose whether to generate a timeline, and then initiate the transcription process.
Before using this tool, ensure you have completed the following steps:
- Register for an OpenAI account and obtain an API key.
-
Clone the repository:
git clone https://github.com/JerryR7/OpenAI-Whisper-Transcription-Tool.git
-
Configure the API key: Open the
transcribe.pyfile and provide your OpenAI API key in theopenai.api_keyvariable. -
If you have the pre-built executable version:
- Navigate to the
distfolder. - Run the executable program to start the transcription tool.
cd dist ./transcribe (or transcribe.exe on Windows)Follow the on-screen prompts to select the audio file, choose the language, and decide whether to generate a timeline for transcription.
- Navigate to the
-
If you want to run the tool from source:
-
Run the transcription tool:
python transcribe.py
Follow the on-screen prompts to select the audio file, choose the language, and decide whether to generate a timeline for transcription.
-
-
The transcription result will be displayed in the console.
This code is licensed under the MIT License. See the LICENSE file for details.
If you encounter any issues or wish to improve this tool, feel free to submit issues or send pull requests. We welcome your contributions!
If you have any questions or need assistance, please don't hesitate to contact us.
Special thanks to OpenAI for providing a powerful speech transcription API.
We hope this tool helps you transcribe audio files efficiently using OpenAI Whisper. Feel free to customize and extend the code to suit your specific requirements.