This is a hobby project that aims to provide an easy-to-use web app that takes audio input from the user, transcribes it, and gives a response based on the user's prompt. The transcription is done using whisper and the response is generated using GPT accessed through OpenAI API. The GUI is built using Streamlit.
This app can be used for various purposes that require generating responses from spoken input. For example, use it to vocalize your thoughts and receive a summarized version. This application benefits individuals who find it challenging to articulate their thoughts in writing.
To use the app, follow these steps:
- Clone the repository to your local machine.
git clone https://github.com/kanishkbh/speech2text_summarization.git- Create a new conda environment and install the required dependencies.
cd speech2text_summarization
conda create -n speech2text_summarization
conda activate speech2text_summarization
pip install -r requirements.txt- Add your Open API key as environment variable.
export OPENAI_API_KEY=<your key>You can get your API key from here.
- Run the app:
streamlit run app.py. - Open your web browser and navigate to the URL displayed in the terminal (usually http://localhost:8501).
- The web app shows instructions to get started.
Enjoy!