Loading repository dataβ¦
Loading repository dataβ¦
Hazrat-Ali9 / repository
π Audio π Health π° Assistant π¨ is an π innovative π AI π powered π healthcare π assistant π that β΄ uses π speech β recognition πΌ natural π language πprocessing π« medical π intelligence π to enable π hands π€ free π voice π―based π« health π interactions π’
A transparent discovery signal based on current public GitHub metadata.
This score does not audit code, security, maintainers, documentation quality, or suitability. Verify the repository and its current documentation before adoption.
The Real-time Multilingual Audio Health Assistant is an intelligent voice-based application designed to assist users in managing their health. It integrates speech recognition, language detection, medical condition assessment, and real-time text-to-speech generation, providing a seamless, conversational experience for users.
This project is designed to detect symptoms based on user voice input and provide tailored advice in different languages. The assistant can also check common medical conditions and generate responses using the AIML API with an embedded AI model.
This assistant performs the following operations:
To run this application, you need to install the following Python packages:
streamlit==1.37.1speechrecognition==3.9.0gtts==2.2.3openai==0.27.0langdetect==1.0.9sounddevice==0.4.6numpy==1.23.5pydub==0.25.1ffmpeg-python==0.2.0A virtual environment helps manage project-specific dependencies and avoids conflicts with other Python projects. Follow these steps to create and use a virtual environment for this project:
Open a terminal or command prompt and navigate to your project directory. Run the following command to create a virtual environment named venv:
python -m venv venv
venv\Scripts\activate
pip install -r requirements.txt
streamlit run <filename>.py