This project implements a talking assistant that utilizes advanced AI capabilities for speech-to-text and text-to-speech functionalities. The application allows users to interact using their voice, processes the input through Groq AI, and responds audibly using Deepgram's text-to-speech technology.
- Groq API: Leveraged for AI-driven chat completions, making use of the powerful Llama3-70b model.
- Deepgram: Utilized for converting text responses back into speech, providing a seamless conversational experience.
- Streamlit: Serves as the frontend framework to create an interactive web application.
- Bokeh: Used within Streamlit to manage interactive elements, such as buttons that trigger speech recognition.
- Python: The core programming language used for the backend processing.
app.py
: Main application file that initializes the Streamlit interface, handles speech-to-text functionality, integrates Groq AI for processing user input, and utilizes the text-to-speech capabilities of Deepgram.groq_ai.py
: Defines thegenerate_response
function which interacts with the Groq API to convert user speech input into text and process it through an AI model to generate a response.TTS.py
: Handles the text-to-speech conversion using Deepgram's API, turning the AI-generated text responses into audible speech.
- Clone the repository:
git clone [repository-url]
- Install required dependencies:
pip install -r requirements.txt
- Set up environment variables:
- GROQ_API_KEY: Your Groq API key.
- DG_API_KEY: Your Deepgram API key.
To run the application, execute the following command in your terminal:
streamlit run app_s.py
- LIAICHI MUSTAPHA
Feel free to contribute to this project by submitting issues or creating pull requests.