This repository contains a Python application designed as a voice assistant using various libraries to handle speech-to-text, text-to-speech, and machine learning capabilities. It's built with the intention of demonstrating a basic interactive voice-based system.
- Text-to-Speech: Converts text to spoken voice responses.
- Speech Recognition: Listens and recognizes spoken words to text.
- Interaction with Offline Language Model: Sends recognized speech to an LM-Studio model for processing and receives a response.
Before you run the assistant, ensure you have the following installed:
LM-Studio, https://lmstudio.ai/
- Python 3.x
- pyttsx3
- sounddevice
- numpy
- vosk
- openai