https://github.com/azkasahar/ai-voice-assistant
A local llm powered AI voice assistant
https://github.com/azkasahar/ai-voice-assistant
Last synced: 10 months ago
JSON representation
A local llm powered AI voice assistant
- Host: GitHub
- URL: https://github.com/azkasahar/ai-voice-assistant
- Owner: AzkaSahar
- Created: 2025-08-05T07:03:53.000Z (11 months ago)
- Default Branch: main
- Last Pushed: 2025-08-05T07:13:05.000Z (11 months ago)
- Last Synced: 2025-08-05T09:24:11.458Z (11 months ago)
- Language: Python
- Size: 1.95 KB
- Stars: 0
- Watchers: 0
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# 🗣️ AI Voice Assistant with LangChain + Ollama
A simple voice assistant that listens to your speech, converts it to text, queries a local LLM using LangChain, and speaks the response back using TTS.
---
## 🎯 Features
- 🎤 Speech-to-text using `SpeechRecognition` + microphone
- 🤖 Local LLM querying via `langchain-ollama` (Mistral model)
- 🧠 Maintains chat history using LangChain memory
- 🔊 Text-to-speech using `pyttsx3`
- 🖥️ UI powered by Streamlit
---
## 📦 Installation
### 1. Clone the repo
```bash
git clone https://github.com/AzkaSahar/AI-Voice-Assistant.git
cd AI-Voice-Assistant
````
### 2. Install dependencies
```bash
pip install -r requirements.txt
```
> ⚠️ You may need to install `pyaudio` manually:
>
> ```bash
> pip install pipwin
> pipwin install pyaudio
> ```
---
## 🚀 Usage
### 1. Start Ollama (if not already running)
Make sure Ollama is installed and the `mistral` model is available:
```bash
ollama run mistral
```
### 2. Run the Streamlit app
```bash
streamlit run ai_voice_Assistant.py
```
---
## 🧠 How It Works
* Listens to user voice input
* Transcribes using `SpeechRecognition`
* Passes query and history to LangChain-powered Mistral model via `langchain-ollama`
* Speaks response using `pyttsx3`
* Maintains a visible chat history
---
## 📝 License
MIT – Free to use, modify, and share.