Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/official-alex/ai-assistant
A real-time speech recognition system powered by Groq and ElevenLabs, designed to listen for audio input, recognize speech, and respond with AI-driven dialogue. Customize the trigger word and personality for dynamic conversations. Includes speech synthesis for vocal replies and a live console interface with Rich library visuals.
https://github.com/official-alex/ai-assistant
ai assistant chatbot chatgpt groq speach-recognition
Last synced: 3 months ago
JSON representation
A real-time speech recognition system powered by Groq and ElevenLabs, designed to listen for audio input, recognize speech, and respond with AI-driven dialogue. Customize the trigger word and personality for dynamic conversations. Includes speech synthesis for vocal replies and a live console interface with Rich library visuals.
- Host: GitHub
- URL: https://github.com/official-alex/ai-assistant
- Owner: official-alex
- Created: 2024-10-21T17:41:26.000Z (3 months ago)
- Default Branch: main
- Last Pushed: 2024-10-21T18:51:28.000Z (3 months ago)
- Last Synced: 2024-10-22T11:10:50.617Z (3 months ago)
- Topics: ai, assistant, chatbot, chatgpt, groq, speach-recognition
- Language: Python
- Homepage:
- Size: 7.81 KB
- Stars: 3
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# 🎤 Speech Recognition AI Conversation System
This repository contains a real-time speech recognition system powered by [Groq](https://console.groq.com) and [ElevenLabs](https://elevenlabs.io). It listens for audio input 🎧, processes it using an AI personality 🤖, and responds via speech synthesis 🎙️.
---
### 🌟 **Features:**
- **🛠️ Custom Trigger Word:** Set your own trigger word for AI activation.
- **🧠 AI Personality:** Customize the AI's personality and response style.
- **🔊 Speech Synthesis:** Uses ElevenLabs API to convert text responses into speech.
---
## 🚀 **Setup Instructions**
1. **📥 Clone the Repository:**
```bash
https://github.com/official-alex/AI-Assistant.git
cd AI-Assistant
```
2. **📦 Install Dependencies:**
Ensure Python 3.8+ is installed, then run:
```bash
pip install -r requirements.txt
```
3. **🔑 Set Up Environment Variables:**
Edit the `.env` file in the project root and add the following:
```plaintext
GROQ_API_KEY=your_groq_api_key_here
ELEVENLABS_API_KEY=your_elevenlabs_api_key_here
```
- For the Groq API key, go to [Groq Console](https://console.groq.com/keys) 🔗.
- For the ElevenLabs API key, log in to [ElevenLabs](https://elevenlabs.io), click your profile (bottom left), and navigate to "API Keys" 🔑.
4. **▶️ Run the Application:**
Start the live speech recognition system with:
```bash
python main.py
```
5. **⚙️ Modify AI Personality & Trigger Word:**
Change the `trigger_word` and `personality` in the `LiveSpeechRecognition` class to customize how the AI interacts with you.
---
## 📝 **Usage**
- **▶️ Start Listening:** The system will start listening for your input.
- **🗣️ Trigger Word:** Say the trigger word (default: `bob`) to activate AI processing.
- **🛑 Stop:** You can say "stop" to halt the recognition.
---
### 💾 Save Transcriptions and Errors
Upon termination, the system saves a transcript of recognized speech to `transcription_history.txt` and logs any errors in `error_log.txt`.