This repository contains a real-time speech recognition system powered by Groq and ElevenLabs. It listens for audio input π§, processes it using an AI personality π€, and responds via speech synthesis ποΈ.
- π οΈ Custom Trigger Word: Set your own trigger word for AI activation.
- π§ AI Personality: Customize the AI's personality and response style.
- π Speech Synthesis: Uses ElevenLabs API to convert text responses into speech.
-
π₯ Clone the Repository:
https://github.com/official-alex/AI-Assistant.git cd AI-Assistant
-
π¦ Install Dependencies: Ensure Python 3.8+ is installed, then run:
pip install -r requirements.txt
-
π Set Up Environment Variables: Edit the
.env
file in the project root and add the following: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 π.
- For the ElevenLabs API key, log in to ElevenLabs, click your profile (bottom left), and navigate to "API Keys" π.
-
βΆοΈ Run the Application: Start the live speech recognition system with:python main.py
-
βοΈ Modify AI Personality & Trigger Word: Change the
trigger_word
andpersonality
in theLiveSpeechRecognition
class to customize how the AI interacts with you.
βΆοΈ Start Listening: The system will start listening for your input.- π£οΈ Trigger Word: Say the trigger word (default:
bob
) to activate AI processing. - π Stop: You can say "stop" to halt the recognition.
Upon termination, the system saves a transcript of recognized speech to transcription_history.txt
and logs any errors in error_log.txt
.