Groq Whisperer is a Python-based application that allows users to record audio and transcribe it to text using Groq's Whisper implementation. The transcribed text is automatically copied to the clipboard for easy pasting into other applications.
- Record audio by holding down the PAUSE key
- Transcribe recorded audio to text using Groq's API
- Automatically copy transcription to clipboard
- Continuous operation for multiple recordings
- Python 3.7 or higher
- A Groq API key (set as an environment variable)
-
Clone the repository:
git clone https://github.com/KennyVaneetvelde/groq_whisperer cd whisperer -
Create a virtual environment:
python -m venv venv -
Activate the virtual environment:
- On Windows:
venv\Scripts\activate - On macOS and Linux:
source venv/bin/activate
- On Windows:
-
Install the required packages:
pip install -r requirements.txt -
Set up your Groq API key as an environment variable:
- On Windows:
setx GROQ_API_KEY "your-api-key-here" - On macOS and Linux:
export GROQ_API_KEY="your-api-key-here"
- On Windows:
-
Run the script:
python main.py -
Press and hold the PAUSE key to start recording.
-
Release the PAUSE key to stop recording and start transcription.
-
The transcribed text will be automatically copied to your clipboard.
-
Repeat steps 2-4 for additional recordings.
The project relies on the following main libraries:
pyaudio: For audio recordingkeyboard: For detecting key pressespyautoguiandpyperclip: For clipboard operationsgroq: For interacting with the Groq API
For a complete list of dependencies, see the requirements.txt file.
- Make sure your microphone is properly configured and working before running the script.
- The transcription quality may vary depending on the audio quality and background noise.
- Ensure you have a stable internet connection for the transcription process.