Whisprly

AI-powered speech-to-text that transcribes wherever your cursor is on your computer

Transform your voice into text instantly, anywhere on your screen ✨

• Real-time transcription - Press F1, speak, release, done!
• Lightning fast - Powered by Groq's Whisper v3 Turbo
• System-wide - Works in any application
• Customizable - Configure hotkeys and settings
• Windows optimized - Native Windows experience
• Lightweight - Minimal resource usage

Want to try it right now?

Download the latest release - Just download Whisprly.exe and run it!

1. Download the latest Whisprly.exe from releases
2. Get your API key from https://console.groq.com/keys
3. Run Whisprly.exe and enter your API key in settings
4. Start transcribing! Press F1 to record

# Clone the repository
git clone https://github.com/plfavreau/whisprly.git
cd whisprly

# Set up environment
uv venv
.venv\Scripts\activate  # Windows
# source .venv/bin/activate  # Linux/Mac

# Install dependencies
uv sync

# Configure
cp .env.example .env
# Add your GROQ_API_KEY to .env

# Run
python main.py

Want to create your own Whisprly.exe? It's super easy!

# Build the executable
uv run python build.py

Your new Whisprly.exe will be in the dist/ folder!

Pro tip: The transcription appears wherever your cursor is - works in any app!

Customize your experience by editing the .env file:

# API Configuration
GROQ_API_KEY=your_api_key_here

# Hotkey Settings
RECORD_KEY=f1
EXIT_KEY=ctrl+alt+x

# Audio Settings
SAMPLE_RATE=16000
CHANNELS=1

This project is licensed under the MIT License - see the LICENSE file for details.

• Groq provides the Whisper v3 Turbo API
• OpenAI provides the original Whisper model
• PyQt6 provides the python UI framework