A lightweight PyQt6 application that automatically displays real-time captions using speech-to-text technology.
Only Linux is supported at the moment.
Only gummy-realtime-v1 is supported at the moment. See Gummy实时语音识别、翻译Python SDK for details.
Set environment variables DASHSCOPE_API_KEY to your API key to use the model.
- Clone the repository.
- Use
uvto install dependencies:uv install
- Run the application:
python main.py