Transcripty is a voice recorder application that allows users to record audio and transcribe it into text. Built with Python using the Flet framework, it provides a simple and user-friendly interface for audio recording and transcription.
- Record audio from selected devices
- Transcribe recorded audio using Whisper
- Toggle between light and dark themes
- Save recordings as WAV files
- Python 3.11.10 or higher
- Internet connection for model downloading
git clone https://github.com/Abdulkhale-1/transcripty.git
cd transcriptyYou can use uv to install the required dependencies. Make sure to create a virtual environment for better package management.
pip install uv
uv venv .venv
uv syncTo start the Transcripty application, use the following command:
uv run main- Select an audio recording device from the dropdown menu.
- Click on the "Tap to Record" button to start recording. The button label will change to "Recording...".
- Click the button again to stop the recording. The audio will be saved automatically.
- The application will automatically transcribe the recorded audio, and the result will be displayed on the screen.
- Use the theme toggle switch to switch between light and dark modes.
If you would like to contribute to the Transcripty project, please follow these steps:
- Fork the repository.
- Create a new branch for your feature or bug fix.
- Make your changes and commit them with descriptive messages.
- Push your branch to your fork.
- Create a pull request explaining your changes.
This project is licensed under the MIT License. See the LICENSE file for more details.
- Flet - A framework for building interactive web apps in Python
- OpenAI Whisper - A speech recognition model
- PvRecorder - A simple audio recorder for Python
For any questions or inquiries, please contact me at abdulkhalek.muhammad.work@gmail.com.