Welcome to AI-Transcription! This app lets you stream audio from your browser, transcribe it in real time, and receive live translations. It utilizes powerful tools like OpenAI Whisper, DeepL, and HuggingFace pyannote. Our goal is to make your transcription and translation process simple and efficient. This application is modular, fast, and, importantly, open source.
Follow these steps to get started with AI-Transcription:
Check System Requirements
Download AI-Transcription Visit this page to download. Here, you will find the latest version of the software.
Install AI-Transcription
.exe
file..dmg
file../ai-transcription
to start the application.Launch the Application
Start Streaming and Transcribing
AI-Transcription uses advanced deep learning models to convert spoken words into text and then translates that text into your preferred language.
The application supports multiple languages. You'll find options during operation based on your settings.
Currently, the application requires an internet connection for transcription and translation services.
If you face issues, check the Troubleshooting section on our GitHub page or contact support for assistance.
We welcome contributions from the community! If you would like to help improve AI-Transcription, feel free to fork the repository and submit a pull request.
This project involves:
To start using AI-Transcription, visit this page to download the latest release. Follow the installation steps mentioned above, and you're ready to begin transcribing and translating audio live.
Feel free to reach out if you have any questions or need support!