This project is a privacy-first AI meeting assistant that captures meeting audio, produces real-time transcripts, and generates summaries while keeping processing entirely on your own machine or infrastructure. It’s built for organizations that want meeting intelligence without sending recordings or transcripts to third-party cloud services, which helps address compliance and data sovereignty requirements. The app supports live transcription with local model options (including Whisper- and Parakeet-based workflows) and presents the transcript as the meeting happens, making it useful both for note-taking and accessibility. After or during the session, it can produce structured, AI-generated summaries, and it’s designed to be flexible about where that summarization comes from, supporting local providers as well as external endpoints when allowed by policy.
Features
- Local-first processing so meeting data stays on your machine
- Real-time transcription with support for Whisper- and Parakeet-style model pipelines
- AI-generated meeting summaries with configurable provider options
- Offline-capable workflow to avoid mandatory cloud dependencies
- Multi-platform support across common desktop operating systems
- Self-hostable and modifiable codebase aimed at enterprise privacy and compliance needs