So, I made a notetaker that runs the ASR model on-device.

- Free with local ASR & LLM models

- No transcription time limit

- High accuracy for non-english speech, support for 100 languages

- Real-time transcription

- Zoom/Google Meet support

- No internet needed

- Efficient battery usage (~6 hours on full charge on my M2 Pro)

This started as a small cli tool I made for myself, then many of my uni friends really liked it, so here it is as an app!

I hope a lot of people can use this in their classes or meetings to help with their work.

During the development process, I also made the fastest streaming ASR pipeline on Apple Silicon. You can see it here: https://github.com/altalt-org/Lightning-SimulWhisper