This project is a daemon that continuously scans a folder on the system for audio files to transcribe into text files. It currently only has a cli so that it can be run the same on a desktop or a headless server.

As of now the projects sit on top of IBM Speech to Text, but the plan is to eventually add support for both Google and Mozilla's Speech to Text engines.

If you run into any issues or have any ideas that you think would make the transcriber better, please send me an email.