I'm looking for an offline speech recognition software for Linux which can handle also German language and which is easy to use and configure.

I already tried CMU Sphinx and a few more others, but all of them had one in common: they have been way too complicated to install/use, mainly because of lack of a good manual and also because of a very crude concept (I try to avoid the word "usability" in this context).

So...is there a speech recognition software out there which can be set-up and configured in finite time, is able to execute scripts on recognised commands and works fully offline, means does not need a cloud service or remote server to analyse spoken words? I'm also willing to pay money for a working and usable solution!

Every hint and idea is welcome!


PS: I'm aware of the thread Is there any decent speech recognition software for Linux? - but the answers given there do NOT point to offline solutions!


It's worth keeping an eye on what Michael Sheldon is doing: http://blog.mikeasoft.com/2017/12/30/speech-recognition-mozillas-deepspeech-gstreamer-and-ibus/

Caveat: it is not yet of any practical use, in my opinion. BUT... after struggling and struggling to configure things I was eventually able to get recognition of spoken words (in English... I have no idea about German).

Mike Sheldon is using the DeepSpeech model from Mozilla, which sounds good.

The comments on that page (my comment no. 100 was when I managed to get some speech recognition) seem to have stopped in July 2018. I have no idea whether he's still working on it.


Try nerd-dictation (demo video).

I ran into the same problem and ended up writing my own tool, while it has some opinionated decisions I find it generally works well for basic dictation needs (based on the excellent VOSK-API).

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.