Is it possible to copy text which is generated after we complete speaking without actually copying manually ?

[Greatz08]

Like If we use this program to transcribes speech successfully, is it possible to interact with it further in some way ? Maybe setting up a key combination that automatically copies the generated text or any function implemented in such a way that if we say particular word then it will auto copy last generated text. This would make tasks like searching, asking questions in chat apps, or performing other actions much easier. As i am lazy person :) It would be especially helpful for people like me, who can speak commands or use a shortcut to copy and paste text, rather than typing it out manually :-)

Btw thankyou very much for this great project. I can use it easily i believe if i set it with hyprland confs to trigger easily and if this thing which i am asking can be implemented then it will make things much better

[homelab-00]

I think some part of this has been implemented in the project, the maintainer will definitely have more in depth suggestions.

The only comment I want to make is that you might run into some issues on hyprland with copy-paste as Wayland still doesn't play very nice with clipboard. I think wl-copy and wl-paste will work better than portals for now.

Edit: For the specific functionality that you're looking for, take a look into KoljaB's other project called Linguflex.
From the README:

Check out Linguflex, the original project from which RealtimeSTT is spun off. It lets you control your environment by speaking and is one of the most capable and sophisticated open-source assistants currently available.

[KoljaB]

Yeah I also thought of Linguflex immediately. Yet this is a bit different. Linguflex switches between active listening and passive (waiting for wake words). Here we'd need to constantly transcribe and on wake word decide what to do. This is very resource intensive but also opens up some possibilities.

[Greatz08]

thanks for suggestions