Prakash Joshi Pax
Prakash Joshi Pax
I'm not currently working on this, but I'd be happy if anyone would like to contribute! @Mgajurel @maelp
No, there's no such addition recently. And it shouldn't be using so much resources. Does quitting VoiceInk reduces the memory usage by `com.apple.cmio.registerassistantservice`?
Can you install it again [using this link](https://github.com/Beingpax/VoiceInk/releases/download/v1.61/VoiceInk.dmg) and update the app
You can pair it up with the AI provider that you can choose from the enhancement settings. Adding support for a custom model within the app itself will not be...
Can you tell me exactly what happens or how to reproduce this issue?
Should be better now.
The thinking model was too slow to respond, taking around 5 to 7 seconds. So, to prevent user confusion, I removed it.
Also the output format doesn't enclose inside think tokens properly messing with our thinking token filter.
You can already do this, there is a retranscribe button in the transcript history itself. Just change the selected model from the menu bar or from the UI itself and...
VoiceInk currently uses a [keyboard shortcuts package](https://github.com/sindresorhus/KeyboardShortcuts), as you said for custom keyboard shortcuts, which does not allow this. You can raise an issue over their GitHub.