the only guy i have doing dictation into a pc (and not into a special system like for medical records) regularly uses dragon on windows using a somewhat expensive microphone, a setup he’s had for probably 30 years. he has one of those old-timey radio host voices, that might help some… but i rarely ever see him having to edit what dragon spits out

I’ve recently read this super interesting and in depth blogpost about this topic:

https://nocoffei.com/?p=451

I used Speed of Sound for a bit on desktop linux and after triggering the global shortcut it pastes the text where you have your cursor. You can use cloud models, local network hosted models or just download whisper/parakeet directly in the app. Worked great for me so far.

If you want to try something else on your phone you can try Outspoke.

https://handy.computer/

A quick question, what accent do you have? As an Aussie I have real trouble speaking naturally with most speech to text software, open or closed source. I feel like the guys in that Scottish sketch show in the voice activated elevator. I sometimes use voice dictation for my notes for work and I spend almost as much time correcting as I do speaking.

That said, I have found a perfect solution. I can get well over the 95% correct mark by simply using an English or American accent. I can do both fairly well and the speech to text has no complaints. I imagine someone from Boston would have a tonne of trouble being understood, as would a Welsh person, but pretending to be a Californian or similar can help immensely.

I would love to find something that can be trained by my speech like Dragon Naturally Speaking used to be. I used that in the early 2000s and at first it was awful, but training it for a few hours really did offer a noticeable improvement, and ongoing use continued to improve further. My computer died and I lost all the trained data, so I never went back, but if I could I would definitely do that again.

I’ve started my own foray into push-to-talk and speech-to-text recently. I opted for faster-whisper since I wanted a lighter, local approach. It might be more DIY than what you’re looking for, but I just wanted to chime in since it’s fresh on my mind.

So sorry about your finger pain. I don’t know if this can be self-hosted, but https://github.com/jatinkrmalik/vocalinux has been pretty incredible.

I was recently reading about Talon Voice, which sounded quite interesting with lots of usability hacks. Unfortunately, not an option anymore if you are a Linux user: https://www.osnews.com/story/145162/accessibility-input-tool-removes-x11-support-doesnt-want-to-support-wayland-users-caught-in-the-middle/

I can’t contribute much. Futo Keyboard is nice for android. Speech Note is a tool for linux that I use from time to time… It is a bit slow without GPU acceleration and the resulting text are about 95% correct.

Have you read this comparison? https://openwhispr.com/blog/best-dictation-tools-linux-2026… It smells a bit like advertising for openwhispr but contains some pointers.

https://m.youtube.com/watch?v=5d_jGOGRSMc&t=16m55s. After a while of talking he mentions KDE connect remote input which could be used with futo keyboard dictation, I guess?