I'm tracking them all here:
https://opensource.builders/alternatives/superwhisper
Just added Ghost Pepper, and you can actually create a skill.md with the features you need to build your own
https://opensource.builders/alternatives/superwhisper
Just added Ghost Pepper, and you can actually create a skill.md with the features you need to build your own
Wish they would do an ios version, but the creator already kind of dismissed it.
I didn't just dismiss for no reason, I am a human! I have needs and I can't just sleeplessly stay in front of the computer putting out code. If I had more time I would, but alas.
Someone could easily vibe code an iOS version in a few hours. I could do the same but I do not have time to support it.
https://apps.apple.com/us/app/voiceink-ai-dictation/id675143...
(I was searching the same as you before I found this last month)
It has all the usual features, plus you can add project specific vocabulary in your repo. It detects the working folder based on the active window, reads a WORDBIRD.md file in that folder and corrects terms accordingly.
(My friend Till built it)
1: livestream transcript directly into the cursor in real time (just like native macOS dictation)
2: show realtime transcript live in an overlay (still has to paste when done, unlike #1, but can still read live while dictating)
1- localvoxtral, 2- FluidVoice (bumping it to 7 features on your list)
I see promise trying to get a bit more into curating by showing the top one or two or three picks for a given standout feature.
Like telling it to edit the text or remove a word.
The cherry on top: it’s completely broken! Enable the Context Awareness filter, the list shrinks. Now enable the Auto-pasting filter, the list grows back.
The categories are clearly LLM generated from the GhostPepper codebase, with vague low level descriptions and links to code. Most categories apply to every listed project.
The UI is the same tiny bit of LLM generated information displayed five different confusing ways. Like seriously, click on a project and you first see a bunch of haphazard feature cards, then a bunch of “feature ... active” rows. Looks fancy, but actually just noise. Textbook slop.
Better would be a simple awesome-style markdown page, with a feature matrix having categories and descriptions curated by a human that actually understands and cares about the domain.
Sorry if this is harsh, but passing off LLM output as “curation” is particularly insulting to me.