Feature Requests

Ability to sync modes, prompts, text replacements, vocabulary.

Create a custom iOS keyboard, so I can use superwhisper everywhere and without switching between apps and without copy-paste flow. Docs: https://developer.apple.com/documentation/uikit/keyboards_and_input/creating_a_custom_keyboard/

My main use case for superwhisper is to transcribe meetings using window recording. While the output is already very useful, it would be even better if the result would be split by speaker. This could be a per-profile configuration, allowing separating a "dictation" use case from a "meeting transcript" use case. Optional follow-up idea: Allow identifying speakers at timestamps while the recording is ongoing to already tag the result with appropriate speaker names in the output.

It would be great to be able to add additional context (similar to the copy text before initiating) to recording's after the fact and include in the prompt. Potentially even prompting with a modal window after recording stops to make the process seamless.

It would be great to be able to chain Superwhisper with Apple Shortcuts. That would open up a whole new world of possible automation use cases.

Ability for user to pause the recording in case there is an interruption or further time is needed to contemplate while recording. It would also be nice to have a keyboard shortcut for this to quickly pause and start recording as needed.

Currently, the recording history will grow without limit unless you click to delete them one at a time or delete using Finder. Add a feature, enabled by default, to limit the recording history to N days.

If I recorded, I can "reprocess" but I would like to change settings. Typical use cases are: I recorded in the wrong category (meetings instead of notes) the app crashed, I want to re-run with a different settings/models not happy with the results, I want to re-prompt / change the models

I believe this is due to the fact that the superwhisper app is not in focus, and I think that the application doesn't catch the keyboard.

I test modes quite a bit and would love to be able to duplicate a mode, especially with the prompt and examples included so I can easily replicate a mode and not have to copy over all of the prompts and examples. Until we can sync these across devices it would also be nice to be able to simply export a mode to JSON or something so it can be imported on another machine. Maybe even just a complete export of everything to make it easy to keep things in sync.