Whisperian is a voice dictation tool made for developers, project managers, writers, and anyone who doesn't like typing and wants to bring their advanced speech-to-text workflows to their Android devices.
The app integrates with the Android system either as a voice keyboard or as a compact, system-wide overlay that stays out of the way when you don’t need it.
Whisperian includes most of the features you’d expect from modern dictation tools, as seen in apps like Superwhisper, as long as they fit the app’s philosophy: avoiding putting limitations on user freedom.
The app's goal is to provide basic building blocks necessary for creating advanced workflows (e.g., custom command modes).
We will exclusively focus on improving the dictation experience instead of trying to duplicate functionality better handled by dedicated apps (e.g., note-taking).
Dictation settings are mostly managed through profiles. Each profile allows you to configure the transcription and post-processing provider/model, language, custom prompts, and text replacement rules.
The app includes continuously evolving default configurations that are ready to use out of the box but can also serve as a starting reference point for experimentation.
The app is currently in early access, and we are offering all the features for free during this period.
The only way to use the app is by providing your own API keys for the services you want to use for processing.
There is no sign-up required, and there are no cloud features yet.
To make the system-wide integration possible, Whisperian uses an Accessibility service to show the system-wide overlay. The accessibility service is used to detect when the keyboard is visible to show or hide the overlay, start the recording session on user action, and read the active text field and cursor position to insert text. It also is used to identify input field types to avoid appearing for fields where dictation doesn't make sense, like password or number fields.
No data accessed via this service is stored or shared.