Skip to content

omegaduncan/Dictate

 
 

Repository files navigation

Dictate Keyboard (Whisper AI transcription)

切换到中文版

Get it on Google Play

Dictate is an easy-to-use keyboard for transcribing and dictating. The app uses OpenAI Whisper in the background, which supports extremely accurate results for many different languages with punctuation and custom AI rewording using GPT-4 Omni. Since a picture is worth a thousand words, here is a showcase video and some screenshots:

dictate_keyboard_notes_recording.png dictate_settings.png
dictate_settings_2.png dictate_prompts_overview.png dictate_prompts_edit.png

Recent Changes

  1. Improved network connectivity handling:
    • Added network availability check before API requests
    • Implemented retry mechanism for failed requests (max 3 attempts)
  2. Enhanced error handling and user feedback:
    • Added new error messages for network issues and max retries reached
    • Improved error logging for better debugging
  3. Upgraded dependencies:
    • Updated GitHub Actions workflow
    • Added OkHttp library for network requests
  4. Refactored network request logic:
    • Replaced Retrofit with OkHttp for more direct control over requests
    • Improved request and response handling

Installation

The app is available on Google Play (for a small fee to support me and the future development), so you get easy installation and free lifetime updates. Just click on the badge above or on this link.

License

Dictate is under the terms of the Apache 2.0 license, following all clarifications stated in the license file

About

A powerful Whisper AI keyboard for reliable speech transcription

Resources

License

Stars

Watchers

Forks

Packages

No packages published

Languages

  • Java 97.4%
  • HTML 2.6%