This is a locally running audio transcription application. Select audio or video files for transcription, and the currently playing part is highlighted in real-time.
![]() |
![]() |
![]() |
- Load a media file (MP3, WAV, M4A, FLAC, MP4, MOV, etc.)
- Local transcription using Whisper-based models
- Controls for video and audio playback, pause, seek, etc.
- Video display within the video window
- Highlighting of the currently playing text segment
- Click on transcribed text to play from that position
- Save transcribed text feature
- Selection of transcription models based on needs
- macOS 14.6 or later
To run locally, execute the following command:
make install
If you edit localization files, execute the following command. This generates the L10n enum, making it accessible in the code.
make swiftgen
If you add external packages, execute the following command. This generates the license file.
make license
This app uses the following external libraries.


