An iOS app for recording and transcribing audio on the go, based on OpenAI's Whisper model.
- Easy-to-use voice recording and playback
- Transcription of recorded audio using Whisper from OpenAI
- Import and export audio files
- Select microphone for recording
- Model selection screen with the ability to download any Whisper model
- Optimize the transcription process by eliminating silent portions of audio, which can reduce the processing time and improve overall efficiency.
- Implement resumable transcription so that users can continue transcribing after the app has been terminated during the transcription process.
- Enable background transcription when the app is minimized, allowing users to perform other tasks while the transcription proceeds.
- Improve visualization of the current state of the transcription process, providing users with a clearer understanding of its progress.
- Provide an estimated time remaining for the transcription to complete, helping users plan accordingly.
- Introduce a transcription queue that allows users to select multiple files for transcription, streamlining the process for bulk transcriptions.
- Implement real-time transcription using smaller, more efficient models, offering users faster results.
- Offer an additional remote transcription option to enhance user experience with larger models, potentially providing more accurate transcriptions or faster processing times.
- Clone this repository
- Run
make - Open the project in Xcode
This project is licensed under the GPL-3.0 license.
