The Transcriber

D'Studios

In-app purchases

About this app

Important: This application is currently optimized to transcribe English audio only.

The Transcriber is an offline audio transcriber that works straight out of the box. No additional downloads needed once the application is installed.

Features :

- Uses offline speech recognition to transcribe incoming audio, even while running in the background.

- Transcribe the audio from your device's microphone or the internal audio from compatible apps.

- Transcribe media files present on device.

- Export and share your recorded audio or transcribed text.

- Seamless playback and easy editing of all your recorded transcripts.

Permissions :

Microphone - Used to access the device's microphone to transcribe detected audio.

Notifications - This enables the application to display notifications with real-time transcription content along with a pause/resume button.

Premium Features :

Support the developer for just 0.99c USD/month, and you can customize the look and feel of the app to match your style. Change the color of eligible icons, backgrounds, and text to any color of your choosing.

- Use precision RGB sliders or paste in your favorite Hex codes for the perfect shade.

- Experiment without fear! The emergency reset gesture ensures you can always get back to the classic design in seconds.

- Find the exact element you want to style using the Advanced Color Search.

Frequently Asked Questions :

Why can't the application transcribe music?

The current AI model is optimized specifically for clear human speech. While it excels at transcribing conversations, meetings, and voice notes, it can struggle to isolate lyrics when there is heavy background noise or overlapping instruments, such as in a full musical track. Research and testing are already in progress to integrate more advanced models in future updates, bringing better performance to richer, more complex audio environments.

What does it mean to transcribe Internal Audio?

Internal audio in this context refers to the audio data generated by various software applications on the device, such as music players, video players, games or system sounds. To transcribe that internal audio would mean to determine whether the application generating the audio allows that data to be accessed, if the audio data is allowed to be accessed it would then need to be processed to determine whether any speech is present. Finally, if speech is present, it is converted to text.

What file formats are supported for transcription?

The application supports almost any standard media file present on your device, including both audio and video recordings. Below is a list of the most common formats supported:

Audio: .mp3, .wav, .m4a, .aac, .flac, .ogg, .opus, .amr, .wma
Video: .mp4, .mov, .wmv, .avi, .mkv, .webm, .flv

Will the application support languages other than English?

At the moment, the application transcribes speech to text exclusively in English. The developer understands the need for multilingual support therefore support for other languages is planned for the near future.

Feedback:

Please feel free to send any comments or suggestions at

[e-mail]

Or follow the developer on Twitter @dstudiosappdev

What’s new

- Added Premium Subscription Feature Full UI Color Control that allows users to change icon colors, backgrounds and text styles on eligible pages of the app.
- Improved UI.
- Fixed an error where the file transcription loading bar would not change when processing a file with no sound.
- Adjusted the animation speed when scrolling to the next transcript paragraph during playback.
- Fixed a bug where the Transcript Screen would go blank after searching for a keyword.