Hello Transcribe 2.1
Hello Transcribe 2.1 is now on the App Store.
- Shortcuts for dictate and transcribe from file.
- Once-off Pro purchase as an alternative to subscriptions.
- Pause, resume and clear dictation.
- Scroll lock - the result will automatically scroll to the latest segment.
- Document picker - you can now select audio document directly from the app.
- Remove non-speech phrases like [Applause] from the result (Pro only).
- Change the transcription font size, which is useful when using the app for live dictation (Pro only).
- Less cluttered and simplified UI.
- Raw audio is not saved (this lead to the app crashing when saving large transcriptions).
This works but is experimental. I’m still on the learning curve with shortcuts so please let me know what improvements and changes you would like to see.
I’ve created two shortcuts:
- Dictate with Hello Transcribe.
- Transcribe file with Hello Transcribe.
Both of these will launch the app, but I’ll work on better UI support for shortcuts. I think I can add a minimal UI like a widget for both workflows so the shortcut doesn’t launch the app.
Now you can do something like this — create a shortcut to automatically create a Reminder (or Note etc.) with dictation:
When you launch it and tap the stop button it will automatically create a reminder:
Or you can create a shortcut which will create a reminder (or Note etc.) from a file:
Both shortcuts have the option to discard the result so it’s not saved.
This is only the beginning of shortcuts, if you have workflows that could benefit please send them to me so I can add support.
I launched two payment options last month, a subscription or a consumable “minutes” option.
I have removed the “minutes” option. Only 3 people bought it and it doesn’t fit in with adding “Pro” features. If you are one of the 3 people who bought minutes for $1 and want a refund or discount please contact me!
Several users asked that I add a once-off Pro purchase. I’ve added that now for $6.99. The subscription option remains $1.99. The app doesn’t have any ongoing server costs so a single purchase makes sense.
The Settings page has been updated with the new Pro options to make it clearer:
The new Pro options are discussed in section 7, and the Pro models remain the same. I’ve added “Fast”, “Balanced” and “Accurate” labels for users who were confused by the Whisper model names.
Dictate Pause/Resume and Clear
When dictating you can now pause/resume the dictation and clear the current result while dictation is on progress:
While transcribing the app will automatically scroll to the last transcription segment so you don’t have to keep swiping to see the last result:
You can turn this off by tapping the “lock” icon in the toolbar.
You can now open an audio file from the app using the Document Picker:
There are two new “Pro” options:
- “Strip non-speech phrases”. Sometimes Whisper will add phrases like [Applause] or [Music Playing] the the output. This option will remove those phrases.
- Font size: The output of the transcription can be set. This is useful in the scenario where someone is using the Dictation feature to transcribe someone else’s speech.
- Previously the app stored the raw audio with Core Data for future use. This created an out-of-memory issue when saving large transcriptions which could lead to the app crashing. Raw audio is not stored any more which removes this issue.
- The UI has been decluttered and simplified. It uses the standard iOS toolbars. It’s also less rainbow-y. If this app ever makes any money I’ll hire a graphic designer to design a nice UI.
- New swipe to delete gesture.
Next for 2.2
As mentioned before I will create smaller, more frequent releases from now on.
For 2.2 I plan on:
- Reviewing the use of Whisper.cpp for better performance.
- Rebuild the transcription service to better handle Shortcuts.
- Lazy load of the model when required to save resources.
- Better Shortcuts.
So it will be mostly behind-the-scenes changes.
Try it out, let me know if you have requests, issues or improvements!