Hello Transcribe 4+

Pretty good

Fundamentally, this is a pretty good implementation of Whisper on iOS. For longer transcriptions, it appears to just chunk the audio into 30 second segments, which can degrade the quality of the transcription, including unexpected line breaks and words that overlap two chunks not being great. I wish there were a few more options. One simple one would be a one-click button that allows you to re-process a finished transcription as a single complete audio file. Alternatively, I would like to set it up so that the real time preview is done using one model of my choice (maybe tiny, maybe base), and then after the transcription is complete, it would automatically process the complete audio with another model of my choice (maybe small or medium).

I go back and forth between this one and WhisperBoard. They’re both good in their own ways, but transcription quality is critical, so I rate WhisperBoard higher since it doesn’t seem to suffer the same oddities that are the result of Hello Transcribe attempting to do real-time transcription.

Convenient, although text saving could be better

I really do enjoy the convenience of this app, as I was previously recording voice clips and then manually processing them through the Whisper local model on my PC - this is much faster.

I do have one complaint though - it’s very easy to lose your transcribed text once you’re finished recording. I’ve created an iOS shortcut to pipe my text into ChatGPT to turn it into markdown-formatted documentation, and the dictation controls are confusing enough that it’s easy to accidentally discard five minutes worth of dictated notes. Could you possibly add an option to automatically save dictated text, and view those files later? That would make this app 5 stars to me.

Developer Response ,

Hi
Sorry about the data loss, and yes this is in the pipeline. I'm going to rework the data handling soon and will save intermediate transcriptions locally. This may require an upgrade to iOS 17 when it is released because I want to use the new SwiftData frameworks.
Regards
Ben

Almost perfect

I’ve been waiting too long for apple to bring AI to voice memos but they haven’t done anything about it yet. I like that it uses whisper locally but would also have the option to just record audio and then let it transcribe overnight when I’m not using the phone (this could also enable us to use larger models since the transcription doesn’t need to be real-time); this in turn should allow me to search later through my recordings and when I tap on a word from the search result it should move the audio player cursor to that position, please implement something like this! Thanks, it’s almost there

Developer Response ,

Thanks for the support! On iOS it's not possible to run transcriptions in the background because of restrictions from Apple, so unfortunately you can only run those workflows on the Mac.

The next major version will have the cursor as you describe! With searchable text.