The demo video raised a lot of questions for me... one was which model was being used for the transcription, how the audio is being stored, and if there was any potential for offloading the recordings after transcription for storage capacity controls?
Parts of the site are confusing too... "Models picked for your Mac
Whisper in 99 languages, and a summary model that fits your Mac's memory."
You mention 'Whisper', but then the screenshot shows two qwen models, gemma, and granite.
Seeing that it's opensource, I'll look into contributing!
Great looking app, simple design.
The demo video raised a lot of questions for me... one was which model was being used for the transcription, how the audio is being stored, and if there was any potential for offloading the recordings after transcription for storage capacity controls?
Parts of the site are confusing too... "Models picked for your Mac Whisper in 99 languages, and a summary model that fits your Mac's memory." You mention 'Whisper', but then the screenshot shows two qwen models, gemma, and granite.
Seeing that it's opensource, I'll look into contributing!