What’s new
Every release, newest first, in the words the App Store and Google Play show. Generated from the release notes that ship with each build.
1.2.6 · 2026-10-28
iPhone Duo: HarkNote adapts as you fold and unfold. The session you have open, and the save confirmation after a recording, stay on screen as the display changes.
Wide screens: unfolded on iPhone Duo, or on iPad, the recording screen shows its controls beside the live preview, and Ask keeps the transcript beside the conversation.
1.2.5 · 2026-10-18
Find Recordings: bring in recordings you already have. Tap FIND on Sessions, or long-press the HarkNote icon and choose Import Recordings. Pick as many audio files as you like from Files or iCloud Drive, or share them from Voice Memos. They transcribe on your device like any other session, and nothing is uploaded.
Sharing several recordings to HarkNote at once now imports every one of them, not just the first.
1.2.4 · 2026-10-02
Naming other people's voices from saved profiles is now off by default. Turn it on under Config, Speaker Detection, Name known voices; a short note explains what it does first. Your own Self voice is matched either way.
1.2.3 · 2026-09-23
Auto-export: choose a folder under Config and every finished transcript and summary is written there as a text file, on its own. Same content as Share, without the share sheet. Off by default.
Every card in Config now collapses, with its current setting in the subtitle.
1.2.2 · 2026-09-21
Transcribe a finished recording again with a different model from the session menu, as long as the audio is still on your iPhone.
Summaries say plainly when no summarizer model is available.
Conversations transcribed with Parakeet now separate into speaker turns, even when people answer each other without pausing.
1.2.1 · 2026-09-09
Speaker labels now finish for hour-plus meetings, and a recording interrupted mid-way picks up where it left off instead of starting over.
The speaker-labels card shows elapsed time, an estimate, and which section it is working on.
1.2.0 · 2026-09-08
Apple Watch: record on your wrist and hand the audio to your iPhone for on-device transcription, with an optional live preview while you record.
Choose which microphone records, and refuse one you don't want.
The interface now ships in English, German, Spanish, French, Italian, Dutch, and Portuguese.
Changing the theme keeps your place in Settings; search dismisses the keyboard on return.
A recording with no speech says so instead of guessing.
Privacy policy v7 describes both transcription engines, Apple Foundation Models, and the Watch companion.
1.0.12 · 2026-10-28
Foldables and tablets: on a Galaxy Z Fold, a Pixel Fold or a tablet, the recording screen shows its controls beside the live preview, and Ask keeps the transcript beside the conversation.
1.0.11 · 2026-10-18
Find recordings: HarkNote can now find the voice recordings already on your phone, like Voice Recorder clips, call recordings and voice notes. Tap FIND RECORDINGS on Sessions, or long-press the HarkNote icon and choose Import Recordings, tick the ones you want, and they transcribe on your phone like any other session. Nothing is uploaded. Can't see one? Browse your files from the same screen.
1.0.10 · 2026-09-25
Naming other people's voices from saved profiles is now off by default. Turn it on under Config, Speakers, Name known voices; a short note explains what it does first. Your own Self voice is matched either way.
1.0.9 · 2026-09-23
Auto-export: pick a folder under Config and every finished transcript and summary is written there as a text file, on its own. Same content as Share, without the share sheet. Off by default.
1.0.8 · 2026-09-21
Updated the libraries that store your recordings and run background transcription. Nothing looks different; this is upkeep.
1.0.7 · 2026-09-09
Transcribe a finished recording again with a different model from the session menu, as long as the audio is still on the phone.
1.0.6 · 2026-09-09
Transcription now uses Parakeet v3 by default: far more accurate than Whisper tiny, seven languages, still fully on-device.
Summaries say plainly when no summarizer model is installed.
1.0.5 · 2026-09-09
Speaker labels are about 2.5 times faster: the speaker model now uses the same processor cores as transcription.
Speaker labels finish for hour-plus meetings, and an interrupted recording picks up where it left off.
The speaker-labels card shows elapsed time, an estimate, and which section it is working on.
1.0.4 · 2026-09-09
Speaker labels now finish for hour-plus meetings, and a recording interrupted mid-way picks up where it left off instead of starting over.
The speaker-labels card shows elapsed time, an estimate, and which section it is working on.
1.0.3 · 2026-09-08
Recovers interrupted recordings automatically after the app is closed mid-capture, on phone and Wear OS.
Clearer privacy disclosures and consent that reads correctly in landscape.
Voice enrollment cleans up its temporary sample reliably.