Starts when your call does
A small prompt offers to record. One click.
Every call transcribed on your Mac, with every speaker named. No bot joins. Nothing gets uploaded.
Coming soon for Mac, iPhone & iPad
See how it worksNo bot in your call
No upload to the cloud
No notes to take
TalkKeep records what your Mac hears: your mic and the meeting’s sound. No extra guest, no invite, no plug-in.
Every voice is told apart on your Mac, then named: straight from Zoom, Slack, Meet, or Tencent Meeting, or once by you, then remembered.
Switch between English and Chinese mid-sentence. TalkKeep keeps both, with real punctuation, in readable paragraphs.
Search every meeting at once, then click a line to play it from exactly there.
A small prompt offers to record. One click.
In the app or in the browser.
Speaker echo is removed from your mic.
What you say on mute is left out.
Saved every minute, even through a crash.
Titled by the app and the people in it.
Markdown, text, subtitles, or the audio.
Recording, transcription, and speaker recognition all run on your device.
Record the meeting in the room on iPhone or iPad, transcribed right on the device. Every meeting, from any of them, is on all of them.
Nothing appears on their side, because TalkKeep doesn’t join the call. Recording laws vary, so tell people when you record; TalkKeep reminds you before your first recording.
No. TalkKeep only goes online to download its speech models once, and to sync through end-to-end encrypted iCloud if you turn that on.
Nearly a hundred, through Whisper large-v3, including meetings that switch between two of them.
Same app. The website version can also read names and mute state from your meeting app, which the App Store doesn’t allow.
macOS 26 or later, or iOS and iPadOS 26 or later. The speech models are a one-time 1.6 GB download on the Mac.
Coming soon for Mac, iPhone & iPad