In-Meeting Notetaker.
On-Device Audio. One Shortcut.
- ✦ Every speaker identified — 99% accurate, recognized next meeting from a voiceprint that stays on your Mac benchmark
- ✦ No bot joins the call — captured at the OS level, so nothing appears in the participant list
- ✦ Action items and summaries — refined as you talk, through the default proxy or an endpoint you choose
- ✦ Keyboard-first — reachable from any app, no hunting through windows mid-meeting
Free meeting recordings and summaries. No credit card or email needed.
Apple Silicon · GDPR & CCPA · Fit it to your company's data policy →
💬Dana cut Sam off before he finished—circle back to his process
Summary
Notes While You Talk
Action items and a summary build during the call, so you can check what’s been agreed before it ends.
Action items that stay put
A reworded promise updates its item instead of adding a second one, and items stay listed for the whole call.
Updates in under a second
Each refresh of the summary and action items takes under a second on average.
Every Speaker Identified
Speaker changes show up live as people take turns. When the call ends, a full pass over the meeting settles who said what.
Most notetakers send a bot into your call to do this. MimicScribe records at the OS level, so nothing shows up in the participant list. You should still tell people you're recording.
Real names instead of “Speaker 3”
An optional AI step reads the transcript and names each speaker from what was said, like “Thanks, Priya.” It sees text, never audio, and it can run on a local model.
An hour-long meeting is ready seconds after you stop
Transcription runs while you talk, so almost everything is done by the time you stop.
Brightwave Reporting Discovery
Sam, you’re the one building these — walk me through what month-end actually looks like for you, step by step.
Sure. On the first I start exporting — GA4, Google Ads, Meta, LinkedIn — each one its own dashboard, one platform at a time.
Got it.
Then everything goes into one master sheet and I start reconciling. The platforms never agree on conversions, so I’m hand-matching attribution windows row by row.
And every client wants their numbers framed a little differently — it’s never quite the same report twice.
Right, so I rebuild the same charts four or five times. By the time the deck’s ready we’re already a week into the month.
And the renewals coming up next quarter — how many of those hinge on getting these out faster?
Name Them Once
Save a name once and that voice is recognized in later meetings.
It asks when it isn’t sure
If a voice isn’t a clear match, you get a name to confirm instead of a guess.
20 seconds to set up
A profile needs about 20 seconds of someone talking, over a few turns. Voice profiles stay on your Mac.
Fewer Words Lost
Built to keep words and figures from going missing.
Recovers words when people talk over each other
Where speech was heard but no words came out, a recovery pass reads the audio again. On AMI meetings, full of crosstalk, 20.7% of words are wrong against 24.5% for stock Parakeet.
Switch languages mid-sentence
No language to pick: 25 languages are detected as they’re spoken. A phrase in Spanish or French inside an English meeting stays in the transcript instead of dropping out. Languages →
Capture Decisions, Action Items
Action items get the right owner because the transcript has the right speaker.
Bookmarks
Bookmark a moment mid-call. The summary covers it, and any follow-up next to it becomes an action item, marked Tentative if nobody committed.
“3 PM my time” → 1 PM yours
If your prep notes say where Marty’s based, the app does the math. Every deadline from him lands in your own time, with the original zone kept alongside.
Brightwave Reporting Discovery
Each Brightwave client report takes most of a week to hand-build across five ad platforms, and four renewals next quarter hinge on fixing it. The proposed build: scheduled API pulls into one store, live per-client dashboards, and an ask-anything agent — all on their own stack.
Action Items
- Mateo (You) — Send a scoped plan + sample dashboard for one client, built on their own data
Sun, Oct 11th (by Friday) - Sam Rivera — Pull every platform they report on + the metrics each client cares about
Add to RemindersPain Points
Desired Outcome
Decision Makers & Approval Path
Open Questions
"Wait, say that again. I'll start recording."
A system-level shortcut, like Spotlight or Raycast. Or let it start itself (beta) →
Run your scenario through the live demo
Connected to Your Tools
Ask Claude, Gemini, or Codex about any meeting, or find it in Spotlight. 94% of test searches put the right meeting in the top three.
> Add today's action items to my Linear inbox.
⏺ mimicscribe · get_action_items
Added 3 issues from "Weekly standup":
· Ship the export fix (Sam, Fri)
· Review the onboarding copy (you, Thu)
· Book the customer interview (Priya, next week)
Connect Your AI Agent
Claude
Gemini
CodexClaude, Gemini or Codex can search, read and update your meetings.
Set up integrations →Notes In Your Vault
Obsidian
LogseqAutomatic Markdown notes in your Obsidian vault or Logseq graph. No agent required, and nothing has to leave your Mac.
Set up the notes folder →Native to Your Mac
Meetings show up in Spotlight and plug into Shortcuts and Siri. It's built on Apple's App Intents, so there's no scripting.
Set up shortcuts →Free to Start
Recording, transcription and speaker separation are free and run on your Mac. Pro is a one-time purchase. Cloud AI is optional.
Recording and transcription- Speaker separation and voice profiles
- Voice typing
- Search across meetings
- AI meeting summaries for light use
- 25 in-meeting briefings a week
- MCP server for AI agents 100 calls / week
- Auto-export Markdown 5 meetings / week
- OpenAI-compatible endpoint 15 summaries / week
Everything in Free, no limits on
- MCP server for AI agentsClaude, Cursor or any MCP client
- Auto-export MarkdownObsidian, Logseq or any folder
- AI on any OpenAI-compatible endpointOllama, LM Studio, Microsoft Foundry, Bedrock
- Yours forever, all 1.x updates
- Activate once, works offline for good
Unlimited summaries, briefings, follow-ups and file imports on our Gemini proxy. Includes Pro while subscribed.
Requires macOS 15+ and Apple Silicon · v1.0.0-rc.40 · secure checkout by Stripe · 30-day money-back guarantee
No account, no usage analytics. Cloud AI has fair-use limits that heavy use doesn't reach.
Questions about plans or billing? support@mimicscribe.app
On-device by Default. You Pick the Provider.
All audio is processed on your Mac. AI is opt-in: a local model, your company's provider, or our open-source Gemini proxy.
Using it at work? Read the company-policy guide →
Bring Your Own Endpoint
Ollama and LM Studio locally, your company's Foundry or Bedrock, or our Gemini proxy. Swap it anytime in Settings.
On-device Per Meeting
Turn it on for every meeting or just one. Transcription and speakers keep running on your Mac, and no text goes to a remote AI.
No Account
No sign-in, no email, no usage analytics. Pro is a license key, not an account.
See Every Request
Settings → Network Log lists each request live: what it was for
and where it went. Check with nettop too.
Common Questions
Compatibility, privacy, pricing and requirements.
Is it really free?
Yes, for light use. Recording, transcription, and summaries with named speakers need no account or card. The live in-meeting assistant (briefings and follow-up questions) runs on a weekly allowance, and a subscription lifts it.
Does it work with Zoom, Teams, and other apps?
Yes. Most AI notetakers join the call as a bot, with a spot in the attendee list and a recording badge. MimicScribe captures system audio at the OS level instead, so it works with Zoom, Teams, Google Meet, Slack huddles, or any app that plays sound. Speakers are still separated on-device. You don't need a plugin or an extension.
What runs on-device vs. in the cloud?
Audio never leaves your Mac. Speech recognition, speaker separation, and echo cancellation always run there. The text-based AI (speaker names, summaries, action items) runs wherever you point it: a local model like Ollama or LM Studio, your company's approved provider, or your own Gemini key. The default is an open-source Gemini proxy that keeps no copies. See the technology page for the full breakdown.
Do I need to tell people I'm recording?
Recording laws vary by state and country — some US states and most of Europe require all parties to consent. MimicScribe doesn't announce itself to participants; that's your call. Best practice: tell attendees at the top of the call, and stop if anyone objects. In a regulated industry, check with legal or compliance first.
Where do my meetings live, and can I get them out?
On your Mac, in one searchable library. Nothing syncs to a server, and no account holds your data. As each meeting ends MimicScribe can drop a Markdown note into an Obsidian or Logseq vault, POST to a webhook for Zapier or Make, and hand meetings to AI agents through an MCP server. See the integrations →
What permissions does MimicScribe need?
- Microphone — required for all voice features.
- System Audio Recording — captures audio from video calls. Audio only — no screen capture or video.
- Accessibility optional — voice editing, plus recognizing meeting sites in a browser for automatic recording. Skip it and meeting recording still works, including automatic recording for Teams, Slack, and Zoom.
Can it start recording on its own?
Yes, in beta. Turn it on and calls in Teams, Slack, Zoom, and browser meeting sites like Google Meet record themselves from the start. Anything it doesn't recognize it leaves alone. While one is recording, the menu bar shows “Capturing audio” with the elapsed time, and recordings stop when the call does. See how each app is detected →
Does it handle other languages and technical terms?
Yes — 25 languages, detected automatically. The transcript and the summary both come out in the language spoken. Technical terms and proper nouns work without a custom dictionary. See the languages page for the list.
Will MimicScribe slow down my Mac?
No. It sits at about 145 MB in the menu bar, and a meeting costs roughly a third of one CPU core, because the heavy ML work runs on the Neural Engine. Runs on any Apple Silicon Mac with macOS 15 or later, including a base M1 with 8 GB. Setup downloads about 1.2 GB of models. There's no Intel build. See full performance details →
Anything else, email support@mimicscribe.app and I'll get back to you.