In-Meeting Technical Assistant.
Notetaker. One Shortcut.
- ✦ Every speaker named — 97% accurate, no meeting bots required — search by speaker benchmark
- ✦ Talking points — What to ask next, facts from your prep — ~2 seconds on demand
- ✦ Keyboard-first — Reachable from any app, no hunting through windows mid-meeting
- ✦ On-device speech processing — Audio never leaves your Mac
Free for everything that runs on your Mac. No account needed.
macOS 15+ · Apple Silicon · v1.0.0-rc.4 · GDPR & CCPA
💬Dana cut Sam off before he finished—circle back to his process
Summary
Get More Done in One Meeting
Anything you miss leaves you guessing at the end or needing a follow-up. The assistant tracks three things so you don't end up there.
For people who end up in fast, packed meetings.
Vague requirements
An ask still unclear after the conversation has moved on.
“Ask what ‘manual slog’ actually means — where’s the time going?”
Goal drift
The conversation wandering from what you came in for.
“Ask which renewals are at risk if reporting doesn’t change.”
Buried prep
A detail from your prep that doesn't surface when it should.
“They dropped a rigid reporting tool last year — lead with why custom fits.”
Tuned against a 96-scenario benchmark to nearly eliminate hallucinations.
"Wait, say that again — I'll start recording."
A system-level shortcut, like Spotlight or Raycast.
Answers from Your Prep Notes
Add your docs in any format and the right details surface at the right point in the conversation 83% of the time. Drop in whatever you have: paste CRM exports, pricing PDFs, competitor briefs — no matter how messy.
Discovery call with Brightwave, a performance marketing agency. Goal: learn how they build client reporting today, what’s forcing a change and by when, and leave with a scoped next step. I build on their own stack — n8n, their warehouse, dashboards — not a tool they rent.
brightwave-account-brief.pdf
client Looker StudioReal Names, Not “Speaker 3”
Speaker identification is accurate 96–98% of the time on the public benchmark. Audio stays on your Mac; an optional cloud step names each speaker from introductions and other cues in the transcript.
Most AI notetakers join your call as a bot to do this. MimicScribe captures audio at the OS level, so nothing joins — no attendee added, no recording badge, no permission to ask the other side (though you probably should).
Speaker profiles saved across meetings
Save a speaker’s name and their voice is recognized automatically in every future meeting. Voice profiles live on your Mac alongside the rest of the audio pipeline.
A 60-minute meeting finishes in about a minute
Apple Silicon makes speaker identification fast enough to feel instant, and accurate 96–98% of the time.
Brightwave Reporting Discovery
34 min · Dana OkaforSam RiveraMateo (You)
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?
Capture Decisions, Action Items
Action items with the right owner because the transcript has the right speaker.
“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.
Send captured items where they belong
Push action items to Apple Reminders or Calendar in one click. Connect an AI agent and it can pull whatever it needs from the meeting into your task tracker, Slack, or anywhere your workflow lives.
Brightwave Reporting Discovery
34 min · Dana OkaforSam RiveraMateo (You)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
Tue, Jun 2nd (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
Keep Working by Voice
Correct, annotate, and draft follow-ups — all in natural language.
Corrections and notes in a sentence
Wrong speaker name? Missed detail? Say it and it’s fixed. Add context that the mic didn’t catch — client names, project codes, decisions made off-camera.
Follow-ups written from what was actually said
Draft emails, Slack messages, or status updates grounded in the real conversation — not your memory of it.
Brightwave Reporting Discovery
34 min · Dana OkaforSam RiveraMateo (You)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
Tue, Jun 2nd (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
Corrected
How long did Sam say a single client report takes?Draft a follow-up email to Dana with the plan
Copy Run your scenario through the live demo
Find Anything from Any Meeting
Search by meaning, not just keywords. Pull up what Sarah said last Tuesday, or every mention of the Q4 deadline — across every meeting you've ever recorded.
Brightwave Reporting Discovery
Summary
- • Each client report takes 3–4 hrs by hand — 22 clients, most of a week, every month
- • No one can answer “why did CPL jump?” without a re-pull — 2 clients flagged it at renewal
- • 4 renewals next quarter hinge on fixing reporting
Action Items
Transcript
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?
Connect Your AI Agent
Make your meetings available to any AI agent — local or remote. Prepare context before a meeting, ask questions after, or automate follow-ups.
Claude
Gemini
CodexStart Free. Go Unlimited
Zero per-minute fees — your Mac handles speech-to-text, so AI only processes text — faster and cheaper.
On-device
- Meeting & file transcription with speakers separated ∞
- Voice typing ∞
AI features
- Meeting summaries with speaker names & transcript correction 2 / day
- In-meeting briefings 5 / day
- Meeting follow-ups & corrections 5 / day
- Voice typing with grammar correction 200 / day
On-device
- Meeting & file transcription with speakers separated ∞
- Voice typing ∞
AI features
- Meeting summaries with speaker names & transcript correction 150 / mo
- In-meeting briefings 100 / mo
- Meeting follow-ups & corrections 100 / mo
- Voice typing with grammar correction ∞
- Bring your own Gemini key Included
On-device
- Meeting & file transcription with speakers separated ∞
- Voice typing ∞
AI features
- Meeting summaries with speaker names & transcript correction ∞
- In-meeting briefings ∞
- Meeting follow-ups & corrections ∞
- Voice typing with grammar correction ∞
- Bring your own Gemini key Included
Free requires macOS 15+ and Apple Silicon · v1.0.0-rc.4 · secure checkout by Stripe · 30-day money-back guarantee
Fair-use limits apply — set high enough that even heavy usage is unaffected.
On-Device Audio. Zero-Retention AI
Audio stays on your Mac. Transcripts route through our open-source proxy with zero retention.
Completely Offline Mode
Pick on-device only at setup, or toggle offline per meeting — transcription stays local, cloud AI pauses.
No Account Required
No login, no email, no account — no way to connect your usage to you.
Bring Your Own Key
Use your own API key — your data flows directly to your provider, never through us.
GDPR & CCPA Compliant
Nothing is retained. We are bound by our privacy policy to never log copies of your transcript data for any reason.
Common Questions
Everything you need to know before getting started.
Does it work with Zoom, Teams, and other apps?
Yes. Most AI notetakers join the call as a participant — a bot in the attendee list, 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 identified on-device, just without anything joining the call. No plugins, no browser extensions.
Does it handle other languages and technical terms?
Yes. The speech model recognizes 25 languages including English, Spanish, French, German, Italian, Portuguese, and more. Meetings that are primarily English with occasional code-switching — a customer quote in Spanish, a German product name, a French aside — transcribe cleanly and stay searchable. Technical vocabulary, proper nouns, and jargon work without a custom dictionary.
What happens if I lose my internet connection?
Transcription always works offline — it runs entirely on your Mac. AI features like text refinement, meeting summaries, and the meeting assistant require an internet connection. If you lose connectivity mid-meeting, transcription continues uninterrupted and AI enrichments are queued until you're back online.
What permissions does MimicScribe need?
- Microphone — required for all voice features.
- System Audio Recording — captures audio from video calls for meeting recording. Audio only — no screen capture or video.
- Accessibility optional — voice editing only. Skip it and meeting recording still works.
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 meeting participants; that's your call. Best practice: tell attendees at the top of the call, and stop recording if anyone objects. If you're in a regulated industry, check with your legal or compliance team before rolling it out.
Will MimicScribe slow down my Mac?
No. MimicScribe holds at about 330 MB during a meeting — less than a single browser tab — and the heap doesn't grow as the recording runs long. ML models run on the Neural Engine, not main RAM, so your other apps aren't competing for memory. See full performance details →
What runs on-device vs. in the cloud?
Speech recognition, speaker separation, and echo cancellation run on your Mac. Speaker attribution, action items, summaries, and real-time suggestions require larger models than what can run locally with acceptable accuracy — so these are handled by cloud AI using transcript text only. Your data is never stored or used for training. See the technology page for the full breakdown.
How do I get the best results?
The AI uses whatever context you give it. Spend two minutes filling out Your Context (your role, what you care about) and add a reference document — product positioning, pricing notes, objection handlers. It turns generic summaries into briefings that actually understand your work. Setup guide with examples →