On-device · MCP-native · $39 once

Mindflow

The private knowledge base of everything you say, hear, and transcribe.

Meetings, dictation, files — all on-device. MCP-native. $39 once.

Three steps. Zero friction.

Download the app, open it, and start recording. No accounts, no API keys, no configuration.

1

Install

Download the DMG and drag Mindflow to Applications. The speech model downloads automatically on first launch.

2

Record

Click record in the menu bar or let it auto-detect meetings. Audio stays 100% on your machine.

3

Ask Claude

Transcripts stream to your AI assistant via MCP. Ask about your meeting while it is still happening.

Live transcripts, streamed into your editor

Mindflow's MCP server runs on localhost. Your AI assistant can start recordings, poll live transcripts, and search your entire knowledge base — all while the meeting is still happening.

Claude Code config
{
  "mcpServers": {
    "mindflow": {
      "command": "node",
      "args": ["/Applications/Mindflow.app/Contents/Resources/mcp-server/dist/index.js"]
    }
  }
}
Example interaction
> /mindflow start
Recording started. Transcription streaming to session.jsonl.

> What did Sarah say about the API deadline?
Based on the live transcript (12:34–12:47):
Sarah proposed pushing the API v2 deadline to March 15th,
contingent on the auth migration completing by end of February.

Works with Claude Code · Cursor · Windsurf · any MCP client

Three ways in.
One knowledge base.

Capture meetings. Dictate anywhere. Drop in files. Everything goes to one place — on your Mac.

🎙️ Meetings

Capture system audio + mic. Live to AI. Never leaves your Mac.

⌨️ Dictation

Global hotkey ⌃⌥⌘Space. ~1.5s latency. Auto-paste anywhere.

📁 Files & URLs

Drag, drop, paste a YouTube URL. Watched folders. Local.

One knowledge base.
Yours forever.

Everything you've ever said, heard, or transcribed — searchable by you and your AI.

🗂️ Organize

Folders by client, project, anything.

Available now

🏷️ Label

Tag any meeting.

Available now

🔍 Search

Across everything. From any AI assistant via MCP.

Available now

✏️ Auto-name

Meetings are named automatically from the first spoken sentence. Rename anytime via MCP or Settings.

Available now

👥 Speaker merge

Consecutive segments from the same speaker are merged in exports for cleaner, more readable transcripts.

Available now

🪪 Your name

Set your display name in Settings so your voice is attributed correctly in every transcript.

Available now

📖 Dictionary

Add custom words and replacements so whisper learns your vocabulary: names, acronyms, jargon.

Available now

🐛 Bug report

Built-in diagnostics: send a report from the menu bar, Settings, or after a crash — one click, no sign-in needed.

Available now

Up and running in 60 seconds

Download, drag, done. Mindflow handles the rest.

1

Download

Click the Download button in the top nav to grab the latest DMG for your Mac.

2

Drag to Applications

Open the DMG and drag Mindflow into your Applications folder. Standard macOS install.

3

Launch & record

Open Mindflow from Applications and grant Screen Recording when asked. The speech model downloads once, then everything runs on your Mac.

100% local. Everything runs on your Mac — no cloud, no account, no telemetry. The speech recognition model downloads once on first launch and stays on your machine forever.

First launch: macOS may ask you to confirm the app is safe to open (standard for apps distributed outside the App Store). Right-click Mindflow in Applications → Open, then click Open in the dialog. One time only.

One plan. No gates.

Mindflow is free during private beta. After beta, $39 one-time. Lifetime updates included. No subscription. No caps.

Mindflow

Currently in private beta

  • 100% local — audio never leaves your Mac
  • Three input methods: meetings, dictation, files & URLs
  • MCP-native — Claude Code, Cursor, Windsurf
  • Search your entire knowledge base from any AI assistant
  • Markdown / SRT / VTT export
  • One-time payment, lifetime updates
  • Existing beta users: lifetime free
Download for macOS

Free during beta

Architecture is privacy.

On-device capture and transcription. No cloud, no account, no telemetry.

Mindflow data flow: system audio is captured via ScreenCaptureKit, transcribed locally by whisper.cpp, saved to Markdown and JSONL files on disk, and served to your AI assistant through a local MCP server. Nothing leaves your Mac.

No cloud uploads

Audio is captured and transcribed entirely on your Mac.

No accounts

Nothing to sign up for, nothing to log in to.

No telemetry

We can’t see what you transcribe. Nobody can.

No bots in your call

Captures system audio directly. Other participants never see a bot.

Why Mindflow?

Other tools cover one slice of voice. Mindflow is the whole knowledge base — on-device, MCP-native, one price.

Mindflow Fathom MacWhisper Wispr Flow
On-device
Live meetings
Dictation
File / URL batch
MCP-native ⚠️ added
One-time price $39 Free with caps $29 (files only) $15/mo

Frequently asked questions

What meetings does it work with?

Any meeting platform: Zoom, Google Meet, Microsoft Teams, Slack Huddles, FaceTime, Discord. Captures system audio, so it works with any app that produces sound.

Does it work on Intel Macs?

Yes, but Apple Silicon (M1/M2/M3/M4) is strongly recommended for real-time transcription performance. Whisper uses Metal GPU acceleration on Apple Silicon.

What languages does it support?

All 99 languages supported by whisper.cpp. Best accuracy with English. Set your language in Settings or per-session via MCP.

How large is the speech model?

Depends on the model you choose. Base (~150 MB) for speed, Large-v3 (~3 GB) for accuracy. Downloaded once on first launch.

Does it record video?

No. Mindflow captures audio only. No screen recording, no camera.

What happens when I stop recording?

The transcript saves as a Markdown file and a JSONL file to ~/.local/share/mindflow/transcripts/. You own the files.

What AI assistants does it work with?

Any MCP-compatible assistant: Claude Code, Cursor, Windsurf, and any tool that supports the Model Context Protocol.

Is it open source?

The speech recognition engine (whisper.cpp) is open source. The Mindflow app itself is proprietary, currently free during beta.

What will it cost after beta?

$39 one-time after beta. Lifetime updates included. The features you get during beta are the features you keep.

Why does macOS ask me to confirm the app is safe?

Mindflow is distributed outside the Mac App Store. Right-click the app and choose Open on first launch. This is standard for independent Mac software.

Ready to keep your meetings private?

Install Mindflow in under a minute. No sign-up required.