pepito records, transcribes and summarizes your meetings with AI — entirely on your device. No bot joins your calls. No audio leaves your machine. No subscription.
Capture audio from any app
Most AI meeting tools send your audio to the cloud, join your calls as bots, or require you to trust third-party servers. pepito was built to make this structurally impossible.
Recording, transcription and summary generation all run on your Mac. No audio file, no transcript and no meeting minutes are ever sent to an external server.
pepito captures your Mac's system audio directly. No bot joins your call, no screen recording, no browser extension. Participants never know you're taking notes.
Once the transcription model is downloaded, the entire pipeline works offline. Ideal for air-gapped networks and secure environments where Internet access is restricted.
"Privacy-friendly" means your data isn't sold. Truly local means it never leaves your device in the first place.
pepito
|
Cloud-based tools | Bot-based tools | |
|---|---|---|---|
| No bot joins your calls | ✓ | Varies | ✕ |
| Audio stays on your device | ✓ | ✕ | ✕ |
| Works fully offline | ✓ | ✕ | ✕ |
| No DPA required | ✓ | ✕ | ✕ |
| No subscription | ✓ | ✕ | ✕ |
A fully local pipeline processes your recordings in four steps. Retry any step individually if something goes wrong.
Capture system audio and microphone with one click. No bot, no plugin.
Auto-converted to M4A for compact storage. 128 to 320 kbps configurable.
Whisper runs locally on your Apple Silicon Mac. Multilingual with automatic language detection, SRT timestamps.
Your LLM generates structured Markdown meeting minutes from the transcript.
Start a new recording while the previous one is still processing. Pipelines run in parallel.
Teams, Zoom, Google Meet, Webex, Slack, Discord, FaceTime — or in-person meetings via microphone. No plugin required, ever.
Monitors active calls in Teams, Zoom, Webex, Slack, Discord, FaceTime, plus Chrome and Safari for browser-based meetings. Starts after 10s of sustained audio, and auto-stops on silence with a configurable delay (default 30s) and an optional confirmation prompt.
Normal (orange timer with live audio levels) or Mini (discreet conversation icon). Double-click the menu bar icon to start or stop instantly.
Reads your macOS calendar via EventKit. Auto-detects the current meeting and injects subject, participants, organizer and location into the summary context for richer output.
OpenAI Whisper embedded in the app via whisper.cpp, optimized for Apple Silicon. Multilingual with automatic language detection, selectable model size, SRT output.
pepito auto-detects local AI CLIs installed on your Mac - Claude, Gemini, Codex, Ollama and opencode - and lists them in the provider picker. Or point pepito at any OpenAI-compatible endpoint (LM Studio, vLLM, your corporate API). Fully editable prompt with {{transcript}} and {{context}} placeholders.
Teach pepito your proper nouns, acronyms and technical jargon. Used to improve both transcription accuracy and summary generation.
Let pepito follow the spoken language automatically, or pin summaries to a fixed language of your choice - ideal for multilingual teams.
Create a Markdown note while recording, pre-filled with date, subject and participants. Injected into the LLM context.
Dedicated window grouped by day. Per-step status, errors and duration. Rename recordings (with AI-suggested titles), retry failed steps, open in Finder. Inline iMessage-style waveform player to replay any moment without leaving the app. Import external audio files (M4A, MP3).
Control pepito via AppleScript. Global keyboard shortcut to start and stop from anywhere.
Configurable model mirror URL. Signed & notarized builds.
No DPA. No data processor. No cross-border transfer.
pepito produces no personal data outside the host machine. Legal & compliance teams can approve it without a subprocessor agreement.
Where recordings cannot leave the firm.
Attorney-client privilege, doctor-patient confidentiality, trading desk compliance. pepito makes leaks structurally impossible.
No Internet required after initial setup.
Connect your internal LLM server. Point the model download URL to your intranet mirror. Works completely offline.
Product owners, managers, assistants, engineers, sales reps — pepito adapts to every role.
I used to spend 30 minutes after each sprint review writing up the minutes. Now it's done in 2 minutes. The time savings are huge, and nothing gets lost.
I manage three teams across different time zones. pepito lets me find every decision made, with full context. Essential for follow-up.
I manage the schedule of four directors. With pepito, I send out meeting minutes within the hour. They can't believe how fast it is.
As an engineer, what I appreciate is that everything runs locally. No data through a third-party cloud. We plug in our own internal LLM and we're set.
After every client meeting, I have a clean summary with key points and action items. I send it right away. It looks really professional.
We deployed pepito on 40 workstations without touching the network. No server, no cloud license. The IT team loved it.
Install via DMG or Homebrew.
An onboarding wizard guides you through permissions and preferences. Download model from within the app — or from your intranet mirror.
And stay focus on your meeting.
After that, pepito works automatically — it detects your calls, records, transcribes and summarizes without any manual intervention.
A native Swift app designed to get the most out of your Mac — tiny footprint, smooth interface, deep system integration.
Smooth and lightweight. Minimal memory footprint, deeply integrated with the system.
Pipeline runs in the background. Record a new meeting while the previous one is still being transcribed.
Each pipeline step can be retried individually. No need to start over.
No Internet connection required. Ideal for secure enterprise environments and air-gapped networks.
Security bookmarks for folder access. Quit confirmation during active recording or processing.
The core pipeline is complete. These are the next differentiators.
Know who said what. The transcript will identify each speaker separately — critical for multi-participant summaries.
See the transcription appear in real time during the recording. Confirm pepito is capturing correctly, without waiting.
Search across all your transcripts and summaries at once. Find any decision, name or action item from any past meeting.
Teach pepito the names, acronyms and jargon of your team for fewer transcription errors. Available in Settings > AI since version 26.25.
Yes, 100%. Recording, transcription and meeting minutes generation all run entirely locally. No data goes through an external server, unless you voluntarily configure a remote LLM endpoint.
Most AI meeting tools send your audio to cloud servers for transcription, or join your calls as a visible bot. pepito's transcription runs with OpenAI Whisper (via whisper.cpp) embedded directly in the app, optimized for Apple Silicon. There is no bot, no browser extension, no screen recording. The entire pipeline — recording, transcription and summary — runs on your Mac.
Yes. Once the transcription model is downloaded, everything works offline. Only meeting minutes generation requires network access if you use a remote LLM server.
All of them. pepito captures your Mac's system audio, so it works with Teams, Zoom, Google Meet, Webex, Slack, Discord, FaceTime and any other tool. It also records in-person meetings via the microphone.
pepito auto-detects local AI CLIs installed on your Mac - Claude, Gemini, Codex, Ollama and opencode - and offers them in the provider picker. You can also point pepito at any OpenAI-compatible server (LM Studio, vLLM, a corporate server or a cloud API) by configuring the URL, API key, model and temperature in the preferences.
pepito produces no personal data outside your Mac. No audio, transcript or summary is transmitted to any external server by the application itself. No DPA is required. If you configure a remote LLM endpoint, your own data processing obligations with that server apply.
Recording consent laws vary by jurisdiction. pepito does not handle consent on your behalf — this remains your responsibility. Because pepito doesn't join calls as a bot, there is no visible "bot is recording" indicator. Check your local laws and your organization's policies before recording.
A Mac running macOS 14 Sonoma or later. Apple Silicon Macs (M1 and later) offer the best transcription performance.
When enabled in settings, pepito monitors selected apps for active calls. Recording starts automatically after 10 seconds of sustained audio and can auto-stop with a confirmation prompt after a configurable silence period.
Yes. You can import M4A and MP3 files directly into pepito. They go through the same pipeline: transcription and AI-generated meeting minutes, with optional context you can add at import time.
pepito is a one-time purchase of 45 EUR. No subscription, no recurring fees. You can try before buying — the app works without a license with limited features.
No subscription. No account. Lifetime updates.
forever
No credit card. Use all features within the limits.
one-time purchase · lifetime updates
free with code · lifetime updates · ends in —
Secure payment via Paddle. VAT included where applicable.
Code applied automatically at checkout. Secure payment via Paddle.
No account, no subscription, no cloud.
Download for macOSor install with Homebrew
brew install vjeantet/tap/pepito