To transcribe meetings offline on a Mac, record them with Whisper Notes, the app we make: it captures Zoom, Teams and Google Meet calls from system audio plus your microphone with no bot joining, detects the call, shows a live transcript panel while you talk, labels who said what (you can set up to 8 speakers), and transcribes up to 24 hours per recording on the device without uploading anything. Meeting recording is in both Mac versions: $7.99 once on the App Store, one purchase for the iPhone app and the Mac App Store version, or $14 once for the Mac app from our website, which is free for 5,000 words a week.
Transcription runs on the built-in Parakeet model (Moondream's Parakeet Ultra, post-trained from NVIDIA Parakeet V3), and, with AI features turned on in the Mac app from our website, the on-device Gemma 4 model can summarize the transcript.
A Typical Monday
10 AM, Zoom call with a client. Whisper Notes captures the meeting audio and your microphone without adding a bot to the participant list. The app cannot decide whether recording is appropriate for you: tell participants and obtain any consent required by your organization and local law.
When the call ends, Parakeet transcribes the recording on your Mac. On a Mac, the built-in Parakeet model runs at about 74× real time, so an hour-long meeting is text in under a minute; your time will vary by Mac, audio, and model. Turn on AI features and Gemma 4 can then summarize the transcript or extract action items without sending it to an API.
The workflow is simple: record, transcribe, review, and summarize. The recording, speech recognition, and Gemma processing stay on the Mac.
What It Does
Recording
Whisper Notes captures the meeting audio and your microphone at the same time, so both sides of a Zoom, Teams, or Google Meet conversation are included. On Mac, Whisper Notes detects Zoom, Teams and Google Meet calls, asks whether to record, and can start automatically if you turn that on; you can review the recording before you keep or share the transcript. The same recording works for any sound your Mac plays, such as a webinar or a YouTube video: see recording system audio on Mac.
Unlike a meeting bot, Whisper Notes does not appear as another participant. That is a workflow difference, not permission to record silently: notification and consent requirements vary by company, country, and state.
Transcription
Parakeet runs on Apple Silicon through CoreML and supports 25 European languages. For Chinese, Japanese, Korean, and Cantonese, SenseVoice runs through MLX. Before Whisper transcribes, Silero VAD skips the silent parts. Performance depends on the Mac, model, audio length, and amount of speech.
A meeting transcript split by speaker, with timestamps; click any sentence to play the audio from that moment
Speaker Labels: Who Said What
Whisper Notes now identifies speakers. Run speaker identification on a meeting recording and every paragraph gets a label — Speaker 1, Speaker 2 — with its timestamp. Rename a speaker once and the label updates through the whole transcript; SRT and VTT exports keep the names.
Like the rest of the workflow, speaker identification runs entirely on-device, and it works on iPhone and Mac. Two or three clearly distinct voices — a client call, an interview — work best; if voices sound similar, set the number of speakers yourself (up to 8). Benchmarks, hard cases, and honest limits are in the announcement: Whisper Notes Now Identifies Speakers.
Speaker labels on a three-person meeting, with the detected speakers renamed
Post-Transcript Tools on Mac
In the Mac app from our website, turn on AI features and Gemma 4 runs on your Mac with no API key or cloud call. After transcription:
- •Summarize — condense the reviewed transcript into key points
- •Action Items — identify candidate tasks and deadlines for you to verify
- •Translate — translate the transcript on supported Macs
- •Chat — ask "what did we agree on pricing?" and get an answer grounded in the transcript
AI Assistant in the Mac app from our website: a summary of the meeting, written on the Mac
How Fast Is Offline Meeting Transcription?
Use measured results as a reference, not a promise. We ran the same English file through two models on an M4 Pro:
| Model | Realtime factor on M4 Pro |
|---|---|
| Parakeet V3 | 103× |
| Whisper Large V3 Turbo | 14.3× |
The comparison uses one file on one Mac. A longer meeting does not always scale perfectly, and exact times vary with your chip, selected model, language, audio quality, and how much silence there is. The Parakeet V3 article linked above contains the full methodology and model comparison.
Why We Built It This Way
Meeting audio can contain sensitive client negotiations, HR reviews, board discussions, or legal consultations. Where that data is processed and stored deserves the same scrutiny as any other confidential record.
Cloud meeting assistants send audio or transcripts to vendor infrastructure and handle them under the vendor's retention and data-processing policies. That can be useful for live collaboration, but it also adds another system for your team to review.
Whisper Notes keeps the recording, speech model, transcript, and Gemma processing on the Mac. That reduces third-party data transfer, but it does not make a workflow automatically compliant with GDPR, HIPAA, privilege rules, or company policy. You still need appropriate consent, access controls, retention rules, and device security.
How It Compares
| Whisper Notes | Typical cloud meeting assistant | |
|---|---|---|
| Processing | 100% on-device | Vendor infrastructure |
| Bot in call | No | Often a bot, browser extension, or calendar integration |
| Price | $7.99 once (App Store) or $14 once (Mac app from our website, 5,000 words/week free) | Usually a free tier and/or subscription |
| Works offline | Yes | Usually requires internet |
| AI summary | Local Gemma 4 (Mac app from our website) | Processed by the provider |
Free and open-source options on GitHub
Search GitHub for offline meeting transcription on a Mac and these four projects come up. All of them keep the audio on your computer:
- •Steno records both sides of Zoom, Meet or Teams calls on macOS 15 or later with Apple silicon, transcribes with Whisper (WhisperKit) and shows words live as people speak; speaker labels appear after you stop. It does not summarize, by design. Free for personal, non-commercial use (Business Source License 1.1).
- •Recap records your microphone and system audio with no bot, transcribes on-device with Whisper models in the background, and turns your in-meeting bullets into notes with Apple Intelligence. It needs macOS 26. MIT licensed, installed from a DMG or Homebrew.
- •local-meeting-transcriber does not record: it is a background service that watches folders of finished recordings, transcribes them with MLX Whisper, labels speakers with pyannote and writes one TXT per file. Setup is in the terminal (Python, FFmpeg, a Hugging Face token). MIT licensed.
- •Meeting Transcriber records your microphone and meeting audio on Windows or on a Mac with macOS 13 or later, Intel included, and transcribes locally with faster-whisper into plain-text notes. It is a preview release (0.1.5), not yet notarized on the Mac. GPL-3.0.
Pick one of these if you want free software, you are comfortable with Homebrew or a terminal, or you need Windows or an Intel Mac (Meeting Transcriber). Pick Whisper Notes if you want one app that detects Zoom, Teams and Google Meet calls, shows the live panel, labels speakers you can rename, offers several engines (Parakeet, Whisper, SenseVoice, Qwen3-ASR) to match the meeting's language, and is the same app on your iPhone for recordings made away from the Mac.
Project details from each README on GitHub, checked 2026-11-02.
Different Meetings, Different Languages
Pick the model that matches your meeting language:
| English / European | Parakeet V3 — 25 European languages; about 74× real time on a Mac; 6.32% English WER on the Open ASR Leaderboard |
| Chinese / Japanese / Korean | SenseVoice — the fast option for Chinese, Japanese, Korean, and Cantonese; 27 minutes of Chinese in 13.83 seconds in our M4 Pro test; that test ran on an earlier version of the app, and today's model card speed, 115–131× realtime, is about the same. For fewer mistakes on the Mac: Qwen3-ASR 1.7B (Beta) |
| Other languages | Whisper Large V3 Turbo — 100+ languages and the broadest language coverage of the three |
Where This Workflow Fits — and Where It Doesn't
Whisper Notes fits meetings where you want a private recording and a reviewed transcript after the call. On Mac, a live transcript panel shows the words during the call, within a few seconds in the 25 European languages Parakeet covers and about every 30 seconds in other languages, such as Chinese; it is a running transcript, not a captioning service. There is no shared cloud workspace where several teammates edit the same transcript at once.
If real-time captions, automatic distribution to a large team, or simultaneous collaborative editing matters more than local processing, a cloud meeting platform may fit better. If the recording should remain on one Mac, the local workflow is the advantage.
If you want to drive this from a script or your own tools, the Mac app downloaded from our website ships a local CLI and MCP server — see the CLI and MCP guide.
Frequently Asked Questions
How do I transcribe a meeting recording on Mac without uploading it?
Use Whisper Notes for Mac. It records the meeting audio and your microphone, then transcribes locally. On a Mac, Parakeet runs at about 74× real time; your result will vary with the Mac, model, language, and recording.
Can I record and transcribe Zoom or Teams meetings offline, without a bot joining the call?
Yes. Whisper Notes captures the meeting audio on the Mac, so it does not add a bot to the participant list. On Mac it detects Zoom, Teams, and Google Meet calls and asks whether to record. Tell participants and obtain any consent required by your organization and local law.
What should I check before recording a meeting?
Confirm that recording is allowed by your organization and the laws that apply to every participant. Tell attendees, obtain the required consent, protect the local file, and delete it according to your retention policy. On-device processing reduces third-party transfer; it does not replace those responsibilities.
Does Whisper Notes transcribe meetings in real time?
Close to it. On Mac, a live transcript panel shows the text during the call, transcribed on your Mac: within a few seconds in the 25 European languages Parakeet covers, about every 30 seconds in other languages, such as Chinese. It is not a real-time captioning tool: if attendees need captions as they speak, use a tool designed for that.
Can I get an AI summary of a meeting without sending the transcript to the cloud?
Yes. In the Mac app from our website, turn on AI features and Gemma 4 runs locally on the Mac to summarize the reviewed transcript, suggest action items, and answer questions about it. No API key or cloud call is required; verify the generated summary and tasks against the transcript.
Are there free open-source apps for offline meeting transcription on Mac?
Yes. Steno and Recap both record the two sides of a call and transcribe on-device with Whisper: Steno shows words live and is free for personal use, Recap needs macOS 26 and is MIT licensed. local-meeting-transcriber transcribes finished recordings from watched folders, and Meeting Transcriber is a preview that also runs on Windows. Whisper Notes is the paid option if you want call detection, a live transcript panel and speaker labels in one app.
Can Whisper Notes show who said what in a meeting?
Yes. On-device speaker identification labels every paragraph by speaker on iPhone and Mac. Rename a speaker once and the whole transcript updates; SRT and VTT exports keep the names. If voices sound similar, set the number of speakers yourself (up to 8).
Download for iOS