{"name":"meeting-transcriber: Transcribe macOS Meetings Locally with WhisperKit","description":"Meeting Transcriber is a Swift menu bar app for macOS that records Teams, Zoom and Webex calls, then transcribes them on-device with WhisperKit or NVIDIA Parakeet. It adds speaker separation and optional Markdown meeting notes while keeping audio on your Mac.","github":"https://github.com/pasrom/meeting-transcriber","url":"https://osrepos.com/repo/pasrom-meeting-transcriber","source":"osrepos.com","sourceDescription":"This repository profile is provided by osrepos.com, an open source repository discovery platform.","repositoryProfile":"https://osrepos.com/repo/pasrom-meeting-transcriber","generatedFor":"open source discovery and AI-assisted research","markdown":"https://osrepos.com/repo/pasrom-meeting-transcriber.md","json":"https://osrepos.com/repo/pasrom-meeting-transcriber.json","topics":["swift","macos","desktop-app","privacy","meeting-transcription","speaker-diarization","whisper"],"keywords":["swift","macos","desktop-app","privacy","meeting-transcription","speaker-diarization","whisper"],"stars":null,"summary":"Meeting Transcriber is a Swift menu bar app for macOS that records Teams, Zoom and Webex calls, then transcribes them on-device with WhisperKit or NVIDIA Parakeet. It adds speaker separation and optional Markdown meeting notes while keeping audio on your Mac.","content":"## Overview\n\nMeeting Transcriber is a local-first meeting recorder and transcriber for macOS, built on WhisperKit from Argmax and NVIDIA’s Parakeet, with FluidAudio for speaker diarization. It captures meeting-app audio and microphone audio separately, processes recordings on-device, and can produce structured Markdown notes using Claude Code CLI or an OpenAI-compatible endpoint.\n\nIt is aimed at people who want meeting transcripts without sending audio to a cloud transcription service, especially in privacy-sensitive or offline settings. It supports Teams, Zoom and Webex detection, with additional opt-in detection paths and file imports for existing recordings.\n\n## Key Features\n\n- Automatically detects Teams, Zoom and Webex meetings and records app audio alongside microphone input.\n- Transcribes locally with WhisperKit, which supports 99+ languages, or NVIDIA Parakeet TDT v3, which supports 25 European languages.\n- Separates speakers with FluidAudio, including separate diarization of app and microphone tracks.\n- Generates meeting summaries, decisions and tasks in Markdown through Claude Code CLI or an OpenAI-compatible service, or saves transcripts without notes.\n- Imports common audio and video formats, with ffmpeg required for MKV and WebM.\n- Offers record-only mode and a localhost automation API in the Homebrew build for external processing and integrations.\n\n## Use Cases\n\n- Teams handling confidential, legal or healthcare discussions can keep recordings and transcription on a Mac rather than uploading audio to a meeting service.\n- Individuals who need searchable meeting records can capture supported calls and generate notes with a configured local LLM or Claude Code CLI.\n- Researchers or multilingual teams can select WhisperKit or Parakeet based on language needs and process imported recordings.\n- Organizations with their own processing infrastructure can use record-only mode to capture source tracks for a separate pipeline.\n\n## Our Take\n\nThis is a feature-rich macOS option for local meeting transcription, with active development and rapid issue and pull-request handling, but its contribution activity is heavily concentrated in one person.\n\n**Good fit if:**\n- You use macOS 14.2 or later and want recording, transcription and speaker separation to run locally.\n- Your workflow benefits from separate app and microphone tracks, Markdown meeting notes, or batch processing of recordings.\n- You are comfortable configuring Claude Code CLI or an OpenAI-compatible endpoint for protocol generation, and adopting an MIT-licensed Swift app.\n\n**Look elsewhere if:**\n- You need a Windows or Linux desktop app, or a cloud-hosted meeting transcription service.\n- You need summaries without configuring a supported LLM provider, or cannot grant the macOS permissions required for your chosen recording features.\n- Your team requires development ownership to be spread across multiple contributors; most code contributions come from one person.\n\n## Project Health\n\n| Signal | Value |\n|---|---|\n| Status | **Active**: regular commits and releases |\n| Last commit | 2026-10-29 (today) |\n| Commits, last 90 days | 100+ |\n| Releases, last 12 months | 31 (latest v0.8.1, 2026-09-11) |\n| Contributors | 20 (top contributor: 95% of commits) |\n| Issues closed, last 90 days | 16+ (typically closed in 2 days) |\n| Pull requests merged, last 90 days | 90 (typically merged in 0 days) |\n| Project age | 8 months |\n\nChecked on 2026-10-29 with the GitHub API.\n\n## Project Facts\n\n- Language: Swift\n- License: MIT\n- Stars: 222\n- Forks: 72\n- Topics: apple-neural-engine, coreml, fluidaudio, local-first, macos, meeting-notes, menu-bar-app, ollama\n- Website: https://meetingtranscriber.app\n- Archived: no\n\n## What You Need\n\nDetected in the repository:\n\n- Swift (main language on GitHub)\n- Automated checks on GitHub Actions\n\n## Getting Started\n\nInstall with Homebrew:\n\n```bash\nbrew tap pasrom/meeting-transcriber\nbrew install --cask meeting-transcriber\n```\n\nThe app requires macOS 14.2 or later. See the [README](https://github.com/pasrom/meeting-transcriber#readme) for permissions, provider setup and build instructions.\n\n## License in Plain Words\n\n**MIT** (permissive).\n\n- Commercial use: yes\n- Modify and redistribute: yes\n- You must keep: the copyright and license notice\n- Share your changes: no\n\nA summary, not legal advice: the LICENSE file is what applies.\n\n## Alternatives\n\n- [meetily](https://osrepos.com/repo/zackriya-solutions-meetily): Meetily records and transcribes meetings locally and can use Ollama or other providers for AI summaries, unlike this app's WhisperKit or Parakeet workflow.\n- [mityu](https://osrepos.com/repo/aydogandagidir-mityu): Mityu emphasizes source-linked summaries and action items, while this app focuses on macOS call recording, on-device transcription, and speaker separation.\n\n| Project | Language | License | Stars | Status |\n|---|---|---|---|---|\n| **meeting-transcriber** | Swift | MIT | 222 | Active |\n| [meetily](https://osrepos.com/repo/zackriya-solutions-meetily) | Rust | MIT | 31.6k | Active |\n| [mityu](https://osrepos.com/repo/aydogandagidir-mityu) | Rust | MIT | 1 | New |\n\n## Considerations\n\n- The project is young, despite frequent commits and releases. Recent issue closures and merged pull requests indicate active maintenance, but its very high contributor concentration makes continuity a consideration for teams adopting it long term.\n- The app requires macOS 14.2 or later for its app-audio capture approach. Microphone access is needed for mic recording, and some detection or participant features rely on additional macOS permissions.\n- Transcription models download on first use. The README describes WhisperKit’s stock model as roughly 1 GB and Parakeet’s as roughly 50 MB; initial setup therefore requires network access and local storage.\n- Meeting-note generation depends on Claude Code CLI or an OpenAI-compatible API endpoint. The transcript-only mode avoids that dependency, but does not generate protocols.\n- The README describes unit tests, linting and analyzer checks in CI, but the repository health data does not report tests as a measured requirement or capability.","metrics":{"detailViews":1,"githubClicks":0},"dates":{"published":null,"modified":"2026-10-29T12:44:24.000Z"}}