The open-source alternatives to Otter.ai are Meetily, OpenWhispr, Buzz and Vibe. Meetily and OpenWhispr capture a live call from your microphone and system audio and produce a transcript and a summary on your own machine. Buzz and Vibe transcribe recordings and files, with live microphone input in Buzz, and both export subtitles and documents. All four are MIT licensed and run Whisper or NVIDIA's Parakeet locally, so the audio stays on the device. A team switches when it cannot send call audio to a vendor, or wants no per-seat bill for a transcript.
Otter.ai, in the vendor's own words: a service that "transcribes every meeting, turning it into searchable knowledge that powers your workflow", by its own description. otter.ai.
| Project | Openness | Licence | Runs as | Platforms | Self-host | Hosted option | Last release | Stars |
|---|---|---|---|---|---|---|---|---|
| Meetily | OSI | MIT | Desktop app | macOS (Apple Silicon), Windows x64, Linux (build from source) | Yes | Yes | Sep 12, 2026 | 30,859 |
| Buzz | OSI | MIT | Desktop app, pip, CLI | macOS (Apple Silicon), Windows, Linux | Yes | No | Aug 23, 2026 | 21,529 |
| OpenWhispr | OSI | MIT | Desktop app | macOS (Apple Silicon and Intel), Windows, Linux | Yes | Yes | Sep 15, 2026 | 8,286 |
| Vibe | OSI | MIT | Desktop app, CLI, Server (HTTP API) | macOS, Windows, Linux | Yes | No | Sep 5, 2026 | 7,510 |
Licence, release and star figures read from GitHub on September 16, 2026. Openness labels: The code, and the weights where the project is a model, carry a licence on the OSI approved list. The code is public, and the licence limits what you may do with it. Read the LICENSE file before commercial use. The model weights can be downloaded and run. The training data or code is closed, or the weights carry a restriction the code does not.
A meeting assistant under MIT that records your microphone and system audio together, transcribes live on your machine with Whisper or Parakeet, and summarises with a language model you choose.
Desktop app · macOS (Apple Silicon), Windows x64, Linux (build from source) · Runs on your own machines · Hosted version available from the maintainers
A desktop app under MIT that transcribes and translates audio and video files, YouTube links and a live microphone offline with Whisper, with speaker identification and SRT, VTT and TXT export.
Desktop app, pip, CLI · macOS (Apple Silicon), Windows, Linux · Runs on your own machines
A dictation and meeting-notes app under MIT that runs Whisper or Parakeet locally or cloud models with your own key, detects Zoom, Teams and FaceTime calls, and labels speakers on device.
Desktop app · macOS (Apple Silicon and Intel), Windows, Linux · Runs on your own machines · Hosted version available from the maintainers
An offline transcription app under MIT that records system audio and the microphone, supports Whisper, Parakeet and Nemotron models, labels speakers, and exports SRT, VTT, TXT, HTML, PDF, JSON and DOCX.
Desktop app, CLI, Server (HTTP API) · macOS, Windows, Linux · Runs on your own machines
For live meetings on your own machine, Meetily (MIT) records microphone and system audio together, transcribes with Whisper or Parakeet, and summarises with a language model you choose, with Ollama recommended for local use. OpenWhispr (MIT) auto-detects Zoom, Teams and FaceTime calls and adds live speaker labels. For recordings and files, Buzz and Vibe (both MIT) transcribe, label speakers and export subtitles.
Meetily captures your microphone and your system audio at the same time, which is how it hears the other side of a Zoom or Teams call, and its README says all processing stays on your machine. OpenWhispr's README says it auto-detects Zoom, Teams and FaceTime calls. Vibe can record system audio too. Buzz records from the microphone.
OpenWhispr does on-device speaker labelling with voice fingerprints that carry across meetings, though not on Intel Macs. Buzz has speaker identification on transcribed media. Vibe lists speaker diarization, which is the term for labelling speakers. Meetily's community edition README does not list it; it appears in the PRO edition as coming soon.
Meetily generates summaries with Ollama locally or with Claude, Groq, OpenRouter, OpenAI or any OpenAI-compatible endpoint. Vibe summarises with the Claude API or locally with Ollama. Buzz has an AI summary plugin. OpenWhispr's notes feature includes summaries through the language model you configure.
All four are MIT licensed. Meetily, Buzz and Vibe transcribe entirely on your machine. OpenWhispr can run fully local or use cloud models with your key. Meetily also sells a PRO edition on a separate codebase, and OpenWhispr runs a hosted cloud for sync and team spaces; the open-source apps do not require either.
Buzz (Flatpak, Snap, AppImage or pip), Vibe, and OpenWhispr (.AppImage, .deb, .rpm). Meetily on Linux is built from source; its installers cover Windows and macOS.
Running one of these inside your own environment, with your own data and your own security rules, is the kind of work Reveneau does. Read how a forward deployed engagement works.