Meetily
Desktop meeting recorder that transcribes and summarizes meetings locally.
Quick answer
Meetily is a desktop meeting recorder that transcribes and summarizes meetings locally, listed under Speech & translation. A typical small-business use: meeting notes for client, legal or HR calls that must not go to a cloud note-taker. It runs on each user's own computer, so there is no server to rent. License: MIT, which allows internal business use.
Last updated · facts verified against official docs on · sources
Activity data comes from GitHub and was last refreshed Oct 26, 2026.
What is Meetily?
Meetily (Community Edition) is a desktop app for macOS and Windows, buildable on Linux, that records microphone and system audio, transcribes in real time with local Whisper or Parakeet models, and writes summaries with Ollama or an LLM provider you choose. Recordings and transcripts stay on the computer, and there is no server to host.
Where it fits in a 10–200 person business
- Meeting notes for client, legal or HR calls that must not go to a cloud note-taker
- Transcribe imported audio files on a laptop without uploading them
- Local meeting summaries with a company Ollama or OpenAI-compatible endpoint
These use cases are our editorial suggestions, not claims made by the project.
Can a business use Meetily? (license)
| License | MIT |
|---|---|
| Type | Permissive: MIT / Apache-2.0: use, modify and sell with few obligations. |
| Internal business use | Allowed under the license text |
| What to watch | Permissive. Internal and commercial use allowed; keep the license notice. Meetily PRO is a separate paid product. |
This is a plain-English summary of the license text, not legal advice. Third-party models you run with it have their own licenses.
Data & compliance: does Meetily phone home?
| Telemetry (usage data sent to the vendor) | Off by default (opt-in) PostHog usage analytics are optional and off by default; when enabled they send anonymized feature usage, session and performance data, never meeting content. Source: github.com/Zackriya-Solutions/meetily/blob/main/PRIVACY_POLICY.md |
|---|---|
| Other calls home by default (updates, marketplaces, default cloud services) | Not documented |
| Single sign-on (OIDC / SAML / LDAP) | Not documented |
| Audit log | Not documented |
| Role-based access control (RBAC) | Not documented |
| Data residency / GDPR notes from the project | Documented Recordings, transcripts and transcription models are stored locally; only LLM providers you choose receive text for summaries. Source: github.com/Zackriya-Solutions/meetily/blob/main/PRIVACY_POLICY.md |
Checked against the project's own docs and repository on . "Not documented" means we could not find the answer in official sources; it does not mean the feature is missing or that no data is sent. Third-party services you connect (model APIs, vector databases, search engines) have their own data policies. Compare all apps.
What hardware does Meetily need?
The project does not publish a minimum CPU/RAM figure, so we leave the official value blank rather than guess.
GPU: macOS packages use Metal and CoreML automatically; Windows packages use a Vulkan-enabled Whisper build. NVIDIA CUDA needs a source build with a CUDA toolchain.
No RAM or disk figures are published. The Windows installer requires an AVX2-capable x64 CPU; the macOS package listed is for Apple Silicon (aarch64).
How much does it cost to host Meetily per month?
Runs on each user's own computer, so there is no server to rent.
How to deploy Meetily
Method: Desktop installer (Linux - build from source)
# Windows / macOS: download the installer from
# https://github.com/Zackriya-Solutions/meetily/releases/latest
# Linux:
git clone https://github.com/Zackriya-Solutions/meeting-minutes
cd meeting-minutes/frontend
pnpm install --frozen-lockfile
./build-gpu.sh From the official instructions: github.com/Zackriya-Solutions/meetily#installation. Always check the source for the current version before you run it.
Known gotchas when self-hosting Meetily
- There is no packaged Linux installer; Linux users build from source (Rust and Node.js toolchain). source
- The Windows installer needs an AVX2-capable x64 CPU and does not use CUDA; CUDA acceleration requires your own source build. source
- Speaker identification, advanced PDF/DOCX exports, custom summary templates, auto-join and self-hosted team deployment are Meetily PRO features, built on a different, paid codebase. source
- Summaries via Claude, Groq, OpenRouter or OpenAI send transcript text to that provider; use Ollama to keep everything on the device. source
Alternatives in Speech & translation
- whisper.cpp Fast C/C++ port of OpenAI Whisper speech recognition with a small HTTP transcription server.
- PDFMathTranslate PDF translator that keeps the original layout, formulas, charts and tables.
- LibreTranslate Self-hosted machine translation API with no dependency on Google or DeepL.
- Speaches OpenAI-compatible speech-to-text and text-to-speech server (faster-whisper, Kokoro, Piper).
Meetily FAQ
How much RAM does Meetily need?
Meetily does not publish an official RAM figure, so we do not state one. No RAM or disk figures are published. The Windows installer requires an AVX2-capable x64 CPU; the macOS package listed is for Apple Silicon (aarch64).
Does Meetily need a GPU?
macOS packages use Metal and CoreML automatically; Windows packages use a Vulkan-enabled Whisper build. NVIDIA CUDA needs a source build with a CUDA toolchain.
How much does it cost to self-host Meetily?
The software is free to download. It runs on each user's own computer, so there is no server to rent.
Is Meetily free for commercial use?
Meetily is licensed under MIT (Permissive). Internal business use is allowed under the license text. Permissive. Internal and commercial use allowed; keep the license notice. Meetily PRO is a separate paid product. This is a summary, not legal advice.
What are common problems when self-hosting Meetily?
There is no packaged Linux installer; Linux users build from source (Rust and Node.js toolchain). The Windows installer needs an AVX2-capable x64 CPU and does not use CUDA; CUDA acceleration requires your own source build. Speaker identification, advanced PDF/DOCX exports, custom summary templates, auto-join and self-hosted team deployment are Meetily PRO features, built on a different, paid codebase. Summaries via Claude, Groq, OpenRouter or OpenAI send transcript text to that provider; use Ollama to keep everything on the device.
Is Meetily still maintained?
Yes, it is actively developed. Last commit: Sep 10, 2026. Latest release: v0.4.1 (Sep 12, 2026). Checked Oct 26, 2026.
How do I install Meetily?
The official method is Desktop installer (Linux - build from source). The exact commands are in the "How to deploy" section above and in the official instructions: https://github.com/Zackriya-Solutions/meetily#installation
What are self-hosted alternatives to Meetily?
Other apps in Speech & translation: whisper.cpp, PDFMathTranslate, LibreTranslate, Speaches.
Sources
- GitHub repository: github.com/Zackriya-Solutions/meetily
- Official documentation, Hardware requirements, Deploy instructions, Gotcha 2: github.com/Zackriya-Solutions/meetily#installation
- License text: github.com/Zackriya-Solutions/meetily/blob/main/LICENSE.md
- Gotcha 1: github.com/Zackriya-Solutions/meetily/blob/main/docs/building_in_linux.md
- Gotcha 3: github.com/Zackriya-Solutions/meetily#meetily-pro
- Gotcha 4: github.com/Zackriya-Solutions/meetily/blob/main/PRIVACY_POLICY.md
- Hetzner Cloud pricing (cost estimate): www.hetzner.com/cloud/regular-performance
- GitHub stars, commits and releases: GitHub REST API, fetched
Facts on this page were checked against the project's own repository and docs on 2026-10-26. Spotted something out of date? Tell us.