AI tools, scored for your job
Get paid to train AI
🤝 You're in the Free & Open Source library — community-built tools you can use without paying. A different concept from our scored AI directory.
Home › Free & Open Source › Audio & Music › meetily
✦ Free & open sourceAudio & Music

meetily

Local-first AI meeting assistant that transcribes audio live and generates meeting summaries on your computer.

Privacy-first local AI meeting transcription and summaries

Transcribe live meetings and generate AI summaries without sending audio data to cloud servers.

Free forever · open source · MIT
✓ Light setup✓ Browser-based✓ Real-time collaboration
8.4
ZEKAI
Top choice for offline notes.
Free & open source · Audio & Music
Ease of setup7
Usefulness8
Maintenance9.5
Community9.2
★ 30,927
GITHUB
Sep 2026
UPDATED
MIT
LICENSE
🛠 Don't want to self-host? We can set it up →
⚡ Quick answer

Meetily is a self-hosted desktop application that captures system and microphone audio, transcribes it locally with Whisper or Parakeet, and creates summaries. It suits audio professionals, enterprise executives, and legal teams who need meeting intelligence without sharing sensitive conversations with third-party cloud services.

Runs on
Cross-platform
Hosting
Desktop
Languages
Rust
License
MIT

What it is

The app records system audio and microphone input simultaneously with audio ducking and clipping prevention. It handles real-time transcription on local hardware using Whisper or Parakeet models and supports audio file imports. Summaries run through local models via Ollama or optional external endpoints like Claude, Groq, and custom OpenAI APIs.

Who it's for

It is ideal for privacy-conscious teams, defense contractors, legal professionals, and voice studio managers who must strictly manage data sovereignty. It is less suitable for users with older hardware lacking AVX2 instructions or those who want zero-setup web interfaces without installing local desktop binaries.

Key features

Local Transcription Engines

Runs Whisper and Parakeet models directly on your hardware using Metal, CoreML, or Vulkan acceleration.

Dual-Channel Audio Capture

Records system audio and microphone simultaneously with dynamic ducking and clipping protection.

Flexible LLM Support

Generates meeting summaries using local Ollama instances or custom OpenAI-compatible endpoints.

Audio File Import

Imports existing audio recordings to generate transcripts or re-transcribe with different local models.

How to start

Up and running in 3 steps

1
Download and run the installer for macOS (.dmg) or Windows (.exe), or compile from source on Linux.
2
Configure your preferred AI summary backend by linking a local Ollama setup or entering an API endpoint.
3
Select your audio input devices and start recording your live meeting or importing an audio file.
Real talk

Our honest verdict

What's great

  • Processes audio locally without sending confidential meeting data to third-party cloud servers.
  • Combines microphone and system audio with built-in ducking and clipping prevention.
  • Supports local LLMs via Ollama alongside custom OpenAI-compatible API endpoints.
  • Accelerated locally using Metal/CoreML on macOS and Vulkan on Windows.

Where it falls short

  • Linux users and NVIDIA CUDA hardware configurations require manual compilation from source.
  • Requires modern hardware with AVX2 CPU support and dedicated GPU resources for fast local inference.
  • Advanced features like PDF/DOCX export and automatic speaker separation are gated behind the paid PRO tier.
Cost

Pricing & license

Meetily Community Edition is free and open source under the MIT license. The creator also offers Meetily PRO as a commercial paid upgrade with advanced export formats, enhanced models, and enterprise team workflows.

Paid work

Open remote AI-training roles

874 open remote AI-training roles, updated November 15, 2026; most pay $20–$170 an hour. Zekai lists them free; the application goes to the employer’s platform.

See all open roles →
Compare

Alternatives

🎁 Free & open-source alternatives

These reviewed AI tools do the same job instantly — from our scored directory.

Get more

Use it, or have us set it up

📄 Free PDF: meetily for Audio & Music
A plain-language guide to getting your first result. Sent to your inbox.
🔔 64 people want a full video tutorial — add your vote
🛠 Don't want to set it up yourself?
We'll install, host & configure meetily for you — and train your team.
Get it done for you ↗
Questions

FAQ

Does Meetily require an active internet connection to transcribe meetings?

No, Meetily processes live audio and generates transcripts completely offline using on-device Whisper or Parakeet models.

How does Meetily handle system and microphone audio together?

It features professional audio mixing that captures both channels at once while applying ducking and clipping prevention.

Can I use external LLMs for summaries if I do not want to run local models?

Yes, you can connect Meetily to Claude, Groq, OpenRouter, or any custom OpenAI-compatible endpoint.

Radar

Latest AI news

✉️ The weekly free toolkit
The best new free & open-source tools for Audio & Music — one short email a week, in your language.
Free · 1 email/week · unsubscribe anytime
Get paid to train AI →

See Zekai first in Google