跳到正文
GitHub·· 17 小时前AI 评分58

Meetily 开源本地 AI 会议助手发布,支持实时转写与本地摘要

Zackriya-Solutions/meetily

AI 导读

Meetily 是一个隐私优先的开源 AI 会议助手,会议录音、转写和摘要默认全部在本地完成,音频与转写文本不离开设备。它使用 Whisper 或 Parakeet 模型做实时转写,摘要可选 Ollama 本地模型,也支持 Claude、Groq、OpenRouter 和自定义 OpenAI 兼容端点。

正文


Privacy-First AI Meeting Assistant

Zackriya-Solutions%2Fmeetily | Trendshift

Pre-Release GitHub Repo stars GitHub Downloads (all assets, all releases) License Supported OS GitHub Tag


Open Source • Privacy-First • Enterprise-Ready

A privacy-first AI meeting assistant that captures, transcribes, and summarizes meetings entirely on your infrastructure. Built by expert AI engineers passionate about data sovereignty and open source solutions. Perfect for enterprises that need advanced meeting intelligence without compromising on privacy, compliance, or control.

Meetily Demo
View full Demo Video


Meetily PRO Upgrade Offer - Meetily PRO is available for users who need speaker identification, API, MCP and other integrations, advanced exports, custom summary workflows, and team-ready features. Use coupon code LAUNCH20 for 20% off until the next Meetily Community Edition release. Pro adds speaker identification (who said what), custom summary templates, PDF/DOCX export, and MCP, CLI and webhook integrations. Explore Meetily PRO →


Table of Contents

Introduction

Meetily is a privacy-first AI meeting assistant that runs entirely on your local machine. It captures your meetings, transcribes them in real-time, and generates summaries with a local model by default. Audio and transcription never leave your device. If you choose a cloud AI provider for summaries, only the transcript text is sent to it. This makes it the perfect solution for professionals and enterprises who need to maintain complete control over their sensitive information.

Why Meetily?

While there are many meeting transcription tools available, this solution stands out by offering:

  • Privacy First: All processing happens locally on your device.
  • Cost-Effective: Uses open-source AI models instead of expensive APIs.
  • Flexible: Works offline and supports multiple meeting platforms.
  • Customizable: Self-host and modify for your specific needs.

Details

Note: Official builds are only on meetily.ai and github.com/Zackriya-Solutions/meetily/releases.

The Privacy Problem

Meeting AI tools create significant privacy and compliance risks across all sectors:

  • $4.4M average cost per data breach (IBM 2024)
  • €5.88 billion in GDPR fines issued by 2025
  • 400+ unlawful recording cases filed in California this year

Whether you're a defense consultant, enterprise executive, legal professional, or healthcare provider, your sensitive discussions shouldn't live on servers you don't control. Cloud meeting tools promise convenience but deliver privacy nightmares with unclear data storage practices and potential unauthorized access.

Meetily solves this: Complete data sovereignty on your infrastructure, zero vendor lock-in, and full control over your sensitive conversations.

Features

  • Local First: All processing is done on your machine. No data ever leaves your computer.
  • Real-time Transcription: Get a live transcript of your meeting as it happens.
  • AI-Powered Summaries: Generate summaries of your meetings using powerful language models.
  • Multi-Platform: Native apps for Windows and macOS (Apple Silicon). On Linux, build from source.
  • Open Source: Meetily is open source and free to use.
  • Flexible AI Provider Support: Choose from Ollama (local), Claude, Groq, OpenRouter, or use your own OpenAI-compatible endpoint.

Installation

Windows and macOS

Platform Download Link Instructions
Windows (x64) .exe installer Download and run the installer
macOS (Apple Silicon) .dmg installer Open the installer, drag Meetily to Applications, then open it from Applications

Windows compatibility: The packaged installer uses a Vulkan-enabled Whisper build. It requires an AVX2-capable x64 CPU; AVX-512 is not required. CUDA acceleration requires a source build configured with a compatible NVIDIA CUDA toolchain.

Linux (recommended): one-line install

Requires x86_64 Linux with glibc 2.35 or newer (.deb preferred, otherwise AppImage).

curl -fsSL https://raw.githubusercontent.com/Zackriya-Solutions/meetily/main/scripts/install-linux.sh | sh

Linux: installer options and manual installation

Pass options after sh -s --:

# Install the AppImage instead of the .deb
curl -fsSL https://raw.githubusercontent.com/Zackriya-Solutions/meetily/main/scripts/install-linux.sh | sh -s -- --appimage

# Uninstall (keeps your meetings and settings unless you add --purge)
curl -fsSL https://raw.githubusercontent.com/Zackriya-Solutions/meetily/main/scripts/install-linux.sh | sh -s -- --uninstall

Run it with --help to see all options.

Manual install (.deb / AppImage)

Package Download Link Instructions
.deb (x64, Debian/Ubuntu-compatible) .deb package sudo apt install ./meetily_0.5.0_amd64.deb, or alternatively sudo dpkg -i meetily_0.5.0_amd64.deb
AppImage (x64) AppImage chmod +x meetily_0.5.0_amd64.AppImage, then ./meetily_0.5.0_amd64.AppImage. System dependencies still apply; see the Linux guide

To build from source, see Building on Linux or General Build Instructions.

Key Features in Action

🎯 Local Transcription

Transcribe meetings entirely on your device using Whisper or Parakeet models. No cloud required.

Meetily Demo

📥 Import & Enhance Beta

Import existing audio files to generate transcripts, or enhance to re-transcribe any recorded meeting with a different model or language, all processed locally.

Contributed by Jeremi Joslin, improved by Vishnu P S and Mohammed Safvan

Import and Enhance

🤖 AI-Powered Summaries

Generate meeting summaries with your choice of AI provider. Ollama (local) is recommended, with support for Claude, Groq, OpenRouter, and OpenAI.

Summary generation

Editor Summary generation

🔒 Privacy-First Design

All data stays on your machine. Transcription models, recordings, and transcripts are stored locally.

Local Transcription and storage

🌐 Custom OpenAI Endpoint Support

Use your own OpenAI-compatible endpoint for AI summaries. Perfect for organizations with custom AI infrastructure or preferred providers.

Custom OpenAI Endpoint Configuration

🎙️ Professional Audio Mixing

Capture microphone and system audio simultaneously with intelligent ducking and clipping prevention.

Device selection

⚡ GPU Acceleration

Acceleration depends on the platform and build you use:

  • macOS packages: Metal and CoreML are enabled automatically.
  • Windows packages: Whisper is built with Vulkan support.
  • Linux: Build from source with the acceleration configuration appropriate for your system.

CUDA is available through an appropriately configured NVIDIA source build; the standard Windows installer does not select it automatically.

System Architecture

Meetily is a single, self-contained application built with Tauri. It uses a Rust-based backend to handle all the core logic, and a Next.js frontend for the user interface.

For more details, see the Architecture documentation.

For Developers

If you want to contribute to Meetily or build it from source, you'll need to have Rust and Node.js installed. For detailed build instructions, please see the Building from Source guide.

Meetily Pro

Upcoming version

Meetily PRO is a professional solution with advanced features for serious users and teams.

Community Thank-You Offer

Meetily Community Edition will remain free and open source (MIT). PRO exists for users and teams who want a more advanced meeting workflow, including speaker identification, custom summary templates, advanced exports, auto-meeting detection, and AI assistant integrations (MCP, CLI, webhooks), and self-hosted deployment options for teams.

For the community that helped Meetily grow, we are making the upgrade easier: use coupon code LAUNCH20 for 20% off Meetily PRO until the next Meetily Community Edition release.

Key Advantages Over Community Edition:

  • Custom Summary Templates: Tailor summaries to your specific workflow and needs
  • Advanced Export Options: PDF, DOCX, and Markdown exports with formatting
  • Auto-detect and Join Meetings: Automatic meeting detection and joining
  • Speaker Identification: Who said what, on your device, live and on imported audio
  • Chat with Meetings: AI-powered meeting insights and queries (Coming Soon)
  • Calendar Integration: Seamless integration with your calendar (Coming Soon)
  • Self-Hosted Deployment: Deploy on your own infrastructure for teams with our enterprise plan
  • GDPR Compliance Built-In: Privacy by design architecture with complete audit trails
  • Priority Support: Dedicated support for PRO users

Who is PRO for?

  • Teams and organizations (2-100 users) requiring self-hosted deployment
  • Power users who need advanced export formats and custom workflows
  • Compliance-focused organizations requiring GDPR readiness

Note: Meetily Community Edition remains free & open source forever (MIT) with local transcription, AI summaries, and core features. PRO is a separate professional solution for users who need enhanced accuracy and advanced capabilities.

Pro is $10/user/month, billed annually, with a 14-day free trial.

For organizations needing 100+ users or managed compliance solutions, explore https://meetily.ai/.

Learn more about pricing and features: https://meetily.ai/pro/

Contributing

We welcome contributions to Meetily! Before starting, search existing issues and PRs and read CONTRIBUTING.md. Coding agents should also follow AGENTS.md. Use the issue forms for actionable bug reports, feature requests, and documentation problems; ask usage questions in the Meetily community chat.

Thanks for all the contributions. Our community is what makes this project possible.

License

MIT License - Feel free to use this project for your own purposes.

Acknowledgments

  • We borrowed some code from Whisper.cpp.
  • We borrowed some code from Screenpipe.
  • We borrowed some code from transcribe-rs.
  • Thanks to NVIDIA for developing the Parakeet model.
  • Thanks to istupakov for providing the ONNX conversion of the Parakeet model.

Star History

Star History Chart

来源:GitHub · github.com