In simple English
Muesli lets you speak to type on your Mac without sending your words to the cloud. It also listens to your video calls and writes meeting summaries for you. Most features run directly on your computer chip to keep your conversations private. You can use it for free, but some optional AI summary features need your own paid API keys. The app only runs on Apple Silicon Macs.
What it is
A native Swift application for macOS that combines local speech-to-text dictation and meeting transcription. It uses Apple's Neural Engine and CoreML to run AI models offline.
What it is good for
Solo builders who want fast, private voice dictation and automated meeting notes on a Mac without paying for a cloud subscription.
- Runs speech recognition locally on Apple Silicon for fast results and privacy.
- Captures both your microphone and system audio during video calls automatically.
- Includes a local command-line tool for developers and coding agents to inspect transcripts.
- Requires an Apple Silicon Mac running macOS 14.2 or later.
- Downloading local AI models takes hundreds of megabytes of disk space.
- Advanced meeting summaries require external API keys or a paid subscription.
Granola, WisprFlow, or commercial cloud transcription services
Ollama, OpenAI, or Claude for generating structured meeting summaries
- ggml-org/whisper.cpp55k stars
Runs OpenAI Whisper speech recognition locally in C/C++ but lacks a native Mac meeting recorder interface.
- snapcast/snapcast8.0k stars
A server and clients that play one audio stream in several rooms, kept in time with each other.
- MusicPlayerDaemon/MPD2.8k stars
A background music player with no interface of its own, controlled over a network by separate client programs.
- AcademySoftwareFoundation/OpenTimelineIO2.0k stars
An interchange format and library for editing timelines: the order and length of cuts, and references to the media, but not the media.
brew install --cask muesli