# Muesli

Muesli is an open-source Mac app for local speech-to-text, dictation, and meeting transcription on Apple Silicon with Parakeet, Whisper, and no cloud STT by default.

## Primary Pages
- Product overview: https://muesli.works/
- Muesli CLI quickstart: https://muesli.works/docs/ - Read meeting transcripts, transcribe audio files, and work with your coding agent through the Muesli CLI on Mac.
- Use Muesli with coding agents: https://muesli.works/docs/agents/ - Connect Codex, Claude Code, and shell-capable coding agents to local Muesli meeting transcripts and notes.
- CLI command reference: https://muesli.works/docs/cli/ - Muesli CLI commands for meeting retrieval, dictation history, audio transcription, JSON output, and writing meeting notes.
- Muesli for iPhone: https://muesli.works/ios - Private voice notes, in-person meeting transcription, and a dictation keyboard with local speech-to-text on iPhone.
- On-device Dictation: https://muesli.works/on-device-dictation - Mac dictation that runs speech-to-text locally on Apple Silicon and pastes clean text into the app you are already using.
- Meeting Notes: https://muesli.works/meeting-notes - AI meeting notes without a meeting bot, using local transcription from your Mac microphone and system audio.
- Local-first AI: https://muesli.works/local-first-ai - A local-first AI Mac app where speech-to-text starts on-device and optional cloud providers stay explicit.
- Mac Dictation App: https://muesli.works/mac-dictation-app - A practical guide to Mac dictation apps, local speech-to-text, offline models such as Parakeet and Whisper, and private voice typing on Apple Silicon.
- Best Dictation Apps for Mac: https://muesli.works/best-dictation-apps-mac - A fair 2026 guide to the best dictation apps for Mac and macOS, including Apple Dictation, Muesli, Superwhisper, Wispr Flow, VoiceInk, and other voice-to-text options.
- Offline dictation apps: https://muesli.works/best-offline-dictation-apps-mac - Compare offline Mac dictation with Muesli, Superwhisper, VoiceInk, and Apple Dictation. Check local models, cleanup, pricing, and your setup without internet.
- Offline Dictation for Mac: https://muesli.works/offline-dictation-mac - A practical guide to offline dictation on Mac, local speech-to-text models, and what can run without sending audio to a cloud transcription service.
- Apple Neural Engine Speech-to-Text on Mac: https://muesli.works/apple-neural-engine-speech-to-text-mac - A technical guide to Apple Neural Engine speech-to-text on Mac, CoreML, local ASR models such as Parakeet and Whisper, and how Muesli uses Apple Silicon for local dictation.
- Local Speech-to-Text Glossary: https://muesli.works/local-speech-to-text-glossary - A technical glossary for local speech-to-text on Mac, covering ASR versus speech-to-text, CoreML, Apple Neural Engine, Parakeet, Whisper, Qwen3 ASR, VAD, diarization, neural AEC, LocalVQE, and local-first transcription.
- ASR Architectures: https://muesli.works/asr-architectures - A practical guide to common speech-to-text architectures, including CTC, RNN-T, TDT, Conformer encoders, encoder-decoder Transformers, and streaming ASR.
- NVIDIA Parakeet speech-to-text: https://muesli.works/nvidia-parakeet-speech-to-text - Use NVIDIA Parakeet for local Mac dictation with Muesli. Compare v3 and v2 language support, install a model, and check recognition and latency on your Mac.
- Whisper Speech-to-Text: https://muesli.works/whisper-speech-to-text - A model guide to OpenAI Whisper speech-to-text, encoder-decoder ASR, multilingual transcription, local inference, and Whisper tradeoffs on Mac.
- Medical Dictation for Mac: https://muesli.works/medical-dictation-mac - A healthcare dictation guide for doctors and medical professionals on Mac who want privacy-focused local speech-to-text before clinical notes move into EHR workflows.
- Local meeting transcription: https://muesli.works/local-meeting-transcription-mac - Set up local meeting transcription on Mac with Muesli. Capture mic and system audio, check permissions, review speaker labels, and export PDF or Markdown.
- Bot-Free Meeting Notes: https://muesli.works/bot-free-meeting-notes - A practical guide to AI meeting notes without a bot, using local-first meeting transcription from the Mac already in the call.
- Apple Dictation Alternative: https://muesli.works/apple-dictation-alternative - An Apple Dictation alternative guide for Mac users who want local-first dictation, offline speech-to-text models, open-source software, and meeting transcription on Apple Silicon.
- Granola alternative: https://muesli.works/granola-alternative - Compare Muesli and Granola for Mac meeting notes: local transcription, free use, transcript access, PDF and Markdown exports, and optional AI summaries.
- Granola vs Muesli: https://muesli.works/granola-vs-muesli - A Granola vs Muesli comparison for Mac users deciding between hosted AI meeting notes and open-source local-first meeting transcription.
- Superwhisper Alternative: https://muesli.works/superwhisper-alternative - A practical Superwhisper alternative guide for Mac users who want local-first dictation, meeting transcription, open-source code, and offline speech-to-text on Apple Silicon.
- Wispr Flow alternatives: https://muesli.works/wispr-flow-alternative - Compare Wispr Flow alternatives for Mac by offline transcription, price, model choice, and setup. Includes Muesli, Superwhisper, VoiceInk, and Apple Dictation.
- Otter.ai Alternative: https://muesli.works/otter-ai-alternative - An Otter.ai alternative guide for Mac users who want local-first meeting transcription, meeting notes without a bot, and notes they can own.
- Fireflies.ai Alternative: https://muesli.works/fireflies-ai-alternative - A practical Fireflies.ai alternative guide for macOS users who want meeting transcription to start on their Mac without sending a bot into every room.
- Hinglish and Indic language meeting notes on Mac with Muesli: https://muesli.works/blog/hinglish-indic-meeting-notes-mac/ - Create meeting notes from Hinglish, English, and Indic conversations on Mac. Use Bodhan for local transcription in Muesli, then review summaries and action items.
- Hinglish and Indic language dictation on Mac with Muesli: https://muesli.works/blog/hinglish-dictation-mac/ - Dictate in Hinglish, English, and Indic languages on Mac with Muesli and Bodhan. Set up local speech-to-text and compare native and mixed-script output.
- Bodhan comes to Mac: Indic speech-to-text in Muesli 0.8.4: https://muesli.works/blog/bodhan-indic-transcription-mac/ - Use Bodhan Core and Flex locally on your Mac with Muesli 0.8.4, with support for India's 22 scheduled languages and English.
- How to dictate in Hindi, Tamil, and other Indian languages on Mac: https://muesli.works/blog/indian-language-dictation-mac/ - Set up local Indian-language dictation on Mac with Bodhan in Muesli. Choose a language, compare Core and Flex, and check mixed-language output.
- Running Bodhan on Apple Silicon with CoreML and MLX Swift: https://muesli.works/blog/bodhan-coreml-mlx-apple-silicon/ - How Muesli 0.8.4 runs Bodhan Core and Flex on Mac with a CoreML encoder, MLX Swift decoder, FP16 and INT8 weights, and local audio processing.
- Help: https://muesli.works/help
- iPhone help: https://muesli.works/help/ios
- Changelog: https://muesli.works/changelog
- GitHub: https://github.com/Muesli-HQ/muesli

## CLI Documentation
- Complete CLI and coding-agent guide: https://muesli.works/docs.txt

## Key Facts
- Runs local speech-to-text on Apple Silicon with model paths such as Parakeet and Whisper.
- Dictate across Mac apps and paste clean text at the cursor.
- Supports hold-to-talk AI dictation and meeting transcription.
- Captures meeting audio from your own Mac without adding a meeting bot.
- Stores dictations, transcripts, and meeting notes locally by default.
- Open-source and inspectable on GitHub.
- No cloud speech-to-text API is required for the default local transcription path after models are installed.
- Optional services such as OpenAI, OpenRouter, ChatGPT, and Google Calendar are explicit integrations, not the default transcription path.

## Technical Facts
- The bundled muesli-cli lets shell-capable coding agents read meeting transcripts and dictations as JSON, transcribe local audio files, and replace formatted meeting notes.
- Coding agents can analyze CLI transcripts using their own model; hosted agent providers may receive transcript text in their context.
- Muesli is a native macOS app built with Swift and AppKit, not Electron.
- Local speech-to-text runs on Apple Silicon through CoreML and Apple Neural Engine-capable model paths where supported.
- For short dictation, local Apple Silicon inference can reduce latency by avoiding the cloud upload, remote inference, response, and paste-back round trip.
- The Apple Neural Engine is dedicated neural network hardware, which helps supported speech models run efficiently on device.
- Muesli supports local ASR model options including NVIDIA Parakeet, Whisper, Qwen3 ASR, and Nemotron Streaming.
- The default dictation workflow does not require a hosted speech-to-text API after local models are installed.
- Meeting transcription combines microphone audio, system audio capture, voice activity detection, and speaker diarization.
- Meeting echo cancellation runs locally with bundled LocalVQE by default and DTLN available as a fallback AEC path.
- Parakeet and Nemotron come from NVIDIA, Whisper comes from OpenAI, Qwen3 ASR comes from Alibaba’s Qwen model family, and Cohere Transcribe comes from Cohere.
- Optional summarization providers are separate from the local transcription path.

## Muesli for iPhone
- Product page: https://muesli.works/ios
- Support page: https://muesli.works/help/ios
- Records voice notes and in-person meetings from the iPhone microphone.
- Runs core speech-to-text locally after a transcription model is downloaded.
- Supports local Parakeet and Whisper model choices with different language, speed, and storage tradeoffs.
- Stores recordings, transcripts, history, and personal dictionary data locally by default.
- The optional Muesli keyboard hands recording to the main app, then receives the result through a shared App Group.
- Optional iCloud sync covers text history; audio and downloaded speech models are not synced.
- Optional OpenRouter or ChatGPT providers can receive transcript text when the user requests an AI summary.
- TelemetryDeck receives anonymized, privacy-preserving aggregate telemetry about app interactions and health, not recordings or transcript text.

## Social Links
- https://github.com/Muesli-HQ/muesli
- https://x.com/fastspeech2text
- https://www.linkedin.com/company/mueslios/
- https://www.youtube.com/@MuesliHQ

## Installation
- Download: https://muesli.works/download/
- Homebrew: brew install --cask muesli
- Latest release: https://github.com/Muesli-HQ/muesli/releases/latest

## Support Questions
### App won't open?
If macOS says Muesli is damaged, open System Settings > Privacy & Security, scroll down, and click Open Anyway. If that still does not clear it, run the command below.
Command: sudo xattr -cr /Applications/Muesli.app

### Why isn't my transcription pasting into the input box?
Usually this means Accessibility access is missing, stale, or attached to the wrong copy of Muesli. Open System Settings > Privacy & Security > Accessibility, make sure Muesli is enabled, then quit and reopen it from /Applications. If it still fails, remove Muesli from Accessibility, add it back, and relaunch.

### Why doesn't the hotkey start dictation?
The global hotkey depends on Input Monitoring. Open System Settings > Privacy & Security > Input Monitoring, confirm Muesli is allowed, then relaunch the app from /Applications. If you changed the shortcut in Settings, make sure you are using the configured key instead of assuming the default.

### Why did Muesli stop working after an update or reinstall?
macOS permissions are tied to a specific installed app path and signature. If you launch Muesli from Downloads, Desktop, or an older duplicate copy, paste and hotkey permissions can silently stop working. Keep one copy in /Applications, delete duplicates, then re-grant Accessibility and Input Monitoring if needed.

### Why is meeting recording failing or missing system audio?
Muesli needs Screen Recording or Screen & System Audio Recording permission for meeting capture. Open System Settings > Privacy & Security, enable Muesli under the relevant recording pane, then relaunch. If microphone transcription works but meeting capture does not, this is usually the missing permission.

### Why isn't Muesli showing upcoming meetings?
Upcoming meetings come from local macOS Calendar access, Google Calendar, or both. If the list is empty, first check Calendar permission. If you rely on Google Calendar, reconnect it in Settings and wait for the next refresh. If you use both, Muesli deduplicates matching events, so you should still only see one entry per meeting.

## Release Sources
- GitHub Releases: https://github.com/Muesli-HQ/muesli/releases - The canonical release history for stable Muesli builds, release notes, and downloadable DMGs.
- Latest Stable Release: https://github.com/Muesli-HQ/muesli/releases/latest - The newest public production build for macOS.
- Source Repository: https://github.com/Muesli-HQ/muesli - The open-source codebase behind the macOS app.