# Muesli-HQ/muesli

Muesli: agent-native local meeting transcription + dictation for macOS (Granola + WisprFlow alternative)

Repository: https://github.com/Muesli-HQ/muesli
Canonical: https://ross.abutalabs.com/products/muesli
Homepage: https://muesli.works
Language: Swift
License: MIT
License Family: permissive
Topics: dictation, on-device-ai, privacy-first, speech-to-text, transcription, meeting-assistant, meeting-notes, apple-silicon, macos, agents
Last push: 2026-09-02T19:17:19+00:00

## Health v2 (maintenance only)
Score: 82/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 100, release rhythm 98, longevity 12
- inputs: {"age_days": 181, "days_push": 0, "days_rel": 15, "gap_med": 1.5, "n_releases_24m": 23}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1072, forks 122 (observed 2026-09-03T02:15:06.736266+00:00)

## What it is
Muesli is an open-source native macOS app that combines hotkey-driven AI dictation with local meeting transcription, running speech-to-text entirely on-device on Apple Silicon. It offers WisprFlow-style dictation and Granola-style meeting notes with speaker diarization, plus optional AI-generated meeting summaries via cloud or local Ollama models.

## Use cases
- dictate text anywhere on my mac with a hotkey
- transcribe meetings locally without a cloud bot
- generate meeting notes and action items from transcripts
- private speech-to-text that never leaves my device
- open-source granola alternative for meeting notes
- wispr flow alternative for voice dictation
- identify speakers in remote meeting transcripts

## When to choose
- you want fully on-device speech-to-text on Apple Silicon with near-zero latency
- you need both dictation and meeting transcription in one privacy-first tool
- you prefer open-source alternatives to Granola or WisprFlow
- you want meeting summaries via your own OpenAI, OpenRouter, ChatGPT, or local Ollama models

## When to avoid
- you need Windows or Linux support - it is macOS 14.2+ only
- you require cloud-scale transcription for many users or servers
- you need non-Apple Silicon Intel Mac support

## Facets
- artifact type: application
- maturity: active
- function: speech-recognition, audio-processing, llm-inference, nlp
- domain: speech-processing, developer-tools, privacy, desktop-applications, artificial-intelligence
- platform: -
- tags: dictation, meeting-transcription, on-device-ai, apple-silicon, granola-alternative, wisprflow-alternative, speaker-diarization, local-first, menu-bar-app, macos, desktop, swift

## Member repositories
- Muesli-HQ/muesli (main) score 82

## Provenance
- Observed fields: from GitHub, fetched 2026-09-03T02:15:06.736266+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:06:37.691911+00:00, confidence not recorded.
  - readme: https://github.com/Muesli-HQ/muesli (fetched 2026-09-03T02:15:06.736266+00:00, sha 287292e459dc)
  - homepage: https://muesli.works (fetched 2026-08-29T13:06:08.565233+00:00, sha 2115590f29a9)
  - site_page: https://muesli.works/changelog (fetched 2026-08-29T13:06:08.574620+00:00, sha 814e004d235a)
- Data as of 2026-08-30T08:39:29.467469+00:00.