Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Muesli - local meeting transcription + dictation for macOS (Granola + WisprFlow alternative)
| Date | Stars |
|---|---|
| 2026-07-24 | 822 |
| 2026-07-25 | 826 |
| 2026-07-28 | 826 |
| 2026-07-30 | 826 |
| 2026-08-06 | 826 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
45.0
growth rate 0.00%/day
<p align="center"> <img src="assets/muesli-readme-og.jpg" alt="Muesli - Speech that is free, Speech that is yours" width="900" /> </p> <h1 align="center">Muesli</h1> <p align="center"> <a href="https://trendshift.io/repositories/25442?utm_source=repository-badge&utm_medium=badge&utm_campaign=badge-repository-25442" target="_blank" rel="noopener noreferrer"><img src="https://trendshift.io/api/badge/repositories/25442" alt="Muesli-HQ%2Fmuesli | Trendshift" width="250" height="55"/></a> </p> <p align="center"> <strong>Local-first dictation & meeting transcription for macOS</strong><br> 100% on-device speech-to-text · Zero cloud costs · Privacy by default </p> <p align="center"> <a href="LICENSE"><img src="https://img.shields.io/badge/license-MIT-blue.svg" alt="MIT License" /></a> <a href="https://buymeacoffee.com/phequals7"><img src="https://img.shields.io/badge/Buy%20Me%20A%20Coffee-support-yellow?logo=buymeacoffee&logoColor=white" alt="Buy Me A Coffee" /></a> <img src="https://img.shields.io/badge/platform-macOS%2014.2%2B-lightgrey?logo=apple" alt="macOS 14.2+" /> <img src="https://img.shields.io/badge/Apple%20Silicon-optimized-green" alt="Apple Silicon" /> </p> --- ## What is Muesli? Muesli is a **lightweight native macOS app** that combines **WisprFlow-style dictation** and **Granola-style meeting transcription** in one tool. All transcription runs locally on Apple Silicon — your audio never leaves your device unless you choose a cloud-backed meeting summary provider. <p align="center"> <img src="assets/muesli-github-ss.png" alt="Muesli interface showing dictations and meeting history" width="900" /> </p> ### Dictation Hold your hotkey (or double-tap for hands-free mode) → speak → release → transcribed text is pasted at your cursor. **~0.13 second latency** via Parakeet TDT on the Apple Neural Engine. ### Meeting Transcription Start a meeting recording → Muesli captures your mic (You) and system audio (Others) simultaneously → VAD-driven chunked transcription happens during the meeting at natural speech boundaries → speaker diarization identifies individual remote speakers (Speaker 1, Speaker 2, etc.) → when you stop, the transcript is ready in seconds, not minutes. Generate structured meeting notes via OpenAI, free OpenRouter models, your ChatGPT Plus/Pro subscription, or local Ollama models. Live meeting transcripts have two explicit modes. **Nemotron 3.5** is a unified multilingual option: its continuous transcript is the normal final raw transcript before diarization and note generation, with the configured meeting model retained only for gap recovery. **Parakeet Realtime EOU** is a low-latency English preview: it powers the live floating transcript while a separately selected meeting model creates the final transcript. Settings always shows which model owns the final transcript. Live transcription is off by default. Download Parakeet Realtime EOU or Nemotron 3.5 from Models, then select one under **Settings → Meetings → Transcription**. The waveform-hover preview can be enabled separately from the same section. Downloading a streaming model does not activate it automatically. --- ## Features - **Native macOS architecture** — Swift, AppKit, and SwiftUI app code with in-process CoreML/ANE, Metal, and LiteRT-LM inference. - **Multiple ASR models** — Parakeet TDT and Nemotron 3.5 (Neural Engine), Cohere Transcribe 2B (mixed precision CoreML), Whisper Tiny/Small/Medium/Large Turbo (CoreML/ANE via WhisperKit), Qwen3 ASR, SenseVoice Small, Indic ASR, and experimental Gemma 4 E2B. - **Hold-to-talk & hands-free** — Hold hotkey for quick dictation, or double-tap for sustained recording. - **Meeting recording** — Captures mic + system audio (including Bluetooth/AirPods) with a CoreAudio process tap by default and ScreenCaptureKit fallback. System audio from Zoom, Teams, and other call clients stays on the Others side of the transcript. - **Live meeting transcript** — Choose Nemotron 3.5 for on
Excerpt of 24,575 characters
Read on GitHub
1.1k
20
13
12
10
8
6
6
6
OpenHands · @all-hands-ai
5
4
3
2
2
2
1
1
Claude · @anthropics
1
Vidit Ostwal · @crewAIInc · India
1
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:f304dfce5c38c408, topic:speech-to-text, readme:speech-to-text, desc:transcription