Show HN: Muesli – If Granola and Wisprflow had an open source on device baby • Hacker News Board

Show HN: Muesli – If Granola and Wisprflow had an open source on device baby

#1

Post by pHequals7 » Mon, May 04, 2026, 4:41 PM UTC

Hey folks, I am the developer behind muesli - which is your one stop app for all your speech to text needs, be it voice dictation or meeting transcriptions that runs on device on your Apple Neural Engine using CoreML based STT models (Parakeet, Whisper, Cohere transcribe). Everything is open source and we are at 160 stars - au naturale - would love for folks to use it and contribute further to the development

Show HN: Muesli – If Granola and Wisprflow had an open source on device baby
freedspeech.xyz

Re: Show HN: Muesli – If Granola and Wisprflow had an open source on device baby

#2

Post by pHequals7 » Mon, May 04, 2026, 4:44 PM UTC

Github: https://github.com/pHequals7/muesli

Looking to add on device CUA and support more models (MSFT Vibevoice, IBM Granite etc)

Re: Show HN: Muesli – If Granola and Wisprflow had an open source on device baby

#3

Post by pbshgthm » Mon, May 04, 2026, 4:59 PM UTC

Finally something that works local and feels polished!

Re: Show HN: Muesli – If Granola and Wisprflow had an open source on device baby

#4

Post by ferril » Mon, May 04, 2026, 5:45 PM UTC

Looking for something like this. An OSS on device version where I can store transcripts as markdowns in my file system.

Re: Show HN: Muesli – If Granola and Wisprflow had an open source on device baby

#5

Post by pHequals7 » Mon, May 04, 2026, 7:53 PM UTC

pbshgthm wrote: post #3

Finally something that works local and feels polished!

let me know if you face any issues - and always looking for more collaborators!

Re: Show HN: Muesli – If Granola and Wisprflow had an open source on device baby

#6

Post by rpdaiml » Mon, May 04, 2026, 7:56 PM UTC

How are you handling the on device speech pipeline, especially around model size, latency, and accuracy tradeoffs on consumer hardware?

Re: Show HN: Muesli – If Granola and Wisprflow had an open source on device baby

#7

Post by alok97 » Mon, May 04, 2026, 9:48 PM UTC

love the sly name!

Re: Show HN: Muesli – If Granola and Wisprflow had an open source on device baby

#8

Post by watertype » Tue, May 05, 2026, 3:43 AM UTC

very cool - going to try this out today

Re: Show HN: Muesli – If Granola and Wisprflow had an open source on device baby

#9

Post by pHequals7 » Tue, May 05, 2026, 3:58 AM UTC

rpdaiml wrote: post #6

How are you handling the on device speech pipeline, especially around model size, latency, and accuracy tradeoffs on consumer hardware?

Currently the on device models such as Parakeet and Whisper are great for English, faster than cloud hosted models a little less accurate - if you switch on the post processing, the ASR output goes through a fine tuned Qwen 3.5 model that improves the accuracy, formatting etc - all of the code is open source feel free to inspect and suggest perf improvements as a PR!

Re: Show HN: Muesli – If Granola and Wisprflow had an open source on device baby

#10

Post by phalgun_g » Tue, May 05, 2026, 4:10 AM UTC

this is now making me hungry