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

pHequals7 · 2026-05-04T16:44:15.000Z 1777913055

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

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

rpdaiml · 2026-05-04T19:56:12.000Z 1777924572

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

pHequals7 · 2026-05-05T03:58:11.000Z 1777953491

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!

pbshgthm · 2026-05-04T16:59:42.000Z 1777913982

Finally something that works local and feels polished!

pHequals7 · 2026-05-04T19:53:45.000Z 1777924425

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

ferril · 2026-05-04T17:45:25.000Z 1777916725

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

watertype · 2026-05-05T03:43:59.000Z 1777952639

very cool - going to try this out today

alok97 · 2026-05-04T21:48:21.000Z 1777931301

love the sly name!

phalgun_g · 2026-05-05T04:10:39.000Z 1777954239

this is now making me hungry