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

5 comments

• rpdaiml 7 hours ago
  How are you handling the on device speech pipeline, especially around model size, latency, and accuracy tradeoffs on consumer hardware?
• pHequals7 10 hours ago
  Github: https://github.com/pHequals7/muesli

  Looking to add on device CUA and support more models (MSFT Vibevoice, IBM Granite etc)
• pbshgthm 10 hours ago
  Finally something that works local and feels polished!
  [-]
  • pHequals7 7 hours ago
    let me know if you face any issues - and always looking for more collaborators!
• ferril 9 hours ago
  Looking for something like this. An OSS on device version where I can store transcripts as markdowns in my file system.
• alok97 5 hours ago
  love the sly name!