block
feat: Added audio transcription input to goose app natively
similar to https://github.com/block/goose/pull/512, but using https://github.com/usefulsensors/moonshine as Speech to text and running purely on client side. It is much faster, but less accurate. I will try to plug different models to see what is better
Desktop App for this PR
The following build is available for testing:
The app is signed and notarized for macOS. After downloading, unzip the file and drag the Goose.app to your Applications folder.
This link is provided by nightly.link and will work even if you're not logged into GitHub.
![github-actions[bot] avatar](https://avatars.githubusercontent.com/in/15368?v=4 "Published by a pub.dev verified publisher"){kind=small}
Desktop App for this PR
The following build is available for testing:
The app is signed and notarized for macOS. After downloading, unzip the file and drag the Goose.app to your Applications folder.
This link is provided by nightly.link and will work even if you're not logged into GitHub.
Same comment as the whisper PR - this is a great idea but out of data enough that we should do a new effort on this against the current main
