- Voice (Beta): talk to LU and hear it answer
- Computer control (Beta): a model works in the apps you approve, off by default
- Local models with image input download with their image part
- Create in chat (Beta): ask for an image or a clip in a Cloud chat
- Ten more chat models on LU Cloud
- A running task says what it is doing, and dialogs have a new look
- The Linux packages carry the voice engine
- Ten security fixes in the new features
- A microphone field in the settings, and seven fixes from user reports
Co-authored-by: Alan Vo <101240385+ALANDVO@users.noreply.github.com>
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
