Dev blog: LIMA 1.9

This release introduces a brand-new guided onboarding experience for first-time users, adds more AI model choices, lets you enter a new key without restarting, and reduces CPU usage so LIMA runs lighter in the background.

New Features

- LIMA now greets new users with a guided onboarding flow. On first run it welcomes you, asks for your name, and walks you through the main window and the four global hotkeys (describe screen, stop talking, mute microphone, pop up textbox). The whole tour is spoken aloud and answered by typing — you can say "next", "repeat", or "skip" to move through it at your own pace.
- Added GPT-5.5 as a selectable AI model.
- Added the Kimi K2.6 model (replacing GPT-5.2). Kimi K2.5 is now marked as legacy.
- AI model options in Settings now include short descriptions (for example, "Most capable, slower") to help you pick the right model for your needs.
- LIMA can now fetch information from the web to give more up-to-date answers.
- Added voice previews for Vietnamese and Tagalog so you can hear a voice before selecting it.

Changes‍ ‍

- When you reach your usage limit, you can now enter a new license key directly from the usage-limit dialog. The new key is validated and applied immediately, with no need to restart LIMA.
- Refreshed the colors in the About and Subscription Information dialogs so the text and links are easier to read on a dark background.
- Reduced CPU usage in both idle and active voice modes, so LIMA is lighter on your system while listening and while waiting.