Blog

This update lets you return to your earlier conversations, improves how LIMA finds and opens programs, and fixes issues with menu shortcuts, the store, and translations.

New Features

• Reopen earlier chats from the new Conversation History menu.

This update matches the AI models to your plan, so you always know which ones you can use, and makes the Subscription Information window more reliable.

Changes

• AI models are now linked to your plan. The biggest models, like Kimi K2.6 and GPT-5.5, are available on the Pro plan only.
• The default model is now Qwen3.8. All models run on Zero Data Retention servers.
• Settings now use easier language, for example "Text-to-Speech" instead of "TTS".
• LIMA now asks for confirmation before replaying the Welcome Tour.

This update provides interface improvements, with visible monthly usage, support for multiple AI-driven actions, improvements to onboarding, and fixes to billing, NVDA support, and program-opening issues.

New Features

• The Subscription Information window now shows your monthly usage and reset time (higher tiers have higher usage).
• LIMA can now carry out several actions from a single request.
• Added Meta's Muse Glimmer 30B to the AI models you can choose in Settings.

You now sign in to LIMA with your Google account instead of typing in a license key. The guided tour for new users is now available in Tagalog and Vietnamese. This release addresses bugs in the update system and voice interruption.

New Features

• Sign in with your Google account. LIMA no longer asks for a license key — just sign in with the email you used when you bought LIMA. You can also sign out from the main window, so switching accounts or sharing a computer is easy.
• The guided tour for new users is now available in Tagalog and Vietnamese.

This release adds new AI model choices and a "thinking-level" control, more reliable web search, a reorganized Settings window with startup options, and multi-monitor support. It also lowers CPU usage, speeds up responses, and fixes a number of stability and speech issues.

New Features

• Kimi K2.6 is now the default AI model.
• Added Opus 4.8 (Anthropic) as a selectable AI model, best for very complex or long-running tasks.
• Added a "thinking-level" setting that lets you choose how much the AI reasons before answering. Off is fastest; higher levels think more deeply but are slower. Low is recommended for everyday use.
• LIMA now supports multi-monitor setups.

This release introduces a brand-new guided onboarding experience for first-time users, adds more AI model choices, 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 enter "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.
• Added voice previews for Vietnamese and Tagalog so you can hear a voice before selecting it.

New Features

• Added Tagalog language option in the installer.
• You can now control how much conversation history LIMA keeps (10–50 messages) and how many screenshots it sends per request (1–5) in Settings.
• Four new voices have been added.
• LIMA now handles YouTube narration and Quick Input in Vietnamese and Tagalog.

This release introduces Facebook video narration, faster responses, waiting sound audio queues, and a range of stability and bug fixes.

New Features

• Streaming TTS is now enabled by default, reducing response times.
• Added Facebook video support to Descriptive Video Service (DVS): LIMA can now detect and narrate Facebook videos.
• Added a waiting sound that plays during long-running tools and screen observation, so users know LIMA is working.
• Added a new "Fastest" TTS playback speed option.

This release focuses on voice enhancements, improved JAWS accessibility, stability and crash fixes.

New Features

• Added 4 new voices, with British and Australian Accents.
• Added a voice preview button to hear a sample of each voice before selecting.
• Added more audio announcements for UI Actions.
• Renamed mute/unmute microphone to Voice Mode, LIMA now starts by default with microphone input turned off. This is configurable in the settings.
• New hotkey - Voice Mode Toggle: Added a configurable hotkey (default: Ctrl+Alt+U) to toggle voice mode on/off.
• Added enhanced compatibility with JAWS.

This release focuses on accessibility improvements with better NVDA support, Tagalog Language support, improved tab order flow, configurable narration languages, and improved microphone start-up handling.

New Features

• Screen Reader Accessibility for Main Transcript: Converted transcript display to allow screen readers to navigate conversation turns individually with arrow keys instead of reading the entire history as one block.
• Improved tab navigation in about, license, update and usage limit dialogs.
• Added auto-scroll to ensure transcript view stays scrolled to the latest content.
• Added support for Tagalog language. We recommend typed input for this language.
• Configurable Narration Language: Both video and website narration services now support configurable output languages (Vietnamese, Tagalog, English).
• Converted microphone input sensitivity to Voice Activity Detection slider for better handling of microphone noise.
• Added handling to show Usage Limit with plan tier information when limits are reached.

Nearly 453,000 Australians are estimated to suffer from blindness or low vision, according to Vision Australia. In this blog, we share five research-backed tips on how to support your family member through this challenging period.

This release focuses on tool improvements, performance optimizations, and reliability.

New Features

• Added voice control tool with speed and voice selection capabilities
• Want to change LIMA's talking speed? just say "talk faster" or "talk slower".
• To adjust the volume output, ask LIMA to speak louder or softer.
• To change the spoken voice, simply ask LIMA to change the voice. You can also ask LIMA what voices are available.