callum ginty callum ginty

Dev Blog - LIMA 1.7.4.1

This release focuses on critical bugfixes, bringing robust functionality to descriptive video service and dynamic web narration features. It also includes the newest model from Open AI, GPT-5.3.

New Features

  • Added GPT-5.3 (OpenAI)

  • Updated Vietnamese language support.

  • Refined AI behaviour for more concise responses.

  • Added end-turn confidence threshold slider in settings, allowing manual-tuning of input speech.

Bug Fixes

  • Fixed license authentication issue.

  • Fixed Open AI model compatibility with Descriptive Video Service

  • Fixed Open AI model compatibility with Dynamic Website Narration

Read More
callum ginty callum ginty

Dev Blog - LIMA 1.7.3.4

This release focuses on improved speech input through automatic end of turn detection, speeding up response times. It also adds a "quick input" hotkey that allows you to type instructions to LIMA with a new hot key "Ctrl - Alt - H". This hot key and the other hotkeys are configurable in the settings. The settings have also been greatly expanded allowing the ability to change LIMA's voice speed, changing the base AI model and adjusting the verbosity of YouTube and Website narration.

New Features

- New speech detection system, automatically detects when you have finished speaking.

- Added new pop up text input widget, enables text input while keeping lima in the background, use ctrl + alt + H to activate (configurable in the settings)

- Adjusted default TTS speaking speed from fast to medium

- Added new settings to change the speaking rate on natural language playback

- Made website and video narration verbosity configurable in settings

- Made Base AI model configurable in settings

  • GPT-5.2 OpenAI

  • Llama 4 Maverick Meta

  • Kimi K2.5 Moonshot

- Switched default AI model for improved performance

- Added option to change the quick input box hotkey in settings

- Added end-turn confidence threshold configuration for speech detection

Bug Fixes

- Added missing Text-to-Speech announcements when settings are changed

- Improved setting UI increasing compatibility with more screen types

Read More
callum ginty callum ginty

Dev Blog - LIMA 1.7.2.2

This changelog covers bug fixes, features, and improvements added since version 1.7.0.2. The changes bring a new feature to handle websites with constantly changing elements as well as stability and bugfixes.


New Features


Dynamic Website Narration (DWN)

A new feature that extends LIMA's narration capabilities beyond YouTube videos to any website content. This feature provides narration on sites that update without user input, like website carousels. This feature integrates with legacy screen readers to send Windows notifications for NVDA or JAWS to narrate, avoiding interruptions to your workflow.

Other features

- Switched to improved vision model for YouTube narration
- Auto Re-Launch After LIMA Update
- Reduced starting latency on cold sessions
- Added settings toggle for Dynamic Website Narration
- Added settings toggle for Descriptive Video Service


Bug Fixes

- Fixed Descriptive Video Service failing to restart a YouTube video after narration
- Addressed text to speech falling back to system voice in Descriptive Video Service
- Improved tooltips and accessible names for UI elements
- Speech Voice reset to clean-up migration to new voice system

Read More
callum ginty callum ginty

Dev Blog - LIMA v 1.7.0.2

This changelog covers bug fixes, features, and improvements added since version 1.6.9. The changes represent significant enhancements to the text-to-speech system, descriptive video service, tool execution, and stability.

New Features

- Implemented new Voice System capable of reading underscores, hyphens, Celsius, dollars and related symbols
- Added links to LIMA's Documentation
- Added 4 new natural voices
- Adjusted initial user guidance
- Improved speed of the observation tool
- Added Descriptive video service support for Brave browser
- Refined AI output for concise responses
- Added a "press enter" tool

Bug Fixes

- Fixed Descriptive Video Service pause/resume crash
- Fixed start-up crash cause by Speech to text
- Fixed Observe screen hotkey (Ctrl + Alt + J)
- Fixed broken "create memory" tool
- Fixed broken "Press windows key" tool
- Addressed some programs not launching when requested
- Addressed Descriptive Video Service sometimes not returning narration
- Addressed broken theme support

Read More