Skip to content

Settings

Open LIMA settings from the File menu → Settings.

Appearance

Setting Description
Theme Controls the look of the LIMA interface. Options: Default, Cool.
Text Size Font size for the chat history. Options: 10–32 pt. Default: 14 pt.

Audio

Setting Description
Language Sets the language for both voice input and AI responses. Options: English, Vietnamese, Tagalog.
AI voice The text-to-speech voice LIMA uses for its responses. See the voice list below.
Speech rate How fast LIMA speaks. Options: slow, medium, fast, fastest.
TTS mode How LIMA generates its voice. Online streams from Google Cloud — higher quality and faster to start speaking, but requires an internet connection. Offline uses your system's built-in voices — works without internet and keeps speech processing on your device, but lower quality.
Microphone sensitivity How sensitive the microphone is to your voice. Increase if LIMA misses commands; decrease if it triggers accidentally.
End Turn Confidence How confident the speech recogniser must be before it considers you finished speaking (0.0–1.0). Lower values end turns faster but may cut you off; higher values wait longer. Default: 0.75.

Available voices

Voice Description
Despina Chill Young Female
Enceladus Middle-Aged Male
Rasalgethi Chill Young Male
Laomedeia Professional Woman
Algenib Australian Man
Aoede Australian Woman
Sadaltager British Man
Callirrhoe British Woman

Note

Algenib, Aoede, Sadaltager, and Callirrhoe are available for English only. Tagalog uses the first four voices.

Hot keys

Four hotkeys can be customised here. See Keyboard Shortcuts for the full list and instructions.

Features

Setting Description
Descriptive Video Service (DVS) Automatically narrates what is happening on screen during YouTube videos. Options: off, minimal, regular, verbose.
Dynamic Website Narration (DWN) Automatically reads out changes on websites as you browse. Options: off, minimal, regular, verbose.
Base AI model The large language model used for all of LIMA's AI responses and screen reading. See model list below.
Conversation history (messages) Number of past user messages included in each AI request. Options: 10, 15, 20, 30, 50. Default: 20.
Max images per request Number of screenshots sent with each AI request. Options: 1–5. Default: 4.
Enable voice mode on startup When enabled, voice mode activates automatically when LIMA starts.
Minimize to tray on close When enabled, closing the LIMA window sends it to the system tray instead of exiting.

Available AI models

Model Notes
GPT-5.5 (OpenAI) Most capable, slower
GPT-5.3 (OpenAI) Very capable, great conversationally — default
Kimi K2.6 (Moonshot) Thinking model, fast and smart
Kimi K2.5 (Moonshot) Thinking model (legacy)
Llama 4 Maverick (Meta) Fastest, prone to hallucinations