Getting Started 👋

Installation & First Steps

Setup API keys

Chatting with Alice

Summon Alice

Agents

Skills

Customizing Themes

Image Generation

Online Mode

Vision Skills

Working with documents & files

Artifacts

Code Interpreter

Multi-agent

Memory

Deep Links (x-scheme-url)

Remote Actions ✨

Remote Actions Basics

First Remote Action Scenario

Quick Scheduling Links Automation

Using existing automations

Advanced 📚

Local Server

Managing messenger inboxes

Using Model Context Protocol (MCP)

Using Zapier MCP

Using N8N MCP

Custom Apps

Open-source models with Ollama

Connect Alice to OpenRouter.ai

Inspirations 💡

Accept Offers with Alice

Craft Compelling Copy

Customer Service

Translations and readability

Formal Communication

Generate Images & use Vision

Getting Mailchimp Campaign Stats

Google Analytics Reports

Harnessing Alice for Development

Instant Text Correction

Instant Voiceovers

Instant Zoom Meetings

Manage Subscribers in Mailer Lite

Managing Social media

Managing Tasks

Quick Google Calendar Events

Recent News with Perplexity

Scheduling Social Media Posts

Simple Automation for Data Insights

Streamline Project Management

Translations and Learning

Unsplash Photos

Wolfram Alpha

YouTube Descriptions

Zoom & Google Calendar

During a conversation with the assistant, you can paste images from the system clipboard or drag and drop files (jpg/png/gif/webp) into the conversation window. The image will also be automatically loaded from your clipboard when you launch the Skill using a keyboard shortcut.

Important Note: Not all models support image processing. Those that do have an appropriate label.

Images before sending the message are saved locally on your computer, and after sending, they are transmitted to the model along with the content of your message.

Remember that Vision models are not perfect and are also subject to the phenomenon of confabulation (commonly referred to as hallucinations).

An example of a Skill utilizing the capabilities of Vision models is OCR, which allows text found in an image to be transcribed. IMPORTANT: avoid sending files that are too large. Focus exclusively on fragments containing content essential for the model.

Skills such as OCR are usually activated with a keyboard shortcut and apply to one specific image. For this reason, it's worth selecting the "Single-turn Skill" option to skip previous conversation messages. As for the response itself, it will usually be needed in another, external program, so it's worth copying it to the clipboard by activating the "Copy responses to Clipboard" option.

Skill Activated: OCR Image

You're now an advanced OCR system, designed to extract text from images with high accuracy.