AI & Productivity Glossary

Understand the technology behind AI text transformation, local LLMs, and voice dictation.

AI tools are evolving rapidly, and the terminology can be confusing. This glossary explains the key concepts behind Echoo and modern AI text processing in plain language. Whether you're curious about local LLMs, want to understand BYOK (Bring Your Own Key), or need to know the difference between speech-to-text and AI voice dictation, you'll find clear explanations here.

Each term includes a definition, detailed explanation, practical examples, and links to related use cases and integrations so you can go from understanding a concept to using it in your workflow. New to Echoo? Start with AI Text Transformation and Keyboard Shortcuts for the fundamentals.

AI Text Transformation

AI text transformation is the process of using artificial intelligence models to modify, improve, or convert text. This includes grammar correction, translation, summarization, tone adjustment, and rewriting.

Local LLM

A local LLM (Large Language Model) is an AI model that runs entirely on your own computer instead of in the cloud. Tools like Ollama, LocalAI, and LiteLLM make it easy to run models locally on Mac.

AI Voice Dictation

AI voice dictation is the use of artificial intelligence to convert spoken words into written text. Modern AI dictation engines run locally on your device, support multiple languages, and can post-process transcriptions with AI.

Prompt Engineering for Text

Prompt engineering is the practice of writing effective instructions for AI models to get the best results. For text transformation, this means crafting prompts that tell the AI exactly how to modify your text.

BYOK (Bring Your Own Key)

BYOK (Bring Your Own Key) is a model where an AI tool lets you use your own API key from an AI provider rather than routing your data through the tool's servers. This gives you direct control over privacy, costs, and model selection.

Speech-to-Text (STT)

Speech-to-text (STT) is the technology that converts spoken language into written text. Also called automatic speech recognition (ASR), it powers dictation tools, voice assistants, and transcription services.

Text Expansion

Text expansion is a productivity technique where short abbreviations or triggers are automatically replaced with longer text snippets. Traditional tools like TextExpander and Espanso use static templates, while AI-powered tools like Echoo generate context-aware output.

Apple Neural Engine

The Apple Neural Engine (ANE) is a dedicated hardware component in Apple Silicon chips (M1, M2, M3, M4) designed to accelerate machine learning tasks. It enables AI models to run locally on Mac at high speed with low power consumption.

API Key

An API key is a unique string of characters that authenticates your requests to an AI service. When you use tools like OpenAI, Anthropic, or Google Gemini, your API key proves your identity and tracks your usage for billing.

Ollama

Ollama is an open-source tool that makes it easy to run large language models (LLMs) locally on your computer. It handles model downloading, optimization, and serving through a simple command-line interface and local API.

AI Grammar Checker

An AI grammar checker uses artificial intelligence to detect and fix grammar, spelling, punctuation, and style issues in text. Unlike rule-based spell-checkers, AI grammar checkers understand context and can suggest better phrasing, not just corrections.

Context Window

A context window is the maximum amount of text an AI model can process in a single request, measured in tokens. Tokens are roughly equivalent to words (1 token ≈ 0.75 words). Larger context windows allow processing longer documents.

GGUF Model Format

GGUF (GPT-Generated Unified Format) is a file format for storing quantized AI models that can run efficiently on consumer hardware. It's the standard format used by Ollama, llama.cpp, and other local AI tools.

Keyboard Shortcuts for Productivity

AI keyboard shortcuts are key combinations that trigger AI-powered text transformations directly in your current application. Instead of copy-pasting text to an AI tool, you select text and press a shortcut to transform it in place.

AI Writing Assistant

An AI writing assistant is software that uses artificial intelligence to help you write, edit, and improve text. These range from grammar checkers to full writing tools that can draft, rewrite, translate, and adjust tone.

Open Source AI

Open source AI refers to AI software whose source code is publicly available under a license that allows inspection, modification, and redistribution. This includes open-weights models (like Llama, Mistral) and tools released under licenses such as MIT or GPL. Some apps publish source on GitHub for transparency without granting full open-source rights.

macOS Accessibility API

The macOS Accessibility API is a system framework that allows applications to interact with UI elements in other apps. It enables tools like Echoo to read selected text and replace it with transformed content in any application.

Voice Launcher

A voice launcher is a feature that lets you execute commands by speaking their name aloud. Instead of memorizing keyboard shortcuts, you hold a trigger key, say what you want ("rewrite", "translate", "summarize"), and the command runs automatically.

AI Read Aloud / Text-to-Speech

AI Read Aloud is a feature that speaks selected text aloud using text-to-speech, with the option to run AI processing on the text first. This lets you hear a summarized, translated, or rewritten version of any text rather than just the raw original.

Screen Context for AI

Screen Context is a feature that captures a screenshot and sends it alongside your text to an AI model, giving the AI visual awareness of what's on your screen. This enables context-aware responses that consider both your selected text and the surrounding visual environment.