Index.En - Localai — ContextQMD

+++ disableToc = false title = "Features" weight = 8 icon = "lightbulb" type = "chapter" url = "/features/" +++

LocalAI provides a comprehensive set of features for running AI models locally. This section covers all the capabilities and functionalities available in LocalAI.

Core Features

Text Generation - Generate text with GPT-compatible models using various backends
Image Generation - Create images with Stable Diffusion and other diffusion models
Audio Processing - Transcribe audio to text and generate speech from text
Text to Audio - Generate speech from text with TTS models
Sound Generation - Generate music and sound effects from text descriptions
Voice Activity Detection - Detect speech segments in audio data
Video Generation - Generate videos from text prompts and reference images
Embeddings - Generate vector embeddings for semantic search and RAG applications
GPT Vision - Analyze and understand images with vision-language models

Advanced Features

OpenAI Functions - Use function calling and tools API with local models
Realtime API - Low-latency multi-modal conversations (voice+text) over WebSocket
Constrained Grammars - Control model output format with BNF grammars
GPU Acceleration - Optimize performance with GPU support
Distribution - Scale inference across multiple nodes (P2P federation or production distributed mode)
P2P API - Monitor and manage P2P worker and federated nodes
Model Context Protocol (MCP) - Enable agentic capabilities with MCP integration
Agents - Autonomous AI agents with tools, knowledge base, and skills

Specialized Features

Object Detection - Detect and locate objects in images
Reranker - Improve retrieval accuracy with cross-encoder models
Stores - Vector similarity search for embeddings
Model Gallery - Browse and install pre-configured models
Backends - Learn about available backends and how to manage them
Backend Monitor - Monitor backend status and resource usage
Runtime Settings - Configure application settings via web UI without restarting

Getting Started

To start using these features, make sure you have LocalAI installed and have downloaded some models. Then explore the feature pages above to learn how to use each capability.