Full Feature Breakdown
Every Feature You Need, None You Don't
Voice conversation, visual canvas, 35+ skills, parallel sub-agents, image generation, music creation — all open source, all self-hosted.
Voice conversation, visual canvas, 35+ skills, parallel sub-agents, image generation, music creation — all open source, all self-hosted.
Features
Speak and watch your AI execute — no typing, no clicking. Wake word activation, push-to-talk, and interrupt mode let you stay completely hands-free. Works with any LLM (OpenAI, Anthropic, Groq, Z.AI, Ollama) and multiple STT providers. Every command builds something real in the canvas.
Your AI builds live HTML pages as it works — dashboards, reports, image galleries, interactive tools, data visualizations. Pages are private by default and persist on your server. Share any page instantly with a public link, or just say "share this" and your AI handles it.
35+ built-in skills: social media management, SEO optimization, email via AgentMail, business briefings, marketing campaigns, customer communications, referral programs, and more. Create custom skills without modifying core code.
Parallel AI workers for complex tasks. Research competitors, write content, and schedule posts — simultaneously. Configurable concurrency and spawn depth.
Schedule recurring tasks: daily business briefings, weekly reports, automated social media posting, regular data backups. Set it and forget it.
Persistent memory across sessions. Remembers your business details, preferences, conversation history, and learned patterns. Gets better with every interaction.
Built-in file management with drag-and-drop uploads. Browse, organize, and manage documents, images, and project files directly in the canvas.
AI image creation with FLUX.1 and Stable Diffusion 3.5. Multiple quality presets, aspect ratios, and styles. Generated images auto-save to your server.
Full Remotion Studio integration. Your AI scripts, directs, and produces video content with voice-over via Orpheus TTS. Film grain, vignette, letterbox effects built in.
AI-generated music via Suno integration. Create custom tracks by describing the mood, genre, and style. Built-in player with crossfade, auto-ducking during voice, and audio visualizer.
OpenVoiceUI adapts to your aesthetic. Choose from macOS, Ubuntu, retro Windows, and more — all running the same powerful AI underneath.
Active Theme
Windows XP
Nostalgic Windows XP aesthetic
Switch themes instantly — no restart required. More themes available in the community.
Free, open source, MIT licensed. Install in under 5 minutes.