OpenVoiceUI is an open-source voice AI assistant platform built for hands-free work and visual, canvas-based output. It is described as working with any LLM and as building live web pages while the user speaks, rather than acting as a text-only chatbot.
Its feature set centers on voice control and visible execution. The platform supports wake word activation, push-to-talk, and interrupt mode for hands-free use. In the canvas UI, it can create live HTML pages during a conversation, including dashboards, reports, image galleries, and interactive tools. It also includes a skill system with 35+ built-in skills such as social media management, SEO, email, business briefings, and marketing, and users can build their own skills without changing the core code. Sub-agents are used for parallel work, and the memory system keeps business details, preferences, and past conversations across sessions. The page also describes OpenClaw AI Gateway as the open-source gateway that turns any LLM into an autonomous agent, handling tools, memory, sub-agents, and multi-step reasoning, and Hermes as a pluggable second AI brain for tasks such as deep research and code generation.
OpenVoiceUI is presented for developers, business owners, and agencies. Example uses include running an LLM of choice, self-hosting on personal hardware, scheduling recurring tasks, managing customer communications, generating reports, handling content creation, and deploying client-specific agents. The page also lists business-stack integrations, including CRM, SEO intelligence, and pluggable AI models, with named examples such as DataForSEO for SEO dashboard functions and Twenty CRM for pipeline management. It says the platform can be installed with Docker, npm, or one-click Pinokio, and also advertises a one-click install with Pinokio and a product tour.
The platform is open source under the MIT license and is described as forever free. It supports self-hosting with no cloud dependency, no vendor lock-in, and no monthly fees, while optional managed hosting is offered for businesses that want the infrastructure handled for them.
In the AI space, OpenVoiceUI takes a focused approach. Enabling users to interact with AI assistants using voice commands and automate tasks visually. It is built as an open-source project for power users and developers seeking customizable AI assistants. OpenVoiceUI is open source under the MIT license. It ships for the web and the command line, and it can be self-hosted.
OpenVoiceUI first shipped in 2026. Development happens publicly on GitHub with 53 stars and 248 commits in the last 90 days. Among its 8 catalogued features are voice control, Canvas UI, and skill system.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do