Voice AI / Space
    Submit
    Back
    OpenvoiceOS

    OpenvoiceOS

    Visit Website
    Tech
    Open Source
    On device

    Open-source platform for customizable, private voice assistants across devices.

    OpenvoiceOS banner

    About OpenvoiceOS

    Open Voice OS: Community-Driven Open Source Voice Assistant Platform

    Open Voice OS (OVOS) is a community-driven, open-source platform for building and running customizable voice assistants on a wide range of devices. With a focus on privacy, flexibility, and extensibility, OVOS empowers developers, makers, and organizations to create voice-controlled interfaces with natural language processing, a customizable UI, and support for both online and offline speech technologies. OVOS is ideal for DIY projects, embedded systems, smart speakers, and experimentation, offering a playground for innovation in voice AI.

    Key Features

    • Open Source and Community-Driven:
      Developed by a global community, released under the Apache License 2.0, and open to contributions from anyone.

    • Multi-Platform Support:
      Runs on Raspberry Pi, Mark I/II devices, Linux desktops/laptops, and Docker containers.

    • Customizable and Extensible:
      Plugin-based architecture for speech-to-text (STT), text-to-speech (TTS), skills, and UI; supports custom wake words and skills.

    • Privacy-Focused:
      Can operate offline with local STT/TTS engines; no required backend server.

    • DIY Friendly:
      Pre-built images for popular hardware and easy installation for makers and developers.

    • Skill Marketplace:
      Extend functionality with community-developed skills for smart home control, media playback, Q&A, and more.

    • Experimental Playground:
      Test new features and ideas before upstreaming to other open-source voice projects.

    • Active Community:
      Welcomes contributions in code, documentation, translations, skill creation, and more.

    Use Cases

    • Creating private, customizable voice assistants for home or business

    • Smart speakers and embedded device projects

    • DIY automation and maker projects

    • Experimenting with new voice AI features and skills

    • Educational and research platforms for voice technology

    Model Selection

    • Plugin-Based Core:
      Choose from multiple STT (e.g., Vosk, DeepSpeech), TTS (e.g., Mimic3, Google TTS), and skill plugins.

    • Device-Specific Images:
      Download pre-built OS images for Raspberry Pi, Mark I/II, and more.

    Getting Started

    Open Voice OS empowers anyone to build, customize, and deploy private, open-source voice assistants-enabling innovation and experimentation in voice AI for all.