Open Voice OS

Open Voice OSOpenVoiceOS is a community-driven, open-source voice AI platform for creating custom voice-controlled ​interfaces across devices with NLP, a customizable UI, and a focus on privacy and security.About Us🎉 OpenVoiceOS Receives NGI Zero Commons fund grant!Why Open Voice OS?Community DrivenPowered by developers around the globe from various Linux and Foss communities, an open platform for developers interested in making cutting-edge voice assistance technology available to everyone.Multi-platformEmbedded headless device or single board computers with screens to build a do-it-yourself smart speaker, Open Voice OS is the open community playground for all platforms to come and experiment at.Experimental at CoreHave an experimental feature you want users to experience before landing them into any of the Linux-based open-source voice assistant projects upstream? Open Voice OS is the platform.DIYOpen Voice OS being a community platform is open to all developers and contributors wanting to support a specific device or a platform.Getting started Installing OVOS couldn't be simpler! Just give our installer a try, and you're all set. We offer two main ways to install OVOS - Docker and Python. Python Virtual Environment If you are a developer, and would like to fiddle with the code, this is the way to go.DockerIf you want a super stable and easy way to run OVOS, Docker is the way to go.To get started, simply copy and paste the following command in your terminal:sh -c "curl -s https://raw.githubusercontent.com/OpenVoiceOS/ovos-installer/main/installer.sh -o installer.sh && chmod +x installer.sh && sudo ./installer.sh && rm installer.sh"Copy to clipboardOwn a Raspberry Pi or Mycroft® Device ?Our Prebuild Image is a stripped-down Linux OS designed to host the open-source voice assistant Open Voice OS, catering specifically to embedded systems, low-spec headless devices, and small touch-friendly screens.Download NowFrequently Asked QuestionsFind answers to the most common questions about Open Voice OS, its features, and how to get involved.GeneralTechnicalContributingUsing OVOSGeneralHow did Open Voice OS start?Open Voice OS started as MycroftOS. Over time, more Mycroft community members joined the project, and it was renamed to OpenVoiceOS to avoid trademark issues.Initially, Open Voice OS focused on bundling Mycroft-core and creating companion software, but due to contributions not being accepted upstream, we now maintain an enhanced reference fork of Mycroft-core with extra functionality while keeping all companion software Mycroft-core (dev branch) compatible.You can think of Open Voice OS as the unsanctioned "Mycroft Community Edition".What is the relationship between Open Voice OS and Mycroft?Both projects are fully independent. Initially, Open Voice OS focused on wrapping Mycroft-core with a minimal OS, but as both projects matured, Open Voice OS-core was created to include extra functionality and make Open Voice OS development faster and more efficient.Open Voice OS has been committed to keeping our components compatible with Mycroft, and many of our changes are submitted to Mycroft to include in their projects at their discretion.Is Open Voice OS free to use?Yes! Open Voice OS is completely free and open source. It's released under the Apache License 2.0, which means you can:Use it for personal or commercial purposesModify and distribute itContribute back to the projectWe do appreciate donations to help sustain the project, but they are entirely optional.TechnicalDoes Open Voice OS work offline?By default, ovos-core does not require a backend internet server to operate. Some skills can be accessed (via command line) entirely offline.The default speech-to-text (STT) engine currently requires an internet connection, though some self-hosted, offline options are available.Individual skills and plugins may require internet, and most of the time you will want to use those for a full experience.What hardware does Open Voice OS support?Open Voice OS can run on a variety of hardware platforms, including:Raspberry Pi models (3B, 3B+, 4, Zero 2)Mark I and Mark II devicesLinux desktops and laptopsDocker containersCheck our downloads page for specific images and installation instructions.How do speech recognition and text-to-speech work in Open Voice OS?Open Voice OS uses a plugin-based architecture for both speech recognition (STT) and text-to-speech (TTS):Speech Recognition (STT): The default configuration uses online services, but you can also set up local/offline options like Vosk or Mozilla DeepSpeech.Text-to-Speech (TTS): Multiple options are available including Mimic3 (local), Google TTS, Amazon Polly, and more. You can choose and configure these in your settings.ContributingHow can I contribute to Open Voice OS?Open Voice OS is a community project and we welcome contributions of all kinds:Testing and reporting bugsWriting or improving documentationCreating or enhancing skillsCode contributionsTranslationsCommunity supportVisit our contribution page to learn how to get started.Using OVOSHow do I install Open Voice OS?The installation process depends on your hardware:For Raspberry Pi: Download our pre-built image and flash it to your SD cardFor desktops/laptops: Install using our Docker container or packageFor Mark II: Download the specific Mark II imageDetailed installation instructions are available on our downloads page.What can I do with Open Voice OS?Open Voice OS allows you to:Create a voice assistant with customizable wake wordsControl smart home devicesPlay music, podcasts, and radioGet answers to questionsSet timers and remindersExtend functionality with skills from our marketplaceCreate your own skillsThe functionality can be extended through our community-developed skills.Got a question that isn't answered here?View Full FAQContact UsHave a question or need help?Feel free to reach out to us. Whether you have a question or want to contribute to the project, we would love to hear from you.GitHubDocumentationDiscussionMatrixEmailAre you a business or organization looking to integrate Open Voice OS into your products?Fill out our contact form to get in touch with us.Want to be a part of Open Voice OS? Check ourContribution Page to learn more. --- About Open Voice OSMeet OpenVoiceOS, a newcomer in the smart speaker scene, offering a different choice from the usual options like Amazon Echo and Google Home. With OpenVoiceOS, you have control over your data and can customize your smart speaker experience. It's designed to respond accurately to your commands, whether you speak or touch the screen. OpenVoiceOS is open-source, meaning anyone can help improve it, and it can run offline for added privacy. If you're looking for a smart speaker that puts you in control, OpenVoiceOS might be the one for you.Open Voice OS is a part of a larger ecosystem of FOSS voice technologies.Check Friends ProjectsHistoryMycroftAI Kickstarter LaunchAugust 2015MycroftAI company launches Kickstarter for their Mark-1 based on a Raspberry Pi3.MycroftAI Mark 1 ReleaseSeptember 2017MycroftAI Mark 1 is released and Kickstarter campaign fulfilled.MycroftAI Mark 2 Kickstarter LaunchJanuary 2018MycroftAI launches second Kickstarter campaign for their Mark 2 device.First GUISeptember 2018The first GUI saw the day of light in a cooperation between MycroftAI and BlueSystems based on KDE framework.MycroftOS CreationOctober 2018Peter Steenbergen (j1nx) creates "MycroftOS", the first version of what will eventually become the OpenVoiceOS framework.Neglect of Community ContributionsEarly 2020MycroftAI as a company starts to neglect community contributions.Renaming to OpenVoiceOS - Mycroft EditionOctober 2020MycroftOS was renamed to OpenVoiceOS - Mycroft Edition due to trademark issues enforced by MycroftAI.Formation of OpenVoiceOS TeamOctober 2020Casimiro Ferreira (Jarbas), Aditya Mehra (AIX), and Peter Steenbergen (j1nx) join forces as Python developer, GUI/QT KDE developer, and Linux OS developer respectively.NeonCore recreated on top of OVOS and relicensed under a FOSS license"October 2021NeonCore recreated on top of OVOS and relicensed under a FOSS licenseDaniel McKnight Joins OpenVoiceOSNovember 2021Daniel McKnight, NeonAI's lead developer, joins the team.MycroftAI LayoffsNovember 2022MycroftAI lays off most of their staff. Only a skeleton crew remains.MycroftAI Partners with NeonAIFebruary 2023MycroftAI partners up with NeonAI to take over the Mark 2 fulfillments and not much later ends its business.OpenVoiceOS FundraiserMarch 2023OpenVoiceOS starts fundraiser to form a non-profit foundation legal entity.Aditya Leaves OpenVoiceOSApril 2023Aditya leaves OpenVoiceOS.Mycroft Forums MoveJanuary 2024Mycroft forums move to Open Conversational AI.OpenVoice OS Foundation EstablishedFebuary 2025OpenVoice OS Foundation is established as a non-profit foundation legal entity.OpenVoiceOS receives NGI Zero Commons Fund grantOctober 2025OpenVoiceOS has been selected to receive a grant from the NGI Zero Commons Fund! --- DownloadsInterested in building your own Voice Assistant? Check out this amazing guide to get started.Supported DevicesSupported PeripheralsWhich device are you using? Raspberry Pi Mycroft® Device Note: If you want to install Open Voice OS on your Laptop/Desktop, consider using our installer script. It will install all the dependencies and set up the environment for you. It supports all major Linux distributions as well as Raspberry Pi 3, 4, and 5. More details here Are you a developer?If you are a developer and want the latest and greatest, check our development releases. Expect bugs, and if you encounter any, please report/contact us (even better, fix it and submit a PR).Development Releases --- Say Hello to Our TeamOpen Voice OS is maintained by a small team of developers and lots of contributors.Daniel McKnight United States 🇺🇸Casimiro Ferreira Portugal 🇵🇹Peter Steenbergen Netherlands 🇳🇱Community Hall of FameA big shoutout to our community members for their invaluable contributions to the project! They have been instrumental in maintaining the core components of OVOS and hosting public servers for everyone in the community to use.Gaëtan TrelluCanada 🇨🇦@goldyfruitMike GrayUSA 🇺🇸@mikejgrayJeremy BrodieUSA 🇺🇸@builderjerSwen GrossGermany 🇩🇪@emphasizeSuvan BanerjeeIndia 🇮🇳@suvanbanerjeeParker SeamanUSA 🇺🇸@5trongthanyTimon van HasseltNetherlands 🇳🇱@timonvanhasseltFlávio De MeloBrazil 🇧🇷@femelo