Open Voice OS
Open-source, privacy-focused voice AI platform.. [Free]
Last verified:
What is Open Voice OS?
Open Voice OS (OVOS) is a community-driven, open-source voice AI platform for creating custom voice-controlled interfaces across devices. It provides the foundational tools and frameworks for integrating voice interaction into a wide range of projects, going beyond traditional voice assistants. As a voice operating system, OVOS is highly customizable and has been used in robots and automation systems, smart furniture and mirrors, cloud-based voice services, embedded devices, and smart TVs.
Key features include natural language processing (NLP), a customizable UI, plugin-based architecture for speech recognition (STT) and text-to-speech (TTS), customizable wake words, smart home device control, music/podcast/radio playback, timers and reminders, and an extensible skills marketplace with community-developed skills. It supports both online and offline operation, with options for local STT like Vosk or Mozilla DeepSpeech and local TTS like Mimic3.
Open Voice OS is designed for developers interested in making cutting-edge voice assistance technology available to everyone, privacy-conscious users who want control over their data, DIY enthusiasts building smart speakers from Raspberry Pi or other single-board computers, organizations looking to integrate voice into products, and anyone wanting an alternative to proprietary assistants like Amazon Alexa, Google Assistant, Microsoft Cortana, or Apple's Siri. It runs on Raspberry Pi models (3B, 3B+, 4, Zero 2), Mark I and Mark II devices, Linux desktops and laptops, and Docker containers on x86 or ARM64 platforms.
Open Voice OS pricing
Pricing model: Freemium
Open Voice OS is completely free and open source. It is released under the Apache License 2.0, which means you can use it for personal or commercial purposes, modify and distribute it, and contribute back to the project. There are no paid plans, subscription fees, or mandatory costs. The project relies on optional donations to sustain development. Pre-built images, the installer, Docker containers, and all core components are free. The skills marketplace is free to access and use. Donations are appreciated but entirely optional to help sustain hosting, development, and long-term maintenance.
Open Voice OS pros
- Completely free and open source under Apache License 2.0
- Can run entirely offline for enhanced privacy
- Full control over user data with no mandatory cloud backend
- Plugin-based architecture for STT, TTS, and wake word engines
- Extensible through community-developed skills marketplace
- Supports customizable wake words
- Works on Raspberry Pi and various single-board computers
- Docker and Python installation options available
- Pre-built images for Raspberry Pi and Mark II devices
- Multi-platform support including Linux desktops and embedded devices
- Community-driven development with global contributor base
- Compatible with Mycroft-core skills and ecosystem
- Multiple TTS options including local Mimic3
- Multiple STT options including local Vosk and DeepSpeech
- NGI Zero Commons Fund grant recipient for sustainable development
- Can create custom voice-enabled applications and APIs
- GUI support with KDE/QT framework
- Smart home device control capabilities
- No subscription fees or mandatory paid plans
Open Voice OS cons
- Default speech-to-text engine requires internet connection
- Primarily targeted at developers rather than casual users
- Requires technical knowledge to set up and configure
- Smaller skill library compared to Alexa or Google Assistant
- Some features still experimental or in development
- No official commercial support or enterprise SLA
- Setup may be complex for non-technical users
- Limited pre-built hardware options compared to commercial smart speakers
- Documentation may have incomplete or outdated sections
Frequently asked questions about Open Voice OS
What is Open Voice OS?
Open Voice OS 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. It started as MycroftOS and was renamed to avoid trademark issues. It serves as an open virtual assistant platform that enables developers and organizations to create custom voice-controlled applications, offering a powerful alternative to proprietary solutions like Amazon Alexa, Google Assistant, Microsoft Cortana, or Apple's Siri.
Is Open Voice OS free?
Yes! Open Voice OS is completely free and open source. It is released under the Apache License 2.0, which means you can use it for personal or commercial purposes, modify and distribute it, and contribute back to the project. Donations are appreciated to help sustain the project but are entirely optional.
Does Open Voice OS require internet?
By default, ovos-core does not require a backend internet server to operate. Some skills can be accessed entirely offline via command line. The default speech-to-text engine currently requires an internet connection, though self-hosted offline options like Vosk or Mozilla DeepSpeech are available. Individual skills and plugins may require internet, and most users will want internet 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 devices, Linux desktops and laptops, and Docker containers. It supports both x86 and ARM64 platforms. Pre-built images are available specifically for Raspberry Pi and Mark II devices.
How do I install Open Voice OS?
Installing OVOS is simple with two main installation methods: Docker and Python. For the Python installer, run the 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. For Raspberry Pi, download the pre-built image and flash it to an SD card. For desktops/laptops, use the Docker container or package. Detailed instructions are available on the downloads page.
What speech recognition options are available?
Open Voice OS uses a plugin-based architecture for speech recognition. The default configuration uses online services, but you can set up local/offline options like Vosk or Mozilla DeepSpeech. This allows you to choose between cloud-based accuracy or offline privacy depending on your needs.
What text-to-speech options are available?
Multiple TTS options are available including Mimic3 (local), Google TTS, Amazon Polly, and more. You can choose and configure these in your settings. Mimic3 provides local TTS processing for enhanced privacy without requiring internet connectivity.
How can I contribute to Open Voice OS?
Open Voice OS is a community project welcoming contributions of all kinds: testing and reporting bugs, writing or improving documentation, creating or enhancing skills, code contributions, translations, and community support. Visit the contribution page to learn how to get started. You can also join OpenVoiceOS Chat where team members are happy to mentor new contributors.
What can I do with Open Voice OS?
Open Voice OS allows you to create a voice assistant with customizable wake words, control smart home devices, play music, podcasts, and radio, get answers to questions, set timers and reminders, extend functionality with skills from the marketplace, and create your own skills. The functionality can be extended through community-developed skills for various use cases including home automation, entertainment, education, and more.
How is Open Voice OS different from Mycroft?
Open Voice OS started as MycroftOS but became fully independent due to trademark issues and contributions not being accepted upstream. OVOS maintains an enhanced reference fork of Mycroft-core with extra functionality while keeping compatibility with Mycroft-core skills. Many OVOS changes are submitted to Mycroft for inclusion at their discretion. OVOS is essentially the unsanctioned 'Mycroft Community Edition' with faster development and additional features.