rhasspy
An offline, open-source voice assistant toolkit for home automation, supporting multiple languages and privacy-focused self-hosting.
What is rhasspy?
Rhasspy is an offline voice assistant toolkit that transcribes voice commands into JSON events for home automation. It allows users to define custom voice commands and integrates with systems like Home Assistant and Node-RED, operating entirely without an internet connection to ensure privacy.
Advanced users and developers who want a privacy-focused, offline voice interface for home automation, particularly those using Home Assistant, Hass.io, or Node-RED.
Developers choose Rhasspy for its complete offline functionality, open-source nature, and seamless integration with popular home automation platforms, offering full control and data privacy without relying on cloud services.
Overview
Rhasspy voice assistant for offline home automation
Use Cases
Best For
- Building a privacy-focused voice-controlled smart home system
- Creating custom voice commands for Home Assistant automations
- Developing offline voice interfaces for IoT projects
- Integrating voice control into Node-RED flows without internet dependency
- Supporting multi-language voice interactions in home automation
- Self-hosting a voice assistant to avoid cloud data processing
Not Ideal For
- Projects requiring high-accuracy, cloud-based speech recognition for complex natural language queries
- Users seeking a plug-and-play voice assistant with minimal configuration and technical setup
- Applications needing extensive language support beyond the 15 listed, especially for less common languages
- Environments where internet connectivity is reliable and cloud privacy concerns are not a priority
Pros & Cons
Pros
Operates entirely without an internet connection, ensuring data privacy and independence from cloud services, as core to its philosophy.
Seamlessly works with Home Assistant, Hass.io, and Node-RED, triggering automations via JSON events for tailored smart home control.
Supports over 15 languages, including English, German, and Spanish, with a detailed table showing compatibility across speech components in the README.
Allows defining commands using a specialized template syntax in profiles, enabling flexible and tailored interactions for home automation.
Cons
This repository is for version 2.4, with a newer version available elsewhere, leading to confusion and potential maintenance issues for users.
Requires understanding of Docker, profile configuration, and multiple speech technology options, making it inaccessible for non-technical users.
Offline engines like pocketsphinx may have lower accuracy, especially for non-English languages, and often require training or fine-tuning, as noted in the README table.
Frequently Asked Questions
Related Projects
TTS🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
DeepSpeechDeepSpeech is an open source embedded (offline, on-device) speech-to-text engine which can run in real time on devices ranging from a Raspberry Pi 4 to high power GPU servers.
mycroft-coreMycroft Core, the Mycroft Artificial Intelligence platform.
DDSPDDSP: Differentiable Digital Signal Processing
Found a gem we're missing?
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.