Rhasspy has moved and improved!
This repository contains code for an older version of Rhasspy (2.4).
Rhasspy (pronounced RAH-SPEE) is an offline voice assistant toolkit inspired by Jasper that supports many languages. It works well with Home Assistant, Hass.io, and Node-RED.
A newer version of Rhasspy (2.5) is available at https://github.com/rhasspy/rhasspy
Rhasspy transcribes voice commands into JSON events that can trigger actions in home automation software, like Home Assistant automations or Node-RED flows. You define custom voice commands in a profile using a specialized template syntax, and Rhasspy takes care of the rest.
To run Rhasspy with the English (en) profile using Docker:
docker run -d -p 12101:12101 \
--restart unless-stopped \
-v "$HOME/.config/rhasspy/profiles:/profiles" \
--device /dev/snd:/dev/snd \
synesthesiam/rhasspy-server:latest \
--profile en \
--user-profiles /profiles
Then visit the web interface at http://localhost:12101 See the web interface documentation for a brief tour of what you can do.
Rhasspy currently supports the following languages:
- English (
en) - German (
de) - Spanish (
es) - French (
fr) - Italian (
it) - Dutch (
nl) - Russian (
ru) - Greek (
el) - Hindi (
hi) - Mandarin (
zh) - Vietnamese (
vi) - Portuguese (
pt) - Swedish (
sv) - Catalan (
ca)
The table below summarizes language support across the various supporting technologies that Rhasspy uses:
| Category | Name | Offline? | en | de | es | fr | it | nl | ru | el | hi | zh | vi | pt | sv | ca |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Wake Word | pocketsphinx | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ||
| porcupine | ✓ | ✓ | ||||||||||||||
| snowboy | requires account | ✓ | • | • | • | • | • | • | • | • | • | • | • | • | • | |
| precise | ✓ | ✓ | • | • | • | • | • | • | • | • | • | • | • | • | • | |
| Speech to Text | pocketsphinx | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ||
| kaldi | ✓ | ✓ | ✓ | |||||||||||||
| Intent Recognition | fsticuffs | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ |
| fuzzywuzzy | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | |
| adapt | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | |
| flair | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ||||||||
| rasaNLU | needs extra software | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | |
| Text to Speech | espeak | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ |
| flite | ✓ | ✓ | ✓ | |||||||||||||
| picotts | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ||||||||||
| marytts | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ||||||||||
| wavenet | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ |
• - yes, but requires training/customization
For more information, please see the documentation.
Rhasspy is intended for advanced users that want to have a voice interface to Home Assistant, but value privacy and freedom above all else. There are many other voice assistants, but none (to my knowledge) that:
- Can function completely disconnected from the Internet
- Are entirely free/open source
- Work well with Home Assistant, Hass.io, and Node-RED
If you feel comfortable sending your voice commands through the Internet for someone else to process, or are not comfortable with rolling your own Home Assistant automations to handle intents, I recommend taking a look at Mycroft.
For users who are also coders, pull requests for bug fixes or new components are always welcome and much appreciated!
If you can speak/write one of the supported languages, I would love to hear your feedback about that language's profile. I only speak English, so I rely on users of Rhasspy (and Google Translate) to help me write example sentences and create test WAV files.