Hardware

Rhasspy is designed to be run on different kinds of hardware, such as:

  • Raspberry Pi 2-3 B/B+ (armhf/aarch64)
  • Desktop/laptop/server (amd64)
  • Raspberry Pi Zero (armv6l)

The table below summarizes architecture compatibility with Rhasspy's components:

Category Name amd64 armhf aarch64 armv6l
Wake Word raven ✓ ✓ ✓ ✓
pocketsphinx ✓ ✓ ✓ ✓
snowboy ✓ ✓ ✓
precise ✓ ✓ ✓
porcupine ✓ ✓ ✓ ✓
Speech to Text pocketsphinx ✓ ✓ ✓ ✓
kaldi ✓ ✓ ✓
deepspeech ✓ ✓ ✓
Intent Recognition fsticuffs ✓ ✓ ✓ ✓
fuzzywuzzy ✓ ✓ ✓ ✓
adapt ✓ ✓ ✓ ✓
flair ✓
rasaNLU ✓ ✓ ✓
Text to Speech espeak ✓ ✓ ✓ ✓
flite ✓ ✓ ✓ ✓
picotts ✓ ✓
nanotts ✓ ✓ ✓ ✓
marytts ✓ ✓ ✓
opentts ✓ ✓ ✓
wavenet ✓ ✓ ✓ ✓
larynx ✓ ✓ ✓

Raspberry Pi

To run Rhasspy on a Raspberry Pi, you'll need at least a 4 GB SD card and a good power supply. I highly recommend the CanaKit Starter Kit, which includes a 32 GB SD card, a good power supply, and a case.

Some components of Rhasspy will not work on the Raspberry Pi 3/4 with a 64-bit operating system (aarch64). As of the time of this writing, these are:

Microphone

Rhasspy can listen to audio input from a local microphone or from a remote audio stream. Most of the local audio testing has been done with the following microphones:

Remote audio testing has mainly used the MATRIX Voice and Romkabouter's excellent MQTT Audio Streamer. For Raspberry Pi's, check out the hermes-audio-server by koenvervloesem. Some users have also reported success with the snips-audio-server package from Snips.AI. In both cases, you will need to configure Rhasspy to listen for audio data over MQTT.

You may also be interested in reading this microphone benchmarking post that the Snips.AI folks did back in 2017.