Piper

A Home Assistant voice assistant needs three parts. Something to turn speech into text, something to turn a reply back into speech, and Assist in the middle to work out what you meant. The first two can run on plain CPU in Docker, so nothing you say has to leave the house. I built the whole stack from scratch on 11 October 2026 on Home Assistant 2026.10.1, ran text and spoken commands through it, and timed the result. This post has the compose file, the settings, the numbers and the two things that tripped me up. ...

Updated October 2026: I re-tested this on 8 October 2026 against the current rhasspy/wyoming-piper image and corrected three things I got wrong in 2023. Piper is text-to-speech, not speech recognition. Port 10200 isn’t a web interface. And voices are now named like en_GB-alba-medium. The compose file also no longer needs a version line. The Home Assistant steps are unchanged from the original and I haven’t re-run them on a current release. ...