jxlarrea/wyoming-voice-match

A Wyoming protocol ASR proxy that verifies speaker identity and isolates voice commands from background noise before forwarding audio to a downstream speech-to-text service. Designed for Home Assistant voice pipelines to prevent false activations from TVs, radios, and other people - and to deliver clean transcripts even in noisy environments.

31
/ 100
Emerging

This project helps Home Assistant users ensure their voice commands are accurately recognized, even in noisy environments. It takes audio captured by a smart home microphone, verifies it's your voice, and removes background noise like TV dialogue or other people talking. The result is a clean audio stream that prevents accidental actions and delivers precise transcripts to your speech-to-text service. This is for anyone using Home Assistant for voice control who struggles with false activations or garbled commands.

Use this if you want to make your Home Assistant voice commands more reliable by filtering out background noise and ensuring only your voice is processed.

Not ideal if you don't use Home Assistant or if your voice commands are already perfectly accurate in quiet environments.

smart-home-automation voice-control home-assistant speech-recognition noise-reduction
No Package No Dependents
Maintenance 10 / 25
Adoption 7 / 25
Maturity 11 / 25
Community 3 / 25

How are scores calculated?

Stars

34

Forks

1

Language

Python

License

MIT

Last pushed

Mar 11, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/jxlarrea/wyoming-voice-match"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.