Self-host wyoming-openwakeword
v2.1.0Self-hosted wake word detection via Wyoming protocol
- Stars
- 207
- Port
- 10400 (Wyoming protocol TCP server for wake word detection)
- Requires
- Python
rhasspy/wyoming-openwakewordWhat is wyoming-openwakeword?
Wyoming openWakeWord is a Wyoming protocol server that wraps the openWakeWord wake word detection system. It allows self-hosted voice assistants like Home Assistant to detect wake words locally by connecting over TCP. The server supports custom wake word models in .tflite format, adjustable detection thresholds, and zeroconf discovery for Home Assistant. It can be run via Docker or a local Python virtual environment. The project is in alpha development status and requires Python 3.9 or newer.
Should you self-host wyoming-openwakeword?
wyoming-openwakeword scores 45/100 on selfhost.directory (how scoring works) and ranks #7 of 11 in Voice Assistants. It has 207 GitHub stars.
It shipped 1 stable release in the past year. The latest, v2.1.0, came out on 30 October 2025.
Setup is moderate: expect some configuration beyond a single command. An official Docker image is available. It is Apache-2.0-licensed and written mostly in Python.
Its closest alternative on selfhost.directory is dograh (70/100, 5 972 stars). It scores higher overall, so compare the two before you pick. See wyoming-openwakeword vs dograh side by side.
Features
- Adjustable detection threshold
- Custom wake word models
- Wake Word Detection
wyoming-openwakeword README
More in Voice Assistants
wyoming-piperSelf-hosted Wyoming protocol server for Piper TTS, providing neural text-to-speech for Home Assistant and Wyoming clients. Open-source, runs locally via Docker or Python.
Yandex Smart HomeOpen-source Home Assistant component exposing devices to Yandex Alice and VK Marusia voice assistants via cloud or direct connection.
AgenticSeekSelf-hosted, open-source alternative to Manus AI: a voice-enabled agent that browses the web, writes and runs code, and plans tasks on local LLMs.
asknavidromeAskNavidrome is an open-source Alexa skill that streams your music from a Subsonic server like Navidrome to Amazon Echo devices, without subscription fees or ads.
audiobook-studioSelf-hosted open-source app for producing audiobooks locally using XTTS voice cloning, with optional Voxtral cloud voices. Multi-voice, segment repair, chapter assembly
dograhSelf-hosted open-source voice AI platform: build phone agents in a visual workflow editor with BYOK LLM/STT/TTS and telephony — an alternative to Vapi and Retell.
FlexTVFlexTV is a self-hosted open-source bridge between Plex Media Server and Google Assistant, Alexa, and Chromecast for voice control.
FlowcatFlowcat is an open-source, self-hosted Rust runtime for real-time voice agents — single binary, no hosted control plane, native SIP/RTP/WebRTC, 80+ provider connectors.
fosscordSpacebar is a free, open-source, self-hosted Discord-compatible platform for chat, voice, and video. Run your own server with existing Discord clients and bots.
ha-bridgeha-bridge is a self-hosted, open-source Java app that emulates the Philips Hue Bridge API, letting Alexa and Google Home control non-Hue devices.
J.A.R.V.I.SSelf-hosted, open-source voice assistant with local Whisper STT, ElevenLabs TTS, and a browser-based holographic HUD to control the Hermes autonomous agent on your LAN.
JasperSelf-hosted, open-source voice assistant you run on a Raspberry Pi, with pluggable speech recognition, text-to-speech, and Python modules for weather, news and Spotify.
0 comments