Filtered by topic: Home Assistant Clear ✕
… And now you're ready to construct your voice assistant profile. Go to your Settings , select Voice Assistants , and create a new pipeline profile. Map your Speech to text field to Whisper and set your Conversation Agent to Home Assistant. Choose your preferred local voice profile in Piper. …
… However, things are vastly different now that HASS supports voice satellite functionality on its Android companion app, which lets me trigger my entire voice assistant pipeline using hot words from an old phone instead of a wake-word detection channel involving microcontrollers and external microph… …
… But that’s where custom voice pipelines come into the equation… My phone became a killer HASS control hub once I tossed custom assistants into the fray I went with local LLMs for a completely self-hosted setup As a Home Assistant tinkerer with a couple of years under my belt, I’ve already set up my… …
… Replacing Google Assistant with a local LLM A private voice assistant that works locally With the help of a local LLM and Home Assistant’s voice pipeline, I built a private voice assistant that works locally. …
… But its voice assistant capabilities are just incredible Ever since the March 2026 update added voice satellite capabilities to the Home Assistant Companion app, my smart home management platform has become an all-in-one voice-controlled command station. …
… Related I turned my old laptop into a dedicated Home Assistant hub in under an hour Turns out, a decade old laptop has enough juice to control my smart home gadgets I use my phone-powered Home Assistant satellite all the time It’s even more effective with an AI-powered voice assistant pipeline If y… …
… That’s a rather low bar for a feature positioned as an upgrade to a voice assistant. …
… Related Home Assistant's latest beta finally turns your Android phone into a voice satellite You can now use your phone as a true voice assistant for Home Assistant. …
… Fortunately, Open WebUI supports local image generation, TTS, and STT models. I’ve already got a ComfyUI pipeline for upscaling images, while Speaches provides the models for my Open WebUI voice assistant. …
… I don't have a typical English accent, and it still handles my voice quite well without mispronouncing words. …