Voice assistants
Wake words run on the display. Audio goes only where your Assist pipeline sends it.
Two assistants
Section titled “Two assistants”Assistant 1 and Assistant 2 each have their own wake word, Assist pipeline, sensitivity, sounds and timing. Use one for Home Assistant’s own assistant and the other for, say, a cloud LLM. A slot with no wake word is off.
Set it up
Section titled “Set it up”-
In Home Assistant, open the display’s Assistant 1 device.
-
Pick an Assistant (Assist pipeline) and a Wake word. Custom wake words added to Home Assistant are listed too.
-
The display downloads the wake word and starts listening.
You can also pick the wake word under Settings → Voice assistants. That needs Allow the device to perform Home Assistant actions turned on for the display in the ESPHome integration; without it the row is dimmed.
Starting without the wake word
Section titled “Starting without the wake word”- Talk now on the assistant’s settings page.
- From Home Assistant: the Wake button on the assistant’s device (
wake_assistant_1,wake_assistant_2).
On the screen
Section titled “On the screen”Settings → Voice assistants has a page per assistant:
-
Talk now
-
Wake word
-
Wake word sensitivity: higher wakes more easily, with more false wakes. In Home Assistant the same setting is a threshold (0.5–0.99, default 0.85) where lower wakes more easily
-
Wake sound: a chime, a custom tone, or none
-
Response playback: Stream starts sooner and can stutter on a slow network; Download first waits for the whole answer
-
Visuals: a visual for listening, thinking and replying, in the panel or full screen
Timing, follow-up and recordings
Section titled “Timing, follow-up and recordings”These are only in Home Assistant, on each assistant’s device:
| Setting | What it does | Default |
|---|---|---|
| Follow-up time | Keep listening after a reply, so you can ask again without the wake word (0–30 s) | 0 |
| Max listening time | Stop listening after this long (5–60 s) | 15 s |
| Max thinking time | Give up waiting for Home Assistant after this long (5–300 s) | 90 s |
| Reply buffer | How much of a streamed reply to collect before playing (0–3000 ms) | 650 ms |
| Recordings kept | Keep the audio of the last N requests (0–10) | 0 |
The Last wake word, Last heard and Last reply sensors show the most recent turn.
Say “stop”, no wake word needed, or tap the screen. It stops, in order: a ringing alarm or timer, the assistant, an announcement, then pauses music.
Stop word sensitivity in Home Assistant (0.5–1, default 0.7) sets how sure it has to be; 1 turns it off.
Voice triggers
Section titled “Voice triggers”Settings → Voice triggers turns on and off the things you can say to the display. Each has its own switch on the Voice triggers device in Home Assistant, under an All actions or All commands switch for its group. All are on to start with.
Commands
Section titled “Commands”Commands need no wake word and are heard on the display itself:
| Say | Does |
|---|---|
| “radar”, or “show me the weather radar” | Opens the Radar app |
| “mirror” | Opens the Mirror app, on displays with a camera |
Actions
Section titled “Actions”Actions are said to your assistant, after the wake word:
| Say | Does |
|---|---|
| “call the kitchen”, “ring the kitchen”, “intercom the kitchen” | Calls that device on the intercom |
| “video call the kitchen” | A video call, on displays with a camera |
| “broadcast” or “announce”, then your message after the tone | Sends what you say to every other device in your home (Broadcasts) |
| “broadcast dinner is ready” | Sends the words, spoken by your Assist pipeline’s voice |
Device names don’t have to match exactly; the closest one is called.
Actions need the companion Home Assistant integration, installed through HACS. Until it is installed and up to date, Settings → Voice triggers shows a warning row; tap it for a code to scan that opens the integration in HACS.
Timers
Section titled “Timers”“Set a timer for ten minutes” starts a timer and shows a countdown. See Messages, timers and alarms.