For sure I hope too, that we can utilize more features of the box-3. For now it’s a nice additional VA.
I think, it would make sense to use the presence sensor in combination with VoiceAssist (getting activated, when presence is detected, else, sleep - or similar scenarios)
Great idea! 
Can anyone offer up an option on the performance as a VA input/output device? I used Rhasspy for a while with a ReSpeaker Mic Array v2.0. It worked ok, but not great. It was fine in a quiet room, but if music or the TV were on performance would drop off significantly.
@bkprath I don’t have any experience with Rhasspy but here are my 2 cents: It might be an unfair comparison but compared to Amazon Echo for example VA is way behind, no matter on which device you install it. BUT VA has made a big step forward since the release of Year-of-the-Voice Chapter 4. If it develops further at that speed it might eventually get there.
The biggest issue for me right now with Box-3 is that the speaker volume is very low. You hardly can hear a response even in a quiet room. I tried to increase the volume by increasing the “volume_multiplier” setting but that didn’t change anything. So no matter how it performs otherwise, it is not very useful right now.
I also tested a homeassistant-satellite https://github.com/synesthesiam/homeassistant-satellite on raspberry 3b using a USB conference system. As a VA this is much better because it has better mics and a much loader speaker. On the other hand this is more expensive and the form factor is not as nice as the Box-3.
My approach right now is to get experience with VA on various devices hoping that in the meantime VA will develop to become a great solution.
What microphone did you utilize with your homassistant-satellite? I tried two different mic arrays from the same company and wasn’t satisfied with either when i used rhasspy. I didn’t have any auto output problems, it was mic pickup and detection in the presents of auto output that gave me trouble.
After testing the BOX3 VA performance I agree it’s still much work ahead.
For me the most important is to allow independent speaker and microphone devices usage in the pipeline.
Have several HA integrated speakers of much better quality than the small speaker in Echo/Box3 and waiting until I can use these for output…
Also have some separate microphones without speaker “ReSpeaker USB mic Array”, “PS3 Eye USB” or M5Stock AtomU which is partly working in ESPhome but needs support for sending audio to some HA speaker…
Hi all!
On @m4v3r1ck post above, I see the “Top Left Button” reachable by Home Assistant.
While mine, shows like this “This Entity is unavailable”:
I’ve tried to edit the yaml on espHome, changing this to “false”:
binary_sensor:
- platform: gpio
pin:
number: GPIO0
mode: INPUT_PULLUP
inverted: true
name: Top Left Button
disabled_by_default: true
But I can’t save after editing this (probably a different issue, but thought to mention this try)
Any ideas?
PS: I was about to post as an issue on “Issues · esphome/firmware · GitHub”, but as I notice Maverick post, likely is something with my install, not with whole ESP thing…
If your VA is based on a device that runs some kind of Linux, e.g. Raspberry Pi with Raspberry Pi OS, then you can install MPD (https://github.com/MusicPlayerDaemon/MPD in addition to your VA software. That gives you a media player in HA that you can use to output vioce. I have homeassistant-satellite and MPD running in parallel just fine.
Have HassOS installation on OdroidC4 and already use 2 network devices running MPD daemon for TTS and audio automations/notifications.
But I still haven’t figured out how to configure the VA pipeline to use them together with independent microphone device…
Seems to me VA at this moment only supports combined(microphone+speaker) devices.
Agree, I think so too.
Did this and it worked like a charm. I can talk with gpt4, but I can’t control any of my devices or read sensors or anything. It could definitely be my home assistant setup though bc I really don’t know home assistant very well.
Gpt cannot control your HA entities because it does not know them. That is a limitation right now and it may not change in the future either but I’m not sure.
Sorry for my late reply.
Select the “top left button” entity
Select settings symbol left to the three dots and enabled the entity:
It may take up to 30 seconds for the entity to show enabled.
Yeah I was thinking that might be the case. It’s all good, I got other stuff that can do that, but it would definitely be cool to have one unified assistant.
On an unrelated note, when I went to sleep last night everything was working, but when I woke up this morning, the screen was off, but the voice assistant was still working. I reset it but it went back to the same state. When I received it initially the screen was popped off the front and kind of stuck to the foam when I opened the box. I just snapped it back j and it seemed tobe fine and it didn’t move over night. Not sure how to proceed really. I guess I’ll try reflashing it and restarting everything and if that doesn’t work I’ll crack it open and take a look.
OK, edit number 2. Turns out I just had to press the factory reset button in esphome and it rebooted and the creen came back on. Has anyone been able to get openai tts to work? I can just get it working with piper and the homeassistant tt, but I’d really like to use openai tts.
Yesterday I have inserted the new/charged battery inside the sensors case and expected it to provide power for the box but nothing.
Battery is “PURFIELD 18650 battery original NCR18650B 3.7V 3400 mah rechargeable lithium”, fully charged.
Has anyone managed the battery sensor working reporting voltage?
What type/number battery do you use?
= N/A
Thanks for pointing me to the docs…
Seems there is a mechanical switch that needs toggle 
Will test later after return home.
P.S. After switch toggle the box is fully working on battery, just don’t know for how long Still no clue how to read the battery voltage, found only this file but there are no GPIO details: https://github.com/espressif/esp-box/blob/master/components/bsp/src/boards/esp32_bsp_sensor.c
But no problem, can wait until more details are available…
My bad! 
For english default sentences you can check the options here:
https://github.com/home-assistant/intents/tree/main/sentences/en
Weather example:
language: en
intents:
HassGetWeather:
data:
- sentences:
- "<what_is>[ the] weather[ like]"
- sentences:
- "<what_is>[ the] weather[ like] (for|in|at) <name>"
- "<what_is>[ the] weather (for|in|at) <name>[ like]"
- "<what_is>[ the] <name> weather[ like]"
requires_context:
domain: weather
Has anyone gotten the OpenAI TTS to work? It just doesn’t work at all when I put it in the pipeline and it gives me an error when I try to test it in the pipeline settings. Also, I didn’t like the default pictures so I changed them and I tweaked the VAD and the mic settings a bit. I’m not artist but I like this better than what they had. I also added a page for the mute button, and I don’t know if it’s just this config file or if it just doesn’t work, but whenever I unmute the box stops working until I reset it. It just doesn’t pick anything up.
EDIT: I’m trying the new .yaml that is supposed to have mute, but mute still isn’t working for me. 