 It's here! π We're very excited to share with you the future of open voice, the Home Assistant Voice Preview Edition! This has been 2 years in the making - we look forward to taking you on this journey with us. π Find more details here: https://www.home-assistant.io/voice-pe/ Catch up on the news in our blog here: https://www.home-assistant.io/blog/2024/12/19/voice-preview-edition-the-era-of-open-voice/ 22 comments
 @GregArcus very cool that you felt the need to yell that out to the world XD @homeassistant Instabuy! Congratulations for not only launching a great product, but a new era of local voice assistants! @danvolchek @homeassistant I'm pretty sure that document is out of date and they're doing the wake word processing on the device itself now  @thibaultmol @homeassistant Oh - I think you're right. The "Which wake words can I select?" FAQ describes an "on-device wake word engine called microWakeWord". Thanks, missed that :)  @danvolchek @thibaultmol @homeassistant It works really well too. I am using it with I just found this on ESP32S3 Box (https://a.aliexpress.com/_EGJE1X6) and the wake word detection is great :)  @danvolchek @homeassistant if this is ever the case I hope this approach stays as an option. I actually have use cases for both @homeassistant Ordered already, will be interesting to see how much better it works than the S3-BOX-3 which struggled unless the room was dead quiet. Will hopefully be doing all the processing locally on a 13th gen i3 NUC.  @homeassistant got one on order as I tried the m5atom thing and it hardly ever heard me. I would love to give Alexa the boot outta here @homeassistant Very cool! I have to admit, I've been too busy to investigate @homeassistant Assist so far (the Alexa integration is great and does what I need), but this is very tempting.  @homeassistant I canβt find what models are used in Home Assistant Cloud. Are these the same models you can run locally (on you HA server)? @homeassistant is it possible to get a little more detail around the hardware requirements for local processing? Intel N100 is mentioned for English/Spanish, but lot of conflicting info if one searches hw requirements for the whisper base model, especially as it regards GPU, memory, etc. @wesgeorge @homeassistant I am running local processing on N100. It handles small models really well, reaction times are really good and while it could be better, the accuracy is fine and totally usable :) Saw this in a Jeff Geerling video π Finally an open source, private and local voice assistant to try out π Also useful for visually impaired people for inclusion. @homeassistant Oh, local distributor finally has it on stock, I'll likely have mine tomorrow :) |
Gregory's Server
@homeassistant So excited for this! I already ordered one π