Voice - Chapter 7 - Supercharged wake words and timers 

What a fabulous voice release. Super stoked about microWakeWords running multiple models even on the old ESP chips. And timers! multiple! Thanks team and welcome to Nabu Casa Kevin 🙂

Decade of voice is coming along well!

Timers are awesome! Great progress! Being able to show the timers on a dashboard is important to me personally. Exposing the timers as an array of timers like the Alexa plug-in does could be a good place to reference.

Continued conversation is so great ! Please hope it’s going to be released as soon as possible

Excited to see what you can do Kevin working full time on this! Please please improve media interaction (specifically being and to play RU-vid by voice) and better official voice hardware with good mics

Like this!!!!

I follow your description related to the voice assistance personality and just to simplify... if you ask to OpenaAI to change personality (without to write the relative automation) it will change the text. The only one automation needed is the reset. Thnaks for all!!!

For the next streams, could you please consider to somehow level the volumes? Jlo is very loud, while Mike was hard to understand. This would be a big improvement for the generally awesome talks 😊

Great job so far. I hope you’ll be able to eliminate the awkward pause currently necessary after the wake word. I’m sure that if my Echo from 10 years ago can react to my merciless prompts without any delay after “Alexa”, you’ll pull it off too! 👍

I love the work going into this and I am super grateful for everything the Nabu Case and the volunteers do. I'm a little concerned with the way timers are being introduced. Shouldn't services and entites be made first, and then voice intents be introduced that works on those entites and services? I feel like the project could fall into a trap of having features that work in voice that don't work elsewhere. Voice should just be another interface to the HA backend. I know you mentioned that further integration with HA is coming, but it just seems like the development is happening in the wrong area or order. I'm sure there's good reasons it's happening this way but if we don't have an answer for "transient entites" yet, shouldn't that be solved first before putting this functionality in the voice layer?

I am currently working on a kit for raspberry pi zero 2w with the hat and a nice speaker. I would love to get more info on that noice cancelling chip.

Is it possibly to get Assist to act on an Yes and No? Like, an automation ask if I want lights in the kitchen. And I answer 'Yes', 'No'. Like the amazone alexa?

Is nabu Casa going to make a smart speaker

where can I buy such kind of small ESP micro device to get started with voice feature? Available in Germany would be best

Just thinking through these assistants. Is it possible for example to have a esp 3s box set up in my sons room, using ai conversation make that device only use a specific assistant ie one that has prompting to call my son by his name, and respond in a fun way that a 12yr old boy would like. And only allow it to control only the things in his room? If that makes sense?