2023 was the Year of the Voice. It was a yearly goal to let users control Home Assistant in their own language. What we built during the Year of the Voice allows almost anyone to build a voice assistant that embodies our Open Home values perfectly: Personalized, Private, and Sustainable. Every component of our voice assistants can be heavily customized to fit your language, your style, and your needs. Fully local options exist for each of them, and finally, you can retrofit your voice assistant into anything, even a 1970s Walkie Talkie found in a flea market!
In this live stream, we explain how each component works and guide you through building your own voice assistant!
We wanted to celebrate what our voice assistants can enable within the community and launched a voice assistant contest! You can learn more about the contest here: https://www.home-assistant.io/blog/20...
And check out our announcement blog of the winners: https://www.home-assistant.io/blog/20...
Chapters:
0:00:00 - Intro
0:07:59 - The contest Specifics
0:20:18 - Everything you need to know to use voice in Home Assistant
0:23:42 - Using Assist via text on Home Assistant
0:25:46 - Using Aliases on Entities and Areas to create more natural sentences
0:27:32 - Exposing specific entities to Assist
0:28:31 - Create our own trigger sentence easily with automations
0:31:29 - Setting up a Voice pipeline with Home Assistant Cloud
0:34:48 - Setting up a Local Voice pipeline with Whisper and Piper
0:39:45 - An example of a local Voice pipeline on better hardware
0:41:30 - Setting up openWakeWord on our Voice pipelines
0:46:16 - Setting up porcupine1 on our Voice pipelines
0:49:25 - Create your own wake word with openWakeWord
0:51:00 - Using community wake word in openWakeWord
0:54:27 - Building a voice assistant based on Wyoming Satellite
1:01:37 - Local Wake Word detection on a Wyoming Satellite
1:07:53 - Building a voice assistant based on ESPHome
1:08:58 - Presenting the components we will use
1:12:54 - Wiring all the components
1:23:55 - Building the first version of the firmware
1:46:47 - Improving the firmware with noise suppression and LED feedback
2:01:32 - Adding the ability to mute our voice assistant
2:11:32 - Building the last version of the firmware
2:20:00 - Wrapping up