Almond VS Speaking Email

The key feature I haven't seen any of these opensource projects implement is microphone response coordination: If you have multiple microphones and speakers, which one responds? My google home's are terrible at this: often one in another room responds, but at least it's only one. When I tried to run Genie (https://genie.stanford.edu/) I had multiple devices responding simultaneously. It was a disaster. For me,... - Source: Hacker News / over 1 year ago

It's incredibly easy to do (caveat - at least if you're familiar with software dev already). Most thermostats are literally just digital thermometers that control a relay that turns the furnace/ac on and off. A simple arduino (or much cheaper IC) can easily do the same thing if you wire it in. And then on the software side... there's several large, open-source projects that exist in this space and provide nice api... - Source: Hacker News / over 1 year ago

Because there's surely enough software available, right (i.e. susi.ai, Mycroft, Kalliope, DeepSpeech, leon, Jasper, Vosk or Genie)? Source: about 2 years ago

On the home assistants, it’s actually a cool solution. What they do is actually use a local ML algorithm to recognize the alert word (hey Google, Alexa, etc.) and only when they hear it do they stream the audio to their inference servers. There are things like almond which is entirely self hosted option I’d like to move to eventually. Source: about 2 years ago

I think a key feature of a smart speaker is the voice assistant. The only privacy aware I know of is Almond (AKA Genie) from Stanford[1]. I don't think there is any commercial speaker using Almond out there. However, Im betting you could DIY it. [1] https://genie.stanford.edu/. - Source: Hacker News / about 2 years ago

Speaking Email was supposedly built for this but the voices are awful and apparently you have to keep your screen on the whole time? Source: over 1 year ago