Why is google speech needed?

[wcoebergh]

Hello,

I'm curious to why google speech is needed to initialize sonus, while it is advertising to be offline. The main reason I am not using any cloud software for speech is that I don't want a recording device at all time in my house that connects to the internet.

Regards!

[evancohen]

Google speech is needed for the streaming part of Sonus. In a nutshell:

• Listen offline for hotword
• Detect hotword
• Stream audio to X cloud recognizer (currently Google is the only one supported, working to get more)
• Stop streaming audio after the end of the utterance.
• Repeat...

Your audio won't be streamed to google unless the hotword is detected, and even then it's only for a single utterance. The object required to stream speech isn't initialized until a hotword is detected, but the gRPC connection to google is created on start to make things simple.

Hope that answers your question 🚀

[wcoebergh]

Hi,

Thanks, yes it does answer my question. I thought you just tried to be the offline hotword part! Would it be possible for an implementation of just that?

[evancohen]

Totally! Check out Snowboy: https://github.com/Kitt-AI/snowboy

[wcoebergh]

Yeah boyyy 🚀 Thanks for the help, keep up the good work!