Inspiration
Big tech bros can use their closed-source smart homes to essentially spy on users. We've mitigated centralized control by performing diverse queries and keeping everything transparent.
What it does
He can play music, answer questions, define words, and rap.
How we built it
We start by getting an audio stream, using Google's speech processing engine to transcribe it, and then treat the transcription like a command to be processed.
Challenges we ran into
The biggest challenge was trying to get the input sensitivity at a level that optimizes performance.
Accomplishments that we're proud of
We got something working with multiple web API's within 12 or so hours. The voice recognition is also not terrible, but it definitely needs some improvement.
What we learned
Accurate and precise live voice processing is hard, man.
What's next for OpenSmartHome
Anthony is still kinda dumb, but together, through the power of open source contributions, he can maybe one day become useful in the real world.
Log in or sign up for Devpost to join the conversation.