I wanted to share a little project I hacked together tonight. It's a Python script that performs an interesting task - it listens to my voice and, when it detects silence, it records my speech into a WAV file. This is just the initial step. The WAV file then goes to OpenAI's Whisper for transcription. Afterward, the transcribed text is processed by GPT-3.5-turbo to determine if I'm attempting to make a function call. If a function call is detected, it's sent to my Homey's API, which subsequently controls my Twinkly lights in the tree. Practically, what does this mean? It allows for a unique interaction with my home automation system. I can now use any tone, any choice of words, and any language to command my home automation. This setup offers a new and interesting way to engage with smart home technologies.
-
Notifications
You must be signed in to change notification settings - Fork 1
Use OpenAI API to transcribe voice commands, send them to GPOT that does function calls to thge Home Pro API.
License
fltman/GPTHomey
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Folders and files
Name | Name | Last commit message | Last commit date | |
---|---|---|---|---|
Repository files navigation
About
Use OpenAI API to transcribe voice commands, send them to GPOT that does function calls to thge Home Pro API.
Resources
License
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published