Using Python & OpenAI Realtime API: Live Audio Demo + Function Calling to Talk with Your local PC

[@catalyst9259]

Thankyou, needed to know how to function call

[@frankfu007]

@@catalyst9259 I have the function calling in the source code.

[@catalyst9259]

@@frankfu007 Yes, I referred that that's for that I am saying thankyou 🫶

[@oussamajmaa9205]

Thanks for the video ! Is there a pre-built method to stop the realtime api automatically when the user is not speaking ( no speech detected) like a timeout attribute or something similar ? thanks in advance .

[@frankfu007]

You could try to mute the mic. Here is the demo kzbin.info/www/bejne/eIu1g6qlmNxqZ7M This will not send any thing to the openAI. It will reduce the cost.

[@mikew2883]

Very cool! 👍

[@marouanbelhaj7881]

You should get a lot more views, thank you!

[@frankfu007]

I hope so, thanks for the support!

[@soulless8471]

U Rock!

[@frankfu007]

Thanks

[@soulless8471]

@@frankfu007 can you help me to implement that in django, at least give some tips (sorry about my english, i'm from Angola/Africa)

[@frankfu007]

Sure. I will try make another video.

[@soulless8471]

@@frankfu007 really? U r the best! thank you"

[@orsemcore]

hi, i'm getting this error on run. Failed to connect to OpenAI: Error connecting to SOCKS5 proxy 127.0.0.1:10808: [WinError 10061] No connection could be made because the target machine actively refused it

[@frankfu007]

Let me take a look. Something may need update.

[@AgustinKuster]

@@frankfu007 Having the same problem here, but on Mac Os, still looking for a fix to share you guyss

[@kangaroobr759]

Same here !

[@frankfu007]

Let me take a look.

[@frankfu007]

hey, Just remove the line 14 socks.set_default_proxy(socks.SOCKS5, "127.0.0.1", 10808) I am going to update the repos.