Nash0x7e2
Joined 7 years ago
Karma
14
Submissions
30
Member since
May 16
Joined 7 years ago
However, I did notice that connect took around a minute to a minute and a half before the agent was in the call and able to speak. Is this a byproduct of the underlying calling service you're using or the traffic?
Regardless, awesome app, curious to see how it continues to improve!
On the backend, it uses Stream's Python SDK to capture the WebRTC frames from the player, send them to YOLO to detect their arms and body, and then feed them to the Gemini Live API. Once we have a response from Gemini, the audio output is encoded and sent directly to the call, where the user can hear and respond.