AI in Webex
Overview
Media Forking streams audio from a live conversation between an agent and a caller to an external endpoint for real-time processing.
anchorOverview
anchorWhen the Media Forking activity runs for a live-agent conversation, Webex Contact Center establishes a gRPC connection to the registered partner endpoint. Webex Contact Center acts as the gRPC client, and the partner endpoint acts as the gRPC server.
The endpoint controls how it processes the received media. The Media Forking sample code provides an implementation example.
Use a publicly reachable TLS endpoint. Each media RPC carries a signed JWS in the gRPC authorization metadata; validate it before processing audio.
anchorHow it works
anchor- Flow Designer runs the Media Forking activity for the live-agent conversation.
- Webex Contact Center opens a bidirectional gRPC stream to the partner endpoint.
- The client sends conversation audio in
ConversationAudioForkingRequestmessages. - After the client half-closes the request stream, the server sends one
ConversationAudioForkingResponsefor the call and closes the response stream. The response can contain acknowledgment, status, or error information.
anchorMedia stream
anchorEach request identifies the conversation and customer organization. Its audio payload includes the raw audio bytes, encoding, sample rate, capture timestamp, participant role, and role ID.
The CALLER and AGENT roles identify the source of each stream. The schema defines LINEAR16, MULAW, and ALAW audio encodings. How the endpoint stores or processes the raw audio is implementation-specific.