Real-time

WebSocket endpoints for live call monitoring and browser-based testing.

Live transcript stream

WebSocket wss://api.nextneural.ai/ws/live/{call_uuid}?token=<token>

Streams real-time transcript events for a specific call. Used by supervisor dashboards and workflow services monitoring live calls.

Authentication: Pass your API key or Firebase token as a query parameter:

?token=nn_k_your_key_here

Events received:

{ "type": "start",      "call_uuid": "cal_c1d2e3f4", "started_at": "2026-05-12T14:32:01Z" }
{ "type": "transcript", "speaker": "agent",    "text": "Hi, good morning!", "timestamp": 0.0 }
{ "type": "transcript", "speaker": "customer", "text": "Yes I was looking at that desk.", "timestamp": 6.2 }
{ "type": "status",     "status": "transfer_initiated", "target": "sales_specialist" }
{ "type": "end",        "outcome": "warm_transfer", "duration_seconds": 113 }

Connecting after the call ends replays up to 200 buffered events from a 10-minute window.

---

Browser test

WebSocket wss://api.nextneural.ai/ws/browser-test/{campaign_uuid}?token=<token>

Enables browser-based testing of a campaign without placing a real telephony call. Accepts raw PCM audio from the browser microphone and returns TTS audio and transcripts. Used during campaign setup and QA.

---

Telephony voicebot (internal)

WebSocket /ws/exotel

Entry point for the telephony provider voicebot applet. The provider opens this socket when a call connects. Not intended for direct client use.