🔀 Juxano WebSocket Load Balancer

Audio stream multiplexer that routes mic and system audio to separate transcription backends, merging responses with speaker attribution.

Endpoints

EndpointDescription
/wsWebSocket connection endpoint
/healthHealth check

Audio Type Routing

Send binary WebSocket frames with a type byte prefix:

PrefixTypeSpeakerBackend
0x01 Microphone you MIC_BACKEND_URL
0x02 System Audio other SYSTEM_BACKEND_URL

Authentication

If API_KEY env var is set, authenticate via query parameter:

ws://host:port/ws?api_key=YOUR_KEY

Response Format

Transcription responses:

{
    "id": "uuid",
    "text": "transcribed text",
    "final": false,
    "rev": 2,
    "lang": "en",
    "speaker": "you" | "other" | "person:N"
}

System Messages

{
    "id": "uuid",
    "type": "connected" | "error" | "disconnected",
    "message": "description"
}