Collected sources and patterns will appear here. Add from search or the patterns library.
WebSocketFrameStream -> PipelineEventStream
Translate inbound and outbound WebSocket audio frame payloads to and from the standardized OpenAI Realtime API event protocol schema.
Problem it solves
Open-source local speech/LLM engines do not natively speak the standardized WebSocket protocols expected by front-end voice-agent clients.
Consumes
Emits
The real projects this mechanism was found in. Attribution is the point — this is how the best teams actually do it.