xAI
xAI is an AI research lab founded by Elon Musk. The xAI API exposes Grok foundation models for chat, function calling, vision, voice, image generation, and video generation, alongside research outputs from the Colossus training supercluster.
5 channels
across 1 AsyncAPI spec
· Provider profile
Channels
-
Client-to-server events for the voice agent: session configuration, conversation item creation, response requests, and input audio buffer management.xAI Realtime WebSocket APIs
-
Server-to-client events for the voice agent: session lifecycle, conversation item events, response streaming (text + audio), transcription of user input, function-call argument completion, and error exAI Realtime WebSocket APIs
-
Client streams audio to the STT server. Audio is sent as binary WebSocket frames containing raw PCM (16-bit signed little-endian), mu-law, or A-law samples matching the `encoding` query parameter. RecxAI Realtime WebSocket APIs
-
Client signals end-of-audio. After the server emits transcript.done, the connection is closed.xAI Realtime WebSocket APIs
-
Server-to-client transcription events for the STT session.xAI Realtime WebSocket APIs