Built for voice agents that can't wait 600ms

xAI: Grok Speech to Text

xai/grok-stt
Speech to textactive

xAI's Grok speech-to-text: transcribes audio files in a single call or streams audio in real time over WebSocket, returning word-level timestamps. Selected by endpoint (/v1/stt); there is no model parameter.

ProviderSlugPriceLatencyUptime