All Models

Grok STT

grok

Speech transcription model for accurate audio-to-text and captioning workflows

Providers1
ReleasedMar 16, 2026
Input Modalitiesaudio
Output Modalitiestext

Available Providers (1)

ProviderModel IDInput CostOutput CostContextMax OutputDocs
Vercel AI Gatewayspacexai/grok-stt—/MTok—/MTok——

Capabilities

Reasoning
Tool Calling
Attachments
Open Weights
Structured Output